Does higgsfield-ai-prompt-skill auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Is higgsfield-ai-prompt-skill free?

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Content

Plugin

higgsfield-ai-prompt-skill

A comprehensive Claude skill library for generating high-quality prompts on Higgsfield AI — the cinematic video and image generation platform.

FLOW.md

osidemedia@osidemedia

GitHub

Plugin Signal85/100Strong

maintained99

capable74

documented100

adopted52

Install

$ npx -y skills add OSideMedia/higgsfield-ai-prompt-skill --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python Node HTML Bash Git

+5 tags

GitHub Markdown Anthropic OpenAI MCP

278

Stars

Forks

Active

Maintenance

Python

Language

MIT

License

1h ago

Last commit

5mo ago

Created

Repo: OSideMedia/higgsfield-ai-prompt-skill

In this plugin

32 skills 2 commands

See everything inside

What's inside

Skills

/higgsfield-actingWrites the character-performance layer of a video prompt as behavior under pressure, not displayed emotion — objective, obstacle, tactics, beats, subtext, listening, body/status/proxemics, and mandatory eye life. Produces a reusable 150–220-word acting master profile per /higgsfield-appsUse when the user asks about Higgsfield's one-click Apps, wants to know which app to use for a specific output, or needs guidance on the Apps workflow./higgsfield-assistUse when the user asks about Higgsfield Assist (the built-in GPT-5 copilot), how to use the platform's native AI assistant, credit optimization strategies, plan selection, how to get more from fewer credits, or platform efficiency tips./higgsfield-audioUse when the user asks about audio in Higgsfield videos, needs to add dialogue or lip-sync, wants sound effects or ambient sound in generated video, asks about music or BGM in output, or is using any audio-capable model (Kling 3.0, Seedance 1.5 Pro, Seedance 2.0, Veo 3/3.1, Grok /higgsfield-cameraUse when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases./higgsfield-canvasUse when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts → images → videos across models on one surface. Covers what Canvas is, the node categories, the seven

Show all 32 skills

/higgsfield-character-designPre-production story-and-character development for Higgsfield projects — the upstream layer that decides WHAT to prompt before any model runs. Use when the user wants to build a character, design a world, develop a story or premise, create a character sheet / character bible //higgsfield-cinemaGuides users through professional filmmaking workflows in Higgsfield Cinema Studio, including creating multi-shot sequences, configuring optical stacks, applying color grading, managing Soul Cast AI actors, and structuring per-scene prompts with Director Panel camera movements./higgsfield-content-factoryUse when the user wants to run a full ad-campaign pipeline on top of Higgsfield Marketing Studio — 'create a campaign', 'build a content plan', 'run the content pipeline', 'generate 100 UGC videos', 'plan and schedule a launch', 'make a batch of ads from my product', or 'how /higgsfield-facsControls facial expressions in Seedance 2.0 with FACS (Facial Action Coding System) Action Unit codes — muscle-level direction (AU12 = lip-corner puller, AU6 = cheek raiser) instead of emotion labels. Use whenever the user wants precise facial acting, a forced/uncanny/mixed /higgsfield-gpt-image-2Use when the user mentions GPT Image 2.0, gpt-image-2, GPT-Image-2 prompts, or wants to generate an image with GPT Image 2.0. Covers the three-format prompt taxonomy (Format A structured JSON for UI mockups and layout-dense images; Format B dense cinematic prose for /higgsfield-image-shotsUse when the user wants to generate a cinematic still image on Higgsfield, asks about shot framing, camera angle, or composition for image prompts, needs a specific shot type (close-up, wide shot, cowboy shot, etc.), or is working with [img] reference-based image generation./higgsfield-marketing-studioUse when the user mentions Marketing Studio, DTC Ads, ad video, UGC video, the marketing_studio_video MCP model, or wants to generate one of the 9 Marketing Studio ad presets (UGC, Tutorial, Unboxing, Hyper Motion, Product Review, TV Spot, Wild Card, UGC Virtual Try On, Pro /higgsfield-mixed-mediaUse when the user asks about Mixed Media, wants to apply artistic preset styles to an image (Noir, Sketch, Paper, Canvas, Particles, Neon, etc.), combine multiple artistic treatments, or create stylized non-photorealistic outputs./higgsfield-modelsUse when the user asks which model to use, wants to compare models, or needs guidance on selecting between Kling, Sora 2, Wan, Seedance, Veo 3, Minimax Hailuo, Soul, Nano Banana, or other Higgsfield engines./higgsfield-moodboardUse when the user asks about Moodboard, building a moodboard from reference images, curated moodboard presets, Soul Hex color transfer, applying a visual style direction to generations, or named moodboard styles like Y2K studio, Warm ambient, Theatrical light, Swag era, Flash /higgsfield-motion-designEnd-to-end motion-design / animated-ad creation flow on Higgsfield via the MCP connector. Use when the user wants to create motion design, animate a logo, make a video from an image, build an animated ad or brand promo, turn a product into motion, or says 'make a motion',/higgsfield-motionUse when the user wants to apply a named Higgsfield motion preset, asks about VFX presets, transformation effects, elemental effects, or transition presets. Contains the full named preset library with descriptions and prompt usage./higgsfield-pipelineUse when the user wants to create a complete multi-shot video, asks how to chain Higgsfield tools together, wants to build a short film or branded content series, asks "what's the full workflow", needs to connect Popcorn → image → video → Recast → audio → assembly, or wants to /higgsfield-promptUse when building, writing, refining, or structuring a Higgsfield AI prompt. Covers the MCSLA formula, prompt structure, narrative vs. timestamped formats, and how to write for both text-to-video and image-to-video workflows./higgsfield-recallUse this skill AUTOMATICALLY before writing any Higgsfield prompt. Query the memory databases for relevant past failures and pre-apply known fixes before the user even hits generate. Triggers include: any request to write a Higgsfield prompt, any use of the higgsfield-prompt /higgsfield-recipesUse when the user wants a genre-specific scene template, starting point for a type of video (action, horror, romance, product ad, documentary, sci-fi, dance, etc.), or asks for prompt examples for a specific style of content./higgsfield-seedance-2-5Seedance 2.5 prompt director — the omni-reference dialect. Routes the four generation modes (t2v / omni_reference / video_edit / video_extension), writes explicit @Image/@Video/@Audio reference roles with exclusions, stages 30-second videos into end-state beats, and covers video /higgsfield-seedance-vfxWrites, improves, or rewrites Seedance 2.0 prompts that TRANSFORM footage the user already has (video-to-video), rather than building a scene from scratch. Use whenever a real clip is the starting point and they want to: add a VFX element (set a head or hair on fire, transform a /higgsfield-seedanceRewrites scene descriptions using professional cinematography language, structures prompts with a six-slot formula (camera + subject + action + setting + style + lighting), and diagnoses content filter rejections via a preflight linter. Use whenever the user asks for a Seedance /higgsfield-shotlist-directorTurns a brief, script, scene breakdown, treatment, or story idea into ONE connected director's shotlist for Seedance 2.0 — a single editable HTML artifact with a global Style Prefix, an @-asset glossary, and named per-scene prompts (1a, 1b, 2a…) each in Style → Characters →/higgsfield-soulCreates and manages reusable character profiles (Soul IDs) for consistent facial and stylistic identity across multiple image and video generations. Provides identity-vs-motion prompt separation, character sheet creation workflows, micro-expression direction, and Soul Cast AI /higgsfield-stackUse when the user mentions the Higgsfield CLI (binaries `higgsfield` / `higgs` / `hf`, `higgsfield auth login`, `higgsfield generate create`, the `@higgsfield/cli` npm package), the Higgsfield MCP custom connector (`mcp.higgsfield.ai/mcp`), Higgsfield's bundled skills /higgsfield-styleUse when the user asks about visual styles, aesthetics, color grades, film looks, or how to set the tone and atmosphere of a Higgsfield generation./higgsfield-troubleshootUse when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output./higgsfield-vibe-motionUse when the user asks about Vibe Motion, motion graphics, kinetic typography, animated text, brand animations, logo animations, infographic animation, presentation animation, data-driven video, or prompt-to-motion-graphic workflows. Vibe Motion is fundamentally different from /higgsfield-workspacesUse when the user is unsure which Higgsfield workspace fits their task, needs to decide between Cinema Studio / Lipsync Studio / Draw-to-Video / Sora 2 Trends / Click to Ad / Higgsfield Audio, or is asking 'what should I use for X'. This sub-skill routes by production problem

Commands

/releaseGuided version bump — validate, tag, and create GitHub release /validateRun pre-release validation checks on all SKILL.md files and JSON databases

Badges

README

Read on GitHub

Higgsfield AI Prompt Skill

A comprehensive Claude skill library for generating high-quality prompts on Higgsfield AI — the cinematic video and image generation platform.

