ai-image-editing
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restoration, and retouch, routed task-first to…
The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using
$ npx -y skills add social-media-skills/skills --skill design-and-templates --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/design-and-templatesContext preview
The summary Claude sees to decide when to auto-load this skill.
The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using
name: design-and-templates description: >- The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using a design tool (Canva/Adobe Express/Figma). For social, consistency + speed beat bespoke. Uses the BRAND framework. Reads brand-profile first. The agent designs the SYSTEM (brand-kit tokens, template set, hierarchy rules, workflow); a design tool or the image tools produce the actual graphics; the finished asset enters the WoopSocial flow (WoopSocial publishes -- it does NOT design or generate). Honest about the ~70-80% on-brand ceiling and AI copyright limits. Distinct from brand-profile (the identity source), thumbnail-design + pinterest-pin-design (single asset types), carousel-writer (copy vs visual frame), and image-prompt + the image tools (generation vs layout). version: 1.0.0
The reusable on-brand **template-system** skill — a **brand kit** + a small set of reusable templates + the rules + the workflow that let a non-designer ship consistent on-brand graphics fast. The agent **designs the system**; a **design tool** or the **image tools** produce the graphics; the **finished asset enters the WoopSocial flow.**
For social, the win isn't one beautiful design — it's **six versions that still look like the same campaign**, produced fast by a non-designer. The lever is a **small reusable template system anchored in a brand kit**, which prevents both **brand drift** and generic **"template energy."** **Brand-kit-first makes the first draft ~80% on-brand instead of ~20%.** The honest ceiling: tools get you **~70–80% on-brand** — a **human eye finishes the hero work.** The agent designs the **system**; a design tool (Canva/Adobe Express/ Figma) or the image tools **produce** the graphics; **WoopSocial publishes the finished asset.**
1. **brand-profile** — the identity source this operationalizes. 2. the **recurring content needs** — what you actually post.
(Depth: `references/the-brand-framework.md`.)
(brand-kit-first = ~80% on-brand drafts).
announcement, Reel cover, Pin); **don't over-build.**
mobile-first.
named/organized; Brand Kit + Magic Switch/Resize.
graphic enters the WoopSocial flow; consistency across the grid; a human finishes the hero pieces.
Design fundamentals (hierarchy/contrast/legibility) are timeless; the **tools** move. **Canva (Magic Studio)** = social-first default (Brand Kit, Magic Design, Magic Switch/Resize, Dream Lab, Bulk Create; Pro ~$15/mo; ~70% "Canva-style" ceiling + AI credit limits; raw AI generally not copyrightable; Canva Shield indemnification Enterprise-only). **Adobe Express+Firefly** = premium, **brand-safe** licensed AI + **IP indemnification**. **Figma** = master design systems/governance (not daily social). Combine by strength zone; brief the image tools (`image-prompt`) or Dream Lab/Firefly for generated imagery: `references/design-tools- 2026-reality.md`. The brand-kit spec, the starter template set + specs, the hierarchy/legibility rules, the production workflow + worked examples: `references/building-the-system.md`.
it specs/advises, it doesn't render.
asset enters the WoopSocial flow** (WoopSocial **publishes** it like any media — it does **NOT** design, template, or generate).
copyrightable** → add human edits; **never fabricate.** (Scope, distinctions + connections: `references/scope-and-connections.md`.)
**design-and-templates (this)** = the reusable template **SYSTEM + brand kit** · **brand-profile** = the identity source it operationalizes · **thumbnail-design** / **pinterest-pin-design** = single asset types (templates **in** the system) · **carousel-writer** = the copy/narrative (this is the visual **frame**) · **image-prompt + the image tools** = generation (this is layout/templates) · **profile-optimization** = the profile assets.
Reads first: **brand-profile** + the **recurring content needs.** Feeds the format siblings: **thumbnail- design**, **pinterest-pin-design**, **instagram-reels-publishing** (cover), **carousel-writer** (the frame its copy fills), **story-writer** — each a template in the system. Briefs for imagery: **image-prompt** → **ideogram**/**flux**/**nano-banana** (or Dream Lab/Firefly). Publishes via: the **finished asset** → **scheduling-and-queue → WoopSocial** (post/Pin/cover/carousel media). Design + generation stay in the design tool / image tools; WoopSocial only publishes.
A reusable system: a brand kit (locked colors/fonts/logo/spacing) plus a small set (~5–7) of named templates mapped to the real recurring formats, each with one focal point, a clear type scale, contrast, safe zones, and mobile-first legibility; a non-designer product
Give your AI agent the skills of a top-1% social media team. 106 of them, free.
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restoration, and retouch, routed task-first to…
The AI music + sound-design skill for social -- original/licensed audio beds and sound design for Reels/TikToks/Shorts/videos. Use when someone needs…
Use to get a brand and its content CITED and RECOMMENDED by AI answer engines — the GEO (Generative Engine Optimization) / AI-search-visibility skill. Run when…
The model-agnostic AI-video router and brief — the counterpart to image-prompt. Use when someone asks "which AI video tool should I use," "make an AI video,"…
The AI narration / voiceover mini-skill (ElevenLabs-led). Use when someone wants an "AI voiceover," "narration," "text-to-speech for a video," "voice for my…
Social media analytics and reporting — read native platform data honestly and turn it into next actions. Use when someone wants to "check my analytics," "see…