/visual-flow-gif
Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer. Use when the user wants to turn source material into a static PNG + animated GIF diagram.
$ npx -y skills add AI-Builder-Club/skills --skill visual-flow-gif --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/visual-flow-gif
Context preview
The summary Claude sees to decide when to auto-load this skill.
Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer. Use when the user wants to turn source material into a static PNG + animated GIF diagram.
SKILL.md
visual-flow-gif.SKILL.mdname: visual-flow-gif
description: Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer. Use when the user wants to turn source material into a static PNG + animated GIF diagram.
user_invocable: true
Visual Flow GIF
Use this skill when a user wants to turn source material into a clear animated flow diagram.
The output should include:
- A static PNG diagram.
- An animated GIF with visible motion.
- The JSON spec used to render the diagram when useful for later edits.
Workflow
1. Read the source material and identify the system.
- Inputs, outputs, actors, modules, tools, stores, and feedback loops.
- Main steps, decision points, shared artifacts, and arrow direction.
- Any visual constraints from a reference image.
2. Create a JSON spec.
- Start from `${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/assets/default-spec.json` for the default light theme.
- Start from `${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/assets/dark-spec.json` only when the user asks for a dark version.
- Use short English labels unless the user asks for another language.
- Use explicit `x`, `y`, `w`, and `h` values for predictable layout.
- Use custom multi-point paths for routed arrows. Corners are rounded by default.
- Add important modules to `animation.pulses`; pulse highlights are strong by default.
- See `${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/references/spec-format.md` for field details.
3. Render the diagram.
Requires Python 3.10+ and Pillow 10+. If Pillow is missing, install it first: `python3 -m pip install -r ${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/requirements.txt`
python3 ${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/scripts/render_animated_gif.py \
--spec /path/to/spec.json \
--outdir /path/to/output \
--basename diagram \
--verify \
--check4. Inspect the PNG and GIF before delivery.
- Text is readable and not clipped.
- Labels and arrows do not overlap important content.
- Arrow directions match the source material.
- The GIF has visible motion.
- Pulse highlights are clearly visible in both light and dark modes.
- The full system fits inside the frame.
Style Guide
- Prefer a clean technical diagram with a lightweight editorial feel.
- Use the light theme by default.
- Use the dark theme only when the user asks for a dark version.
- Prefer Excalifont when available; the renderer falls back automatically.
- Keep important labels bold enough to scan quickly.
- Use rounded routed arrows instead of hard right-angle turns.
- Use color to separate roles:
- Blue for core process areas.
- Green for active loops, tools, memory, or operational panels.
- Purple for shared layers, archives, or internal systems.
- Red for friction, risk, warnings, or signals.
- Keep node labels short and concrete.
- Do not invent structure, metrics, claims, or arrow direction that is not present in the source.
Quality Bar
Always run with `--verify --check` before delivery.
`--verify` prints sampled frame differences so the GIF animation can be confirmed.
`--check` validates that:
- PNG and GIF files exist.
- Output dimensions match the spec.
- GIF frame count matches the spec.
- Sampled frames contain visible motion.
Read more
name: visual-flow-gif description: Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON specification and a local Python/Pillow renderer. Use when the user wants to turn source material into a static PNG + animated GIF diagram. user_invocable: true
Visual Flow GIF
Use this skill when a user wants to turn source material into a clear animated flow diagram.
The output should include:
- A static PNG diagram.
- An animated GIF with visible motion.
- The JSON spec used to render the diagram when useful for later edits.
Workflow
1. Read the source material and identify the system.
- Inputs, outputs, actors, modules, tools, stores, and feedback loops.
- Main steps, decision points, shared artifacts, and arrow direction.
- Any visual constraints from a reference image.
2. Create a JSON spec.
- Start from `${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/assets/default-spec.json` for the default light theme.
- Start from `${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/assets/dark-spec.json` only when the user asks for a dark version.
- Use short English labels unless the user asks for another language.
- Use explicit `x`, `y`, `w`, and `h` values for predictable layout.
- Use custom multi-point paths for routed arrows. Corners are rounded by default.
- Add important modules to `animation.pulses`; pulse highlights are strong by default.
- See `${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/references/spec-format.md` for field details.
3. Render the diagram.
Requires Python 3.10+ and Pillow 10+. If Pillow is missing, install it first: `python3 -m pip install -r ${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/requirements.txt`
python3 ${CLAUDE_PLUGIN_ROOT}/skills/visual-flow-gif/scripts/render_animated_gif.py \
--spec /path/to/spec.json \
--outdir /path/to/output \
--basename diagram \
--verify \
--check4. Inspect the PNG and GIF before delivery.
- Text is readable and not clipped.
- Labels and arrows do not overlap important content.
- Arrow directions match the source material.
- The GIF has visible motion.
- Pulse highlights are clearly visible in both light and dark modes.
- The full system fits inside the frame.
Style Guide
- Prefer a clean technical diagram with a lightweight editorial feel.
- Use the light theme by default.
- Use the dark theme only when the user asks for a dark version.
- Prefer Excalifont when available; the renderer falls back automatically.
- Keep important labels bold enough to scan quickly.
- Use rounded routed arrows instead of hard right-angle turns.
- Use color to separate roles:
- Blue for core process areas.
- Green for active loops, tools, memory, or operational panels.
- Purple for shared layers, archives, or internal systems.
- Red for friction, risk, warnings, or signals.
- Keep node labels short and concrete.
- Do not invent structure, metrics, claims, or arrow direction that is not present in the source.
Quality Bar
Always run with `--verify --check` before delivery.
`--verify` prints sampled frame differences so the GIF animation can be confirmed.
`--check` validates that:
- PNG and GIF files exist.
- Output dimensions match the spec.
- GIF frame count matches the spec.
- Sampled frames contain visible motion.
A Claude Code plugin marketplace of the skills we share at for building loop engineers: agents that get triggered on their own, pick up work, ship it, verify it, and log what they learned, so the work compounds without you prompting every step.
Repo: AI-Builder-Club/skills
Other skills on ai-builder-club-skills.
- /agent-context-audit
Audit a repo's agent context — CLAUDE.md files, codebase docs, skills, and tool/MCP designs — against Anthropic's Claude 5 context-engineering guidance ("unhobbling": Anthropic cut ~80% of Claude Code's system prompt with no eval loss). Finds overconstraint, conflicting
Open skill - /crabbox-setup
Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup. Each agent gets its own full stack (own DB + dev server) and an in-box browser for e2e, so concurrent loops never collide on ports/state.
Open skill - /dev-local-setup
Scaffold a one-command `dev-local` launcher for ANY codebase. Investigates the repo to find its services, ports, and infra dependencies, then generates a single `scripts/dev-local.sh` (up/down/status/logs/restart) that runs every dev server in one tmux session, plus a short
Open skill - /e2e-setup
Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want
Open skill - /new-loop
Spin up a new loop (domain) in a file-based knowledge base — bootstrap the substrate if it's missing, gather the loop's charter, scaffold domains/<loop>/README.md, then do ONE real test run and record it in the loop's Timeline and LOG.md. Use when the user says "set up a new
Open skill - /open-agent-teams
Delegate tasks to ANY CLI agent (claude, codex, aider, ...) running in a detached tmux session, with a race-safe done-signal protocol and multi-turn iteration. Use when delegating work to a non-Claude CLI agent, when the user says "tmux delegate", "run agent in tmux", "delegate
Open skill