What This Skill Does

Transforms natural language requests into production-ready Higgsfield prompts using:

The MCSLA formula (Model · Camera · Subject · Look · Action)
Named camera controls and motion presets the platform recognizes
Model selection guidance across Kling 3.0 / 3.0 Omni / 3.0 Motion Control, Sora 2, Veo 3.1, Wan, Seedance 2.5 / 2.0, FLUX 3 Video, Minimax Hailuo, Higgsfield DoP, and more
Genre recipe templates for action, horror, romance, sci-fi, product ads, and more
Soul ID character consistency guidance + Character Sheet creation
Troubleshooting for failed or poor generations
Cinema Studio 2.5 advanced features: Soul Cast AI actors, built-in color grading, 3D Mode (Gaussian Splatting), Grid Generation, Resolution Settings, Frame Extraction Loop, Object & Person Insertion, Per-Character Emotions, Clustering, Five-View Location Reference Sheet, Reference Sheet Types (Motion / Outfit / Palette), Elements System with library surface (5 source tabs × 6 element categories)
Cinema Studio 3.0 (Business/Team plan): native dual-channel stereo audio, Smart shot control, 15s max duration, 7 genres, @ reference patterns, Soul Cast 3.0
Cinema Studio 3.5: three-pill main UI (Genre / Style / Camera), Style Settings panel (8 Color Palette / 6 Lighting / 9 Camera Moveset Style + Manual Style mode), Camera Settings four-axis panel (3 Camera Body / 5 Lens / 5 Focal Length including new 75mm / 3 Aperture), Image Mode with four Cinematic models picker (Soul Cinema default, Cinematic Characters, Cinematic Locations, Cinematic Cameras with 2.5 vocabulary)
Seedance 2.0 prompting best practices — Intent over Precision, Genre Router, I2V Gate, Anti-Slop, Physics Language, SCELA audio, Reference-Based / Continuation / Expand Shot / Edit Shot / Transformation prompt modes, Continuation Prompt Formula, the Iteration Rule
Seedance 2.5 omni-reference director — the four generation modes (t2v / omni_reference / video_edit / video_extension), explicit @Image / @Video / @Audio reference roles with exclusions, the five-step multi-reference workflow, 30-second staging with end states, timestamp pacing, bracket syntax for music / SFX / dialogue / subtitles, in-prompt first-last-frame and multi-keyframe control, storyboard grids, coarse-vs-fine blockout rendering, one-click video, seamless transitions, and a 2.0-vs-2.5 routing table
Hell Grind feature-film pipeline — Higgsfield's open-sourced 95-minute-feature system: headless character sheets, mask-composited point edits, location sheets with anchors and one light logic, the per-scene GEO SPATIAL LAYOUT block, the position-fixing first second, dialogue construction, the ban dictionary, the 10–15 iteration rule, and the crowd / giant / threshold solutions
AI-VFX pipeline — the production layer under Seedance 2.5, from Higgsfield's AI-vs-VFX challenge build: model routing per asset class (faces / creatures / clothing / locations), the plain-grey sheet law, two-close-up creature sheets, the face-lock crop, the size-ref frame for scale between two subjects, location batching selected on light, the omni_reference video-to-video lane (source ≥4s, duration = source) with its performance-inheritance clause, the four-batch stop rule and the i2v fallback with a deliberate empty-frame stitch point, and a slop catalog of the tells that give a shot away
Acting director — performance as behavior under pressure: objective / obstacle / tactics / beats / subtext, listening markers, body + status + proxemics, mandatory eye life, the 150–220-word acting master profile and its per-scene rewrite, the locked voice prompt, a 15-symptom atlas of bad acting, and a 0–5 performance scale
GPT Image 2.0 prompt director — three-format taxonomy (structured JSON for UI mockups / infographics / reference sheets, dense cinematic prose for single-subject scenes, auto-derive meta-prompt for theme-only concepts) plus reference-sheet and static-ad-recreation workflow satellites
Higgsfield Canvas — node-based / infinite-board workspace guidance: chaining prompts → images → videos, named canvas patterns, Shared Canvas live collaboration, build-free / generate-paid cost model
Marketing Studio + Content Factory — 9 DTC ad presets (UGC / Tutorial / Unboxing / Hyper Motion / TV Spot / Wild Card / Virtual Try-On) with 4–15s ad video, plus an end-to-end campaign pipeline (research → plan → generate → publish → report) with a cost-savings report
Shared negative constraints reference — categorized artifacts + prevention phrases (positive alternatives for 3.0); Kling 3.0 Motion Control failure diagnostic; Physics Rendering — Resolution Decision Matrix (cross-model 480p / 720p / 1080p routing rule for Seedance 2.0 + Cinema Studio 3.x)
Identity vs. Motion separation — hard rule for character consistency across shots
Annotated templates library — 10 genre templates with Cinema Studio 3.0 genre mappings, plus Seedance technique + character-design + text-overlay sub-libraries (18 files across 3 categories)
DISCIPLINE.md cross-cutting framework — 9 named discipline patterns in 3-3-3 tier symmetry (prompt-construction, model-selection, iteration-discipline) governing decisions across all sub-skills
production-benchmarks.md — Hell Grind 90-min Cannes feature reference, per-character iteration anchors, acceptance-rate calibration; what "production quality" means in practice
FAILURE-MODES.md (Seedance) — 8 named render failures documented with symptom + mechanism + counter for diagnosis-first iteration
C-arc Building Complete AI Projects — 10-Step Methodology — end-to-end pipeline from idea to delivered project; complements the genre/scene templates
Expanded Seedance methodology + Soul refinement — Iteration Rule + 6-Pass Diagnostic Sequence + Four Questions + Next-Shot Decision Tree + Bridging / Continuation / Repair working modes; Character Anchor Block + Two-Tool Refinement Pipeline for character consistency at production scale

Install

Claude Code

git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield

Claude Cowork

Drop the repo folder into your Cowork workspace. The skill dispatcher is at SKILL.md in the repo root.

Claude.ai Projects

Upload SKILL.md (root) as your project instruction base. Upload files from skills/ as project documents.

Higgsfield Stack Integration

This skill is the prompt-construction layer. Higgsfield ships official execution tooling — a CLI, an MCP custom connector, and a bundled skills package. They complement each other: this skill produces the prompt, their tooling executes it. None of their tooling is required for this skill to work — you can always paste prompts directly into higgsfield.ai. But if you want an end-to-end loop, you'll want one of the three.

A Higgsfield account is required for any of the tooling below. Sign up at higgsfield.ai.

Higgsfield CLI

Command-line tool for terminal-native agents (Claude Code, Codex, Cursor). Per Higgsfield's own guidance, prefer the CLI over the MCP if you're working in a terminal.

Repo: github.com/higgsfield-ai/cli
Install: curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh or brew install higgsfield-ai/tap/higgsfield
Auth: higgsfield auth login

Higgsfield MCP

Custom connector for claude.ai web and the Claude desktop app. Separate product from the CLI.

Connector URL: https://mcp.higgsfield.ai/mcp
Install: claude.ai → Settings → Connectors → Add custom connector → paste the URL above → sign in

Higgsfield Bundled Skills

Markdown skill bundle for agents that consume Cowork-style skills. All three skills drive the CLI under the hood.

Repo: github.com/higgsfield-ai/skills
Install: npx skills add higgsfield-ai/skills
Skills included: higgsfield-generate, higgsfield-soul, higgsfield-product-photoshoot
Invoke: /higgsfield:generate, /higgsfield:soul, /higgsfield:product-photoshoot

End-to-end example

How the layers fit together for a real request:

USER:    "Make me a cinematic chase scene through a night market.
          Use my trained Soul character — reference_id abc123."
   ↓
THIS SKILL — higgsfield-ai-prompt-skill
   • routes to higgsfield-prompt + higgsfield-camera + higgsfield-soul
   • picks Kling 3.0 (character-focused, supports --soul-id)
   • applies MCSLA: model, camera preset, subject, look, action
   • appends shared negative constraints
   • outputs a production-grade Higgsfield prompt
   ↓
PRE-FLIGHT (optional, recommended for Veo / Kling / Sora / Seedance video):

   SCHEMA VERIFY (recommended for any model you haven't called recently):
   CLI path:        higgsfield model get kling3_0
                    → returns schema: aspect_ratio enum, duration range,
                      mode/sound options, media roles
   MCP path:        models_explore(action="get", model_id="kling3_0")
                    → returns same schema as CLI

   COST ESTIMATE (no job submitted):
   MCP path:        generate_video(..., get_cost: true)
                    → returns credit cost + adjustments block

   CLI path:        higgsfield generate cost kling3_0 \
                      --prompt "<prompt from this skill>" \
                      --aspect_ratio 16:9 \
                      --duration 8
                    # (add reference flags as needed: --soul-id, --start-image,
                    #  --end-image — consult `higgsfield model get kling3_0`
                    #  for supported media roles)

   Bundled skills:  drop to CLI for the cost check (same auth, same workspace),
                    then invoke /higgsfield:generate

   Optional account checks (same data across surfaces):
   MCP path:        balance / transactions tools
   CLI path:        higgsfield account status
                    higgsfield account transactions --size 50

   Note: 2.35:1 is anamorphic STYLE vocabulary, not a valid Kling 3.0 output
         ratio. Output ratios are platform-bounded: 16:9 / 9:16 / 1:1 only.
   ↓
HIGGSFIELD STACK — one of three execution surfaces:

   CLI path:
     higgsfield generate create kling3_0 \
       --prompt "<prompt from this skill>" \
       --aspect_ratio 16:9 \
       --duration 8 \
       --wait
     # (add reference flags as needed: --soul-id, --start-image, --end-image —
     #  consult `higgsfield model get kling3_0` for supported media roles)

   Bundled skills path:
     /higgsfield:generate — takes the prompt as its --prompt argument,
     formats the CLI call above under the hood

   MCP path (claude.ai web/desktop):
     Claude invokes the Higgsfield connector with the prompt as input
   ↓
USER:    Result URL returned. Iterate if needed (this skill's
         iteration discipline applies regardless of execution surface).

The layer split holds in every case: this skill always produces the prompt, the Higgsfield stack always handles the generation call. None of the three execution paths reach back into prompt construction; this skill never shells out to their CLI or API.

Full preflight discipline — when to surface it, marketing-studio caveat, CLI naming gotchas (account status, not balance), and the plan-tier-vs-surface framing — lives in skills/higgsfield-stack/SKILL.md § Preflight discipline.

Coexistence rules

For the full coexistence rules, detection signals, naming-collision callouts, and handoff templates, see skills/higgsfield-stack/SKILL.md.

Structure

.
├── SKILL.md                          ← Main dispatcher (routes to sub-skills — start here)
├── README.md                         ← This file
├── CHANGELOG.md                      ← Version history
├── CONTRIBUTING.md                   ← Contribution guidelines
├── LICENSE                           ← MIT license
├── CLAUDE.md                         ← Project instructions for Claude Code
├── .markdownlint.json                ← Linter config (CHANGELOG convention silencing — v3.6.1)
├── model-guide.md                    ← Model comparison tables + decision flowchart
├── image-models.md                   ← Image model reference + pricing tiers
├── vocab.md                          ← Full platform vocabulary reference
├── prompt-examples.md                ← High-quality example prompts + Before/After pairs
├── photodump-presets.md              ← Photodump mode presets
├── DISCIPLINE.md                     ← Cross-cutting discipline framework (9 patterns, 3-3-3 tier symmetry)
├── production-benchmarks.md          ← Production-quality anchors + acceptance-rate calibration
├── scripts/                          ← Python tooling (run from the repo root)
│   ├── higgsfield_memory.py          ← Memory system script
│   ├── seedance_lint.py              ← Seedance preflight linter
│   ├── validate.py                   ← Pre-release validation script
│   ├── build_index.py                ← Regenerates INDEX.md + checks QUICK FACTS anchors
│   ├── sync_specs.py                 ← Regenerates specs/ from a models_explore snapshot
│   ├── refresh_specs.py              ← Spec-drift tripwire (live CLI vs baseline)
│   ├── generate_user_guide.py        ← USER-GUIDE.pdf generator (Path B refactor — v3.7.0)
│   ├── validate_user_guide.py        ← USER-GUIDE.pdf drift validator (text-extract + binary diff)
│   └── sub_skill_descriptions.py     ← Canonical sub-skill roster (shared data module)
├── db/
│   ├── filter-memory.json            ← Content filter memory (seeded)
│   └── quality-memory.json           ← Quality failure memory (seeded)
├── docs/                             ← Extended reference documents
│   ├── Seedance 2 Skill.md           ← Bilingual EN+ZH Seedance director reference
│   ├── archive/                      ← Historical records
│   │   ├── HISTORY.md                ← Consolidated v3.0.0–v3.6.0 audit + inventory snapshots
│   │   └── AUDIT-2026-06-03.md       ← Full repo audit (security, bugs, docs hygiene)
│   └── user-guide/                   ← Exported USER-GUIDE.pdf + current-version baseline (rotate, not accumulate)
├── templates/                        ← Genre templates + Seedance coordination + text-overlays
│   ├── 01-cinematic-action-chase.md
│   ├── 02-product-ugc-showcase.md
│   ├── 03-horror-atmosphere.md
│   ├── 04-fashion-editorial.md
│   ├── 05-sci-fi-vfx.md
│   ├── 06-portrait-character-intro.md
│   ├── 07-landscape-establishing-shot.md
│   ├── 08-comedy-social-media.md
│   ├── 09-romantic-intimate.md
│   ├── 10-dance-music-performance.md
│   ├── seedance/                     ← Seedance technique templates (9)
│   │   ├── multi-character-anchor.md
│   │   ├── single-character-position.md
│   │   ├── top-down-map.md
│   │   ├── omni-reference-2-5.md     ← Seedance 2.5 multi-reference brief
│   │   └── worked-example-two-character.md
│   └── text-overlays/                ← Text overlay templates
│       ├── slogan.md
│       ├── speech-bubble.md
│       └── subtitle.md
└── skills/
    ├── shared/
    │   └── negative-constraints.md       ← Shared artifact prevention reference
    ├── higgsfield-prompt/SKILL.md        ← Core MCSLA formula + prompt structure + Identity/Motion separation
    ├── higgsfield-image-shots/SKILL.md   ← Cinematic image prompting (shots, angles, composition)
    ├── higgsfield-gpt-image-2/
    │   ├── SKILL.md                      ← GPT Image 2.0 director (JSON / prose / meta-prompt taxonomy)
    │   ├── reference-sheet-workflow.md   ← Automatic product reference-sheet workflow
    │   └── static-ads-workflow.md        ← Static-ad recreation workflow
    ├── higgsfield-models/
    │   ├── SKILL.md                      ← Compact model selection guide
    │   └── MODELS-DEEP-REFERENCE.md      ← Full per-model documentation (on-demand)
    ├── higgsfield-camera/SKILL.md        ← All camera controls + usage
    ├── higgsfield-motion/SKILL.md        ← Named motion presets library
    ├── higgsfield-style/SKILL.md         ← Visual styles + color grades + lighting
    ├── higgsfield-soul/SKILL.md          ← Soul ID character consistency
    ├── higgsfield-audio/SKILL.md         ← Audio prompting + Cinema Studio 3.0 native audio
    ├── higgsfield-apps/SKILL.md          ← One-click Apps guide
    ├── higgsfield-recipes/SKILL.md       ← Genre scene templates
    ├── higgsfield-troubleshoot/SKILL.md  ← Fix failing generations
    ├── higgsfield-assist/SKILL.md        ← General assistant + platform guidance
    ├── higgsfield-mixed-media/SKILL.md   ← Mixed media + hybrid generation
    ├── higgsfield-moodboard/SKILL.md     ← Moodboard creation workflows
    ├── higgsfield-pipeline/SKILL.md      ← Multi-step generation pipelines
    ├── higgsfield-canvas/SKILL.md        ← Node-based Canvas workspace + named patterns + Shared Canvas
    ├── higgsfield-content-factory/
    │   ├── SKILL.md                      ← Campaign pipeline (research → plan → generate → publish → report)
    │   └── publish-and-report-workflow.md ← Publish + cost-savings report satellite
    ├── higgsfield-marketing-studio/
    │   ├── SKILL.md                      ← Marketing Studio: 9 ad presets + 4–15s ad video
    │   └── cross-surface-workflow.md     ← ms_image / DTC Ads cross-surface workflow
    ├── higgsfield-recall/SKILL.md        ← Recall + regeneration patterns
    ├── higgsfield-cinema/SKILL.md        ← Cinema Studio 2.5 + 3.0 + 3.5 (Soul Cast, Color Grading, 3D Mode, Smart Mode, @ References, Native Audio, three-pill UI, Image Mode, Cinematic models picker)
    ├── higgsfield-seedance/
    │   ├── SKILL.md                      ← Seedance 2.0 prompt director + content-filter preflight
    │   ├── ENGINE-RULES.md               ← Hard rendering constraints shared across the Seedance family
    │   ├── PRODUCTION-PATTERNS.md        ← Tutorial-demonstrated production patterns
    │   ├── HELL-GRIND.md                 ← Higgsfield's open-sourced 95-min feature pipeline
    │   └── FAILURE-MODES.md              ← 8 named Seedance render failures (symptom · mechanism · counter)
    ├── higgsfield-seedance-2-5/
    │   ├── SKILL.md                      ← Seedance 2.5 omni-reference dialect + 4-mode router
    │   ├── MODE-PLAYBOOKS.md             ← Edit / extend / storyboard / blockout / one-click / transitions
    │   └── VFX-PIPELINE.md               ← AI-VFX pipeline: asset routing, size-ref frame, omni_reference v2v, slop catalog
    ├── higgsfield-acting/SKILL.md        ← Performance craft: objective, beats, eye life, master profile
    ├── higgsfield-vibe-motion/SKILL.md   ← Vibe-based motion direction
    └── higgsfield-workspaces/SKILL.md    ← Workspace-first decision layer (Cinema Studio / Lipsync / Draw-to-Video / Sora 2 Trends / Click to Ad / Higgsfield Audio)

Generation Ledger

Every generation attempt — kept, rejected, or filter-flagged — gets one row in db/ledger/<project>.json, logged by the agent in ≤5 seconds (one question, one command — never a form). After ~30–40 rows a production has empirical takes-per-kept ratios per shot type instead of vibes:

python3 scripts/higgsfield_memory.py log-gen adze --model seedance_2_0 \
  --tags dialogue-cu,two-char --outcome rejected --reason extra-cuts
python3 scripts/higgsfield_memory.py ratio adze --credits     # hit rates + money view
python3 scripts/higgsfield_memory.py budget adze --shots plan.json   # price before burning

Tags and reject reasons come from controlled vocabularies (db/ledger/README.md); rows are append-only with superseding corrections; ratio splits structural vs stochastic rejections and flags low-n rows instead of faking precision.

Maintenance — two activation steps

Two capabilities ship inactive on purpose and need a one-time setup.

1. Activate the scheduled spec-drift check

.github/workflows/spec-drift.yml runs scripts/refresh_specs.py weekly to catch when Higgsfield changes a model's lineup or capabilities before the 30-day staleness warning would. It ships dormant until you give it the Higgsfield CLI credentials as a repo secret:

higgsfield auth login                 # if not already authenticated locally
gh secret set HIGGSFIELD_CREDENTIALS < ~/.config/higgsfield/credentials.json

Then run it once manually (Actions tab → spec-drift → Run workflow) to confirm the CLI-install step resolves on the runner. After that it's automatic: fresh → nothing; drift → it opens/updates a GitHub issue with next steps; auth expired → the job fails so GitHub notifies you to re-run higgsfield auth login and refresh the secret. The credentials live only in the GitHub secret — they are never committed.

2. Let routing telemetry accumulate before pruning

log-route / routing (in scripts/higgsfield_memory.py) record which sub-skills each request opens, so "which skills are load-bearing, which to retire" becomes a data question:

python3 scripts/higgsfield_memory.py log-route --skills higgsfield-prompt,higgsfield-camera
python3 scripts/higgsfield_memory.py routing     # ranks opens, lists the never-opened tail

This is instrumentation, not a verdict — let real requests accumulate before acting on the tail. A small sample is not evidence a skill is dead.

Example Prompts

Basic:

"Write me a Higgsfield prompt for a cinematic action chase through a night market"

Specific:

"I need a horror prompt using VHS style, Dutch angle camera, and the Horror Face preset"

With reference:

"I have a Soul ID character. Write 3 different scene prompts with her — office, party, rooftop"

Model question:

"Should I use Kling 3.0 or Sora 2 for a large-scale battle scene?"

Troubleshoot:

"My image-to-video isn't animating, it's just static. What am I doing wrong?"

The MCSLA Formula

Letter	Layer	Example
M	Model	Kling 3.0
C	Camera	FPV Drone weaving through the alley
S	Subject	A woman in a tactical jacket
L	Look	Cinematic, cold blue shadows, 16:9
A	Action	She sprints, slides under a gate

Built February 2026 · v3.26.0 (updated 2026-08-08) · Platform: higgsfield.ai

File tree

175

OSideMedia/higgsfield-ai-prompt-skillView on GitHub

.claude/
  commands/
    release.md
    validate.md
  rules/
    cinematic-vocab.md
    image-models.md
    model-reference.md
    photodump-presets.md
    prompt-formula.md
  settings.json
.gitattributes
.github/
  workflows/
    spec-drift.yml
    validate.yml
.gitignore
.markdownlint.json
assets/
  fonts/
    DejaVuSansCondensed-Bold.ttf
    DejaVuSansCondensed-Oblique.ttf
    DejaVuSansCondensed.ttf
    DejaVuSansMono.ttf
    README.md
CHANGELOG.md
CLAUDE.md
CONTRIBUTING.md
db/
  filter-memory.json
  ledger/
    _demo.json
    _global.json
    README.md
  memory-summary.md
  quality-memory.json
  routing-log.json
DISCIPLINE.md
docs/
  archive/
    AUDIT-2026-06-03.md
    CHANGELOG-v3.0-v3.14.md
    HISTORY.md
  Seedance 2 Skill.md
  user-guide/
    MANIFEST.json
evals/
  cases/
    audio.json
    cinema.json
    harvest.json
    models.json
    prompt.json
    seedance-2-5.json
    seedance.json
  run_evals.py
image-models.md
INDEX.md
LICENSE
model-guide.md
photodump-presets.md
production-benchmarks.md
prompt-examples.md
README.md
requirements.txt
scripts/
  build_index.py
  generate_user_guide.py
  higgsfield_memory.py
  refresh_specs.py
  seedance_lint.py
  sub_skill_descriptions.py
  sync_specs.py
  validate_user_guide.py
  validate.py
SKILL.md
skills/
  higgsfield-acting/
    SKILL.md
  higgsfield-apps/
    SKILL.md
  higgsfield-assist/
    SKILL.md
  higgsfield-audio/
    SKILL.md
  higgsfield-camera/
    SKILL.md
  higgsfield-canvas/
    SKILL.md
  higgsfield-character-design/
    SKILL.md
  higgsfield-cinema/
    SKILL.md
  higgsfield-content-factory/
    publish-and-report-workflow.md
    SKILL.md
  higgsfield-facs/
    SKILL.md
  higgsfield-gpt-image-2/
    reference-sheet-workflow.md
    SKILL.md
    static-ads-workflow.md
  higgsfield-image-shots/
    SKILL.md
  higgsfield-marketing-studio/
    cross-surface-workflow.md
    SKILL.md
  higgsfield-mixed-media/
    SKILL.md
  higgsfield-models/
    MODELS-DEEP-REFERENCE.md
    SKILL.md
  higgsfield-moodboard/
    SKILL.md
  higgsfield-motion/
  higgsfield-motion-design/
    SKILL.md
    SKILL.md
  higgsfield-pipeline/
    SKILL.md
  higgsfield-prompt/
    SKILL.md
  higgsfield-recall/
    SKILL.md
  higgsfield-recipes/
    SKILL.md
  higgsfield-seedance/
  higgsfield-seedance-2-5/
    MODE-PLAYBOOKS.md
    SKILL.md
    VFX-PIPELINE.md
  higgsfield-seedance-vfx/
    references/
      dialogue-timing.md
      first-frame.md
    SKILL.md
    ENGINE-RULES.md
    FAILURE-MODES.md
    HELL-GRIND.md
    PRODUCTION-PATTERNS.md
    SKILL.md
  higgsfield-shotlist-director/
    SKILL.md
  higgsfield-soul/
    SKILL.md
  higgsfield-stack/
    SKILL.md
  higgsfield-style/
    SKILL.md
  higgsfield-troubleshoot/
    SKILL.md
  higgsfield-vibe-motion/
    SKILL.md
  higgsfield-workspaces/
    SKILL.md
  shared/
    negative-constraints.md
specs/
  audio-model-specs.json
  AUDIO-MODEL-SPECS.md
  audio-model-specs.yaml
  cli_baseline.json
  image-model-specs.json
  IMAGE-MODEL-SPECS.md
  image-model-specs.yaml
  model-specs.json
  MODEL-SPECS.md
  model-specs.yaml
  models_explore_snapshot_2026-06-11.json
  models_explore_snapshot_2026-06-22.json
  models_explore_snapshot_2026-07-05.json
  models_explore_snapshot_2026-08-01.json
  models_explore_snapshot_2026-08-07.json
  models_explore_snapshot_audio_2026-07-05.json
  models_explore_snapshot_audio_2026-08-01.json
  models_explore_snapshot_image_2026-06-22.json
  models_explore_snapshot_image_2026-07-05.json
  models_explore_snapshot_image_2026-08-01.json
templates/
  01-cinematic-action-chase.md
  02-product-ugc-showcase.md
  03-horror-atmosphere.md
  04-fashion-editorial.md
  05-sci-fi-vfx.md
  06-portrait-character-intro.md
  07-landscape-establishing-shot.md
  08-comedy-social-media.md
  09-romantic-intimate.md
  10-dance-music-performance.md
  ad-asset-prep.md
  character-design/
    9-question-character-sheet.md
    character-web.md
    premise.md
    story-spine.md
    style-sheet.md
    world-sheet.md
  seedance/
    anime-animation.md
    facs-expression-beats.md
    footage-vfx-transform.md
    global-style-prefix.md
    multi-character-anchor.md
    omni-reference-2-5.md
    single-character-position.md
    top-down-map.md
    worked-example-two-character.md
  text-overlays/
    slogan.md
    speech-bubble.md
    subtitle.md
tests/
  conftest.py
  fixtures/
    cli_1_0_1_model_get_seedance_2_0.json
    cli_1_0_1_model_list_video.json
    models_explore_snapshot_2026-06-11.json
  test_ledger.py
  test_lint_rules.py
  test_memory.py
  test_refresh.py
  test_routing.py
  test_sync_specs.py
  test_validate.py
vocab.md
workspace/
  input/
    .gitignore
    README.md
  output/
    .gitignore
    README.md
  processed/
    .gitignore
    README.md
  README.md

FAQ

higgsfield-ai-prompt-skill is a Claude Code plugin with 32 hand-picked skills for content work, indexed on Flowy. Install it with the command on its page. It includes higgsfield-acting, higgsfield-apps, higgsfield-assist. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is higgsfield-ai-prompt-skill?: A comprehensive Claude skill library for generating high-quality prompts on Higgsfield AI — the cinematic video and image generation platform.
How do I install higgsfield-ai-prompt-skill?: Run these in Claude Code: npx -y skills add OSideMedia/higgsfield-ai-prompt-skill --agent claude-code. Then prompt normally.
Does higgsfield-ai-prompt-skill auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is higgsfield-ai-prompt-skill free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Content

Plugin

higgsfield-ai-prompt-skill

A comprehensive Claude skill library for generating high-quality prompts on Higgsfield AI — the cinematic video and image generation platform.

FLOW.md

osidemedia@osidemedia

GitHub

Plugin Signal85/100Strong

maintained99

capable74

documented100

adopted52

Install

$ npx -y skills add OSideMedia/higgsfield-ai-prompt-skill --agent claude-code

Run the curl in your terminal, the rest in Claude Code.

Stats

Python Node HTML Bash Git

+5 tags

GitHub Markdown Anthropic OpenAI MCP

278

Stars

Forks

Active

Maintenance

Python

Language

MIT

License

1h ago

Last commit

5mo ago

Created

Repo: OSideMedia/higgsfield-ai-prompt-skill

In this plugin

32 skills 2 commands

See everything inside

What's inside

Skills

Show all 32 skills

Commands

/releaseGuided version bump — validate, tag, and create GitHub release /validateRun pre-release validation checks on all SKILL.md files and JSON databases

Badges

README

Read on GitHub

Higgsfield AI Prompt Skill

A comprehensive Claude skill library for generating high-quality prompts on Higgsfield AI — the cinematic video and image generation platform.

What This Skill Does

Transforms natural language requests into production-ready Higgsfield prompts using:

The MCSLA formula (Model · Camera · Subject · Look · Action)
Named camera controls and motion presets the platform recognizes
Model selection guidance across Kling 3.0 / 3.0 Omni / 3.0 Motion Control, Sora 2, Veo 3.1, Wan, Seedance 2.5 / 2.0, FLUX 3 Video, Minimax Hailuo, Higgsfield DoP, and more
Genre recipe templates for action, horror, romance, sci-fi, product ads, and more
Soul ID character consistency guidance + Character Sheet creation
Troubleshooting for failed or poor generations
Cinema Studio 2.5 advanced features: Soul Cast AI actors, built-in color grading, 3D Mode (Gaussian Splatting), Grid Generation, Resolution Settings, Frame Extraction Loop, Object & Person Insertion, Per-Character Emotions, Clustering, Five-View Location Reference Sheet, Reference Sheet Types (Motion / Outfit / Palette), Elements System with library surface (5 source tabs × 6 element categories)
Cinema Studio 3.0 (Business/Team plan): native dual-channel stereo audio, Smart shot control, 15s max duration, 7 genres, @ reference patterns, Soul Cast 3.0
Cinema Studio 3.5: three-pill main UI (Genre / Style / Camera), Style Settings panel (8 Color Palette / 6 Lighting / 9 Camera Moveset Style + Manual Style mode), Camera Settings four-axis panel (3 Camera Body / 5 Lens / 5 Focal Length including new 75mm / 3 Aperture), Image Mode with four Cinematic models picker (Soul Cinema default, Cinematic Characters, Cinematic Locations, Cinematic Cameras with 2.5 vocabulary)
Seedance 2.0 prompting best practices — Intent over Precision, Genre Router, I2V Gate, Anti-Slop, Physics Language, SCELA audio, Reference-Based / Continuation / Expand Shot / Edit Shot / Transformation prompt modes, Continuation Prompt Formula, the Iteration Rule
Seedance 2.5 omni-reference director — the four generation modes (t2v / omni_reference / video_edit / video_extension), explicit @Image / @Video / @Audio reference roles with exclusions, the five-step multi-reference workflow, 30-second staging with end states, timestamp pacing, bracket syntax for music / SFX / dialogue / subtitles, in-prompt first-last-frame and multi-keyframe control, storyboard grids, coarse-vs-fine blockout rendering, one-click video, seamless transitions, and a 2.0-vs-2.5 routing table
Hell Grind feature-film pipeline — Higgsfield's open-sourced 95-minute-feature system: headless character sheets, mask-composited point edits, location sheets with anchors and one light logic, the per-scene GEO SPATIAL LAYOUT block, the position-fixing first second, dialogue construction, the ban dictionary, the 10–15 iteration rule, and the crowd / giant / threshold solutions
AI-VFX pipeline — the production layer under Seedance 2.5, from Higgsfield's AI-vs-VFX challenge build: model routing per asset class (faces / creatures / clothing / locations), the plain-grey sheet law, two-close-up creature sheets, the face-lock crop, the size-ref frame for scale between two subjects, location batching selected on light, the omni_reference video-to-video lane (source ≥4s, duration = source) with its performance-inheritance clause, the four-batch stop rule and the i2v fallback with a deliberate empty-frame stitch point, and a slop catalog of the tells that give a shot away
Acting director — performance as behavior under pressure: objective / obstacle / tactics / beats / subtext, listening markers, body + status + proxemics, mandatory eye life, the 150–220-word acting master profile and its per-scene rewrite, the locked voice prompt, a 15-symptom atlas of bad acting, and a 0–5 performance scale
GPT Image 2.0 prompt director — three-format taxonomy (structured JSON for UI mockups / infographics / reference sheets, dense cinematic prose for single-subject scenes, auto-derive meta-prompt for theme-only concepts) plus reference-sheet and static-ad-recreation workflow satellites
Higgsfield Canvas — node-based / infinite-board workspace guidance: chaining prompts → images → videos, named canvas patterns, Shared Canvas live collaboration, build-free / generate-paid cost model
Marketing Studio + Content Factory — 9 DTC ad presets (UGC / Tutorial / Unboxing / Hyper Motion / TV Spot / Wild Card / Virtual Try-On) with 4–15s ad video, plus an end-to-end campaign pipeline (research → plan → generate → publish → report) with a cost-savings report
Shared negative constraints reference — categorized artifacts + prevention phrases (positive alternatives for 3.0); Kling 3.0 Motion Control failure diagnostic; Physics Rendering — Resolution Decision Matrix (cross-model 480p / 720p / 1080p routing rule for Seedance 2.0 + Cinema Studio 3.x)
Identity vs. Motion separation — hard rule for character consistency across shots
Annotated templates library — 10 genre templates with Cinema Studio 3.0 genre mappings, plus Seedance technique + character-design + text-overlay sub-libraries (18 files across 3 categories)
DISCIPLINE.md cross-cutting framework — 9 named discipline patterns in 3-3-3 tier symmetry (prompt-construction, model-selection, iteration-discipline) governing decisions across all sub-skills
production-benchmarks.md — Hell Grind 90-min Cannes feature reference, per-character iteration anchors, acceptance-rate calibration; what "production quality" means in practice
FAILURE-MODES.md (Seedance) — 8 named render failures documented with symptom + mechanism + counter for diagnosis-first iteration
C-arc Building Complete AI Projects — 10-Step Methodology — end-to-end pipeline from idea to delivered project; complements the genre/scene templates
Expanded Seedance methodology + Soul refinement — Iteration Rule + 6-Pass Diagnostic Sequence + Four Questions + Next-Shot Decision Tree + Bridging / Continuation / Repair working modes; Character Anchor Block + Two-Tool Refinement Pipeline for character consistency at production scale

Install

Claude Code

git clone https://github.com/OSideMedia/higgsfield-ai-prompt-skill ~/.claude/skills/higgsfield

Claude Cowork

Drop the repo folder into your Cowork workspace. The skill dispatcher is at SKILL.md in the repo root.

Claude.ai Projects

Upload SKILL.md (root) as your project instruction base. Upload files from skills/ as project documents.

Higgsfield Stack Integration

A Higgsfield account is required for any of the tooling below. Sign up at higgsfield.ai.

Higgsfield CLI

Command-line tool for terminal-native agents (Claude Code, Codex, Cursor). Per Higgsfield's own guidance, prefer the CLI over the MCP if you're working in a terminal.

Repo: github.com/higgsfield-ai/cli
Install: curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh or brew install higgsfield-ai/tap/higgsfield
Auth: higgsfield auth login

Higgsfield MCP

Custom connector for claude.ai web and the Claude desktop app. Separate product from the CLI.

Connector URL: https://mcp.higgsfield.ai/mcp
Install: claude.ai → Settings → Connectors → Add custom connector → paste the URL above → sign in

Higgsfield Bundled Skills

Markdown skill bundle for agents that consume Cowork-style skills. All three skills drive the CLI under the hood.

Repo: github.com/higgsfield-ai/skills
Install: npx skills add higgsfield-ai/skills
Skills included: higgsfield-generate, higgsfield-soul, higgsfield-product-photoshoot
Invoke: /higgsfield:generate, /higgsfield:soul, /higgsfield:product-photoshoot

End-to-end example

How the layers fit together for a real request:

USER:    "Make me a cinematic chase scene through a night market.
          Use my trained Soul character — reference_id abc123."
   ↓
THIS SKILL — higgsfield-ai-prompt-skill
   • routes to higgsfield-prompt + higgsfield-camera + higgsfield-soul
   • picks Kling 3.0 (character-focused, supports --soul-id)
   • applies MCSLA: model, camera preset, subject, look, action
   • appends shared negative constraints
   • outputs a production-grade Higgsfield prompt
   ↓
PRE-FLIGHT (optional, recommended for Veo / Kling / Sora / Seedance video):

   SCHEMA VERIFY (recommended for any model you haven't called recently):
   CLI path:        higgsfield model get kling3_0
                    → returns schema: aspect_ratio enum, duration range,
                      mode/sound options, media roles
   MCP path:        models_explore(action="get", model_id="kling3_0")
                    → returns same schema as CLI

   COST ESTIMATE (no job submitted):
   MCP path:        generate_video(..., get_cost: true)
                    → returns credit cost + adjustments block

   CLI path:        higgsfield generate cost kling3_0 \
                      --prompt "<prompt from this skill>" \
                      --aspect_ratio 16:9 \
                      --duration 8
                    # (add reference flags as needed: --soul-id, --start-image,
                    #  --end-image — consult `higgsfield model get kling3_0`
                    #  for supported media roles)

   Bundled skills:  drop to CLI for the cost check (same auth, same workspace),
                    then invoke /higgsfield:generate

   Optional account checks (same data across surfaces):
   MCP path:        balance / transactions tools
   CLI path:        higgsfield account status
                    higgsfield account transactions --size 50

   Note: 2.35:1 is anamorphic STYLE vocabulary, not a valid Kling 3.0 output
         ratio. Output ratios are platform-bounded: 16:9 / 9:16 / 1:1 only.
   ↓
HIGGSFIELD STACK — one of three execution surfaces:

   CLI path:
     higgsfield generate create kling3_0 \
       --prompt "<prompt from this skill>" \
       --aspect_ratio 16:9 \
       --duration 8 \
       --wait
     # (add reference flags as needed: --soul-id, --start-image, --end-image —
     #  consult `higgsfield model get kling3_0` for supported media roles)

   Bundled skills path:
     /higgsfield:generate — takes the prompt as its --prompt argument,
     formats the CLI call above under the hood

   MCP path (claude.ai web/desktop):
     Claude invokes the Higgsfield connector with the prompt as input
   ↓
USER:    Result URL returned. Iterate if needed (this skill's
         iteration discipline applies regardless of execution surface).

Full preflight discipline — when to surface it, marketing-studio caveat, CLI naming gotchas (account status, not balance), and the plan-tier-vs-surface framing — lives in skills/higgsfield-stack/SKILL.md § Preflight discipline.

Coexistence rules

For the full coexistence rules, detection signals, naming-collision callouts, and handoff templates, see skills/higgsfield-stack/SKILL.md.

Structure

.
├── SKILL.md                          ← Main dispatcher (routes to sub-skills — start here)
├── README.md                         ← This file
├── CHANGELOG.md                      ← Version history
├── CONTRIBUTING.md                   ← Contribution guidelines
├── LICENSE                           ← MIT license
├── CLAUDE.md                         ← Project instructions for Claude Code
├── .markdownlint.json                ← Linter config (CHANGELOG convention silencing — v3.6.1)
├── model-guide.md                    ← Model comparison tables + decision flowchart
├── image-models.md                   ← Image model reference + pricing tiers
├── vocab.md                          ← Full platform vocabulary reference
├── prompt-examples.md                ← High-quality example prompts + Before/After pairs
├── photodump-presets.md              ← Photodump mode presets
├── DISCIPLINE.md                     ← Cross-cutting discipline framework (9 patterns, 3-3-3 tier symmetry)
├── production-benchmarks.md          ← Production-quality anchors + acceptance-rate calibration
├── scripts/                          ← Python tooling (run from the repo root)
│   ├── higgsfield_memory.py          ← Memory system script
│   ├── seedance_lint.py              ← Seedance preflight linter
│   ├── validate.py                   ← Pre-release validation script
│   ├── build_index.py                ← Regenerates INDEX.md + checks QUICK FACTS anchors
│   ├── sync_specs.py                 ← Regenerates specs/ from a models_explore snapshot
│   ├── refresh_specs.py              ← Spec-drift tripwire (live CLI vs baseline)
│   ├── generate_user_guide.py        ← USER-GUIDE.pdf generator (Path B refactor — v3.7.0)
│   ├── validate_user_guide.py        ← USER-GUIDE.pdf drift validator (text-extract + binary diff)
│   └── sub_skill_descriptions.py     ← Canonical sub-skill roster (shared data module)
├── db/
│   ├── filter-memory.json            ← Content filter memory (seeded)
│   └── quality-memory.json           ← Quality failure memory (seeded)
├── docs/                             ← Extended reference documents
│   ├── Seedance 2 Skill.md           ← Bilingual EN+ZH Seedance director reference
│   ├── archive/                      ← Historical records
│   │   ├── HISTORY.md                ← Consolidated v3.0.0–v3.6.0 audit + inventory snapshots
│   │   └── AUDIT-2026-06-03.md       ← Full repo audit (security, bugs, docs hygiene)
│   └── user-guide/                   ← Exported USER-GUIDE.pdf + current-version baseline (rotate, not accumulate)
├── templates/                        ← Genre templates + Seedance coordination + text-overlays
│   ├── 01-cinematic-action-chase.md
│   ├── 02-product-ugc-showcase.md
│   ├── 03-horror-atmosphere.md
│   ├── 04-fashion-editorial.md
│   ├── 05-sci-fi-vfx.md
│   ├── 06-portrait-character-intro.md
│   ├── 07-landscape-establishing-shot.md
│   ├── 08-comedy-social-media.md
│   ├── 09-romantic-intimate.md
│   ├── 10-dance-music-performance.md
│   ├── seedance/                     ← Seedance technique templates (9)
│   │   ├── multi-character-anchor.md
│   │   ├── single-character-position.md
│   │   ├── top-down-map.md
│   │   ├── omni-reference-2-5.md     ← Seedance 2.5 multi-reference brief
│   │   └── worked-example-two-character.md
│   └── text-overlays/                ← Text overlay templates
│       ├── slogan.md
│       ├── speech-bubble.md
│       └── subtitle.md
└── skills/
    ├── shared/
    │   └── negative-constraints.md       ← Shared artifact prevention reference
    ├── higgsfield-prompt/SKILL.md        ← Core MCSLA formula + prompt structure + Identity/Motion separation
    ├── higgsfield-image-shots/SKILL.md   ← Cinematic image prompting (shots, angles, composition)
    ├── higgsfield-gpt-image-2/
    │   ├── SKILL.md                      ← GPT Image 2.0 director (JSON / prose / meta-prompt taxonomy)
    │   ├── reference-sheet-workflow.md   ← Automatic product reference-sheet workflow
    │   └── static-ads-workflow.md        ← Static-ad recreation workflow
    ├── higgsfield-models/
    │   ├── SKILL.md                      ← Compact model selection guide
    │   └── MODELS-DEEP-REFERENCE.md      ← Full per-model documentation (on-demand)
    ├── higgsfield-camera/SKILL.md        ← All camera controls + usage
    ├── higgsfield-motion/SKILL.md        ← Named motion presets library
    ├── higgsfield-style/SKILL.md         ← Visual styles + color grades + lighting
    ├── higgsfield-soul/SKILL.md          ← Soul ID character consistency
    ├── higgsfield-audio/SKILL.md         ← Audio prompting + Cinema Studio 3.0 native audio
    ├── higgsfield-apps/SKILL.md          ← One-click Apps guide
    ├── higgsfield-recipes/SKILL.md       ← Genre scene templates
    ├── higgsfield-troubleshoot/SKILL.md  ← Fix failing generations
    ├── higgsfield-assist/SKILL.md        ← General assistant + platform guidance
    ├── higgsfield-mixed-media/SKILL.md   ← Mixed media + hybrid generation
    ├── higgsfield-moodboard/SKILL.md     ← Moodboard creation workflows
    ├── higgsfield-pipeline/SKILL.md      ← Multi-step generation pipelines
    ├── higgsfield-canvas/SKILL.md        ← Node-based Canvas workspace + named patterns + Shared Canvas
    ├── higgsfield-content-factory/
    │   ├── SKILL.md                      ← Campaign pipeline (research → plan → generate → publish → report)
    │   └── publish-and-report-workflow.md ← Publish + cost-savings report satellite
    ├── higgsfield-marketing-studio/
    │   ├── SKILL.md                      ← Marketing Studio: 9 ad presets + 4–15s ad video
    │   └── cross-surface-workflow.md     ← ms_image / DTC Ads cross-surface workflow
    ├── higgsfield-recall/SKILL.md        ← Recall + regeneration patterns
    ├── higgsfield-cinema/SKILL.md        ← Cinema Studio 2.5 + 3.0 + 3.5 (Soul Cast, Color Grading, 3D Mode, Smart Mode, @ References, Native Audio, three-pill UI, Image Mode, Cinematic models picker)
    ├── higgsfield-seedance/
    │   ├── SKILL.md                      ← Seedance 2.0 prompt director + content-filter preflight
    │   ├── ENGINE-RULES.md               ← Hard rendering constraints shared across the Seedance family
    │   ├── PRODUCTION-PATTERNS.md        ← Tutorial-demonstrated production patterns
    │   ├── HELL-GRIND.md                 ← Higgsfield's open-sourced 95-min feature pipeline
    │   └── FAILURE-MODES.md              ← 8 named Seedance render failures (symptom · mechanism · counter)
    ├── higgsfield-seedance-2-5/
    │   ├── SKILL.md                      ← Seedance 2.5 omni-reference dialect + 4-mode router
    │   ├── MODE-PLAYBOOKS.md             ← Edit / extend / storyboard / blockout / one-click / transitions
    │   └── VFX-PIPELINE.md               ← AI-VFX pipeline: asset routing, size-ref frame, omni_reference v2v, slop catalog
    ├── higgsfield-acting/SKILL.md        ← Performance craft: objective, beats, eye life, master profile
    ├── higgsfield-vibe-motion/SKILL.md   ← Vibe-based motion direction
    └── higgsfield-workspaces/SKILL.md    ← Workspace-first decision layer (Cinema Studio / Lipsync / Draw-to-Video / Sora 2 Trends / Click to Ad / Higgsfield Audio)

Generation Ledger

python3 scripts/higgsfield_memory.py log-gen adze --model seedance_2_0 \
  --tags dialogue-cu,two-char --outcome rejected --reason extra-cuts
python3 scripts/higgsfield_memory.py ratio adze --credits     # hit rates + money view
python3 scripts/higgsfield_memory.py budget adze --shots plan.json   # price before burning

Maintenance — two activation steps

Two capabilities ship inactive on purpose and need a one-time setup.

1. Activate the scheduled spec-drift check

higgsfield auth login                 # if not already authenticated locally
gh secret set HIGGSFIELD_CREDENTIALS < ~/.config/higgsfield/credentials.json

2. Let routing telemetry accumulate before pruning

log-route / routing (in scripts/higgsfield_memory.py) record which sub-skills each request opens, so "which skills are load-bearing, which to retire" becomes a data question:

python3 scripts/higgsfield_memory.py log-route --skills higgsfield-prompt,higgsfield-camera
python3 scripts/higgsfield_memory.py routing     # ranks opens, lists the never-opened tail

This is instrumentation, not a verdict — let real requests accumulate before acting on the tail. A small sample is not evidence a skill is dead.

Example Prompts

Basic:

"Write me a Higgsfield prompt for a cinematic action chase through a night market"

Specific:

"I need a horror prompt using VHS style, Dutch angle camera, and the Horror Face preset"

With reference:

"I have a Soul ID character. Write 3 different scene prompts with her — office, party, rooftop"

Model question:

"Should I use Kling 3.0 or Sora 2 for a large-scale battle scene?"

Troubleshoot:

"My image-to-video isn't animating, it's just static. What am I doing wrong?"

The MCSLA Formula

Letter	Layer	Example
M	Model	Kling 3.0
C	Camera	FPV Drone weaving through the alley
S	Subject	A woman in a tactical jacket
L	Look	Cinematic, cold blue shadows, 16:9
A	Action	She sprints, slides under a gate

Built February 2026 · v3.26.0 (updated 2026-08-08) · Platform: higgsfield.ai

File tree

175

OSideMedia/higgsfield-ai-prompt-skillView on GitHub

.claude/
  commands/
    release.md
    validate.md
  rules/
    cinematic-vocab.md
    image-models.md
    model-reference.md
    photodump-presets.md
    prompt-formula.md
  settings.json
.gitattributes
.github/
  workflows/
    spec-drift.yml
    validate.yml
.gitignore
.markdownlint.json
assets/
  fonts/
    DejaVuSansCondensed-Bold.ttf
    DejaVuSansCondensed-Oblique.ttf
    DejaVuSansCondensed.ttf
    DejaVuSansMono.ttf
    README.md
CHANGELOG.md
CLAUDE.md
CONTRIBUTING.md
db/
  filter-memory.json
  ledger/
    _demo.json
    _global.json
    README.md
  memory-summary.md
  quality-memory.json
  routing-log.json
DISCIPLINE.md
docs/
  archive/
    AUDIT-2026-06-03.md
    CHANGELOG-v3.0-v3.14.md
    HISTORY.md
  Seedance 2 Skill.md
  user-guide/
    MANIFEST.json
evals/
  cases/
    audio.json
    cinema.json
    harvest.json
    models.json
    prompt.json
    seedance-2-5.json
    seedance.json
  run_evals.py
image-models.md
INDEX.md
LICENSE
model-guide.md
photodump-presets.md
production-benchmarks.md
prompt-examples.md
README.md
requirements.txt
scripts/
  build_index.py
  generate_user_guide.py
  higgsfield_memory.py
  refresh_specs.py
  seedance_lint.py
  sub_skill_descriptions.py
  sync_specs.py
  validate_user_guide.py
  validate.py
SKILL.md
skills/
  higgsfield-acting/
    SKILL.md
  higgsfield-apps/
    SKILL.md
  higgsfield-assist/
    SKILL.md
  higgsfield-audio/
    SKILL.md
  higgsfield-camera/
    SKILL.md
  higgsfield-canvas/
    SKILL.md
  higgsfield-character-design/
    SKILL.md
  higgsfield-cinema/
    SKILL.md
  higgsfield-content-factory/
    publish-and-report-workflow.md
    SKILL.md
  higgsfield-facs/
    SKILL.md
  higgsfield-gpt-image-2/
    reference-sheet-workflow.md
    SKILL.md
    static-ads-workflow.md
  higgsfield-image-shots/
    SKILL.md
  higgsfield-marketing-studio/
    cross-surface-workflow.md
    SKILL.md
  higgsfield-mixed-media/
    SKILL.md
  higgsfield-models/
    MODELS-DEEP-REFERENCE.md
    SKILL.md
  higgsfield-moodboard/
    SKILL.md
  higgsfield-motion/
  higgsfield-motion-design/
    SKILL.md
    SKILL.md
  higgsfield-pipeline/
    SKILL.md
  higgsfield-prompt/
    SKILL.md
  higgsfield-recall/
    SKILL.md
  higgsfield-recipes/
    SKILL.md
  higgsfield-seedance/
  higgsfield-seedance-2-5/
    MODE-PLAYBOOKS.md
    SKILL.md
    VFX-PIPELINE.md
  higgsfield-seedance-vfx/
    references/
      dialogue-timing.md
      first-frame.md
    SKILL.md
    ENGINE-RULES.md
    FAILURE-MODES.md
    HELL-GRIND.md
    PRODUCTION-PATTERNS.md
    SKILL.md
  higgsfield-shotlist-director/
    SKILL.md
  higgsfield-soul/
    SKILL.md
  higgsfield-stack/
    SKILL.md
  higgsfield-style/
    SKILL.md
  higgsfield-troubleshoot/
    SKILL.md
  higgsfield-vibe-motion/
    SKILL.md
  higgsfield-workspaces/
    SKILL.md
  shared/
    negative-constraints.md
specs/
  audio-model-specs.json
  AUDIO-MODEL-SPECS.md
  audio-model-specs.yaml
  cli_baseline.json
  image-model-specs.json
  IMAGE-MODEL-SPECS.md
  image-model-specs.yaml
  model-specs.json
  MODEL-SPECS.md
  model-specs.yaml
  models_explore_snapshot_2026-06-11.json
  models_explore_snapshot_2026-06-22.json
  models_explore_snapshot_2026-07-05.json
  models_explore_snapshot_2026-08-01.json
  models_explore_snapshot_2026-08-07.json
  models_explore_snapshot_audio_2026-07-05.json
  models_explore_snapshot_audio_2026-08-01.json
  models_explore_snapshot_image_2026-06-22.json
  models_explore_snapshot_image_2026-07-05.json
  models_explore_snapshot_image_2026-08-01.json
templates/
  01-cinematic-action-chase.md
  02-product-ugc-showcase.md
  03-horror-atmosphere.md
  04-fashion-editorial.md
  05-sci-fi-vfx.md
  06-portrait-character-intro.md
  07-landscape-establishing-shot.md
  08-comedy-social-media.md
  09-romantic-intimate.md
  10-dance-music-performance.md
  ad-asset-prep.md
  character-design/
    9-question-character-sheet.md
    character-web.md
    premise.md
    story-spine.md
    style-sheet.md
    world-sheet.md
  seedance/
    anime-animation.md
    facs-expression-beats.md
    footage-vfx-transform.md
    global-style-prefix.md
    multi-character-anchor.md
    omni-reference-2-5.md
    single-character-position.md
    top-down-map.md
    worked-example-two-character.md
  text-overlays/
    slogan.md
    speech-bubble.md
    subtitle.md
tests/
  conftest.py
  fixtures/
    cli_1_0_1_model_get_seedance_2_0.json
    cli_1_0_1_model_list_video.json
    models_explore_snapshot_2026-06-11.json
  test_ledger.py
  test_lint_rules.py
  test_memory.py
  test_refresh.py
  test_routing.py
  test_sync_specs.py
  test_validate.py
vocab.md
workspace/
  input/
    .gitignore
    README.md
  output/
    .gitignore
    README.md
  processed/
    .gitignore
    README.md
  README.md

FAQ

What is higgsfield-ai-prompt-skill?: A comprehensive Claude skill library for generating high-quality prompts on Higgsfield AI — the cinematic video and image generation platform.
How do I install higgsfield-ai-prompt-skill?: Run these in Claude Code: npx -y skills add OSideMedia/higgsfield-ai-prompt-skill --agent claude-code. Then prompt normally.
Does higgsfield-ai-prompt-skill auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is higgsfield-ai-prompt-skill free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.