agentleFS
Agents365-aiAgents365-ai/skill-visualizer/SKILL.md

skill-visualizer

Skill4 starsChanged 9 months agoMITView on GitHub

Use when user asks to visualize, diagram, or analyze the structure of any skill. Generates Mermaid flowcharts rendered to a single PDF.

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. mhylle/claude-skills-collection★ 20same name
    2. Gtato-ai/skill-visualizer★ 8same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 8 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check mmdc is installed:

    line 26
  2. Distinctive:

    If not installed, inform user:

    line 31
  3. Distinctive:

    Check target skill exists:

    line 37
  4. Distinctive:

    If not found, list available skills and ask user to confirm.

    line 42
  5. Very specific:

    Read SKILL.md + all scripts/configs/templates in the directory

    line 47
  6. Very specific:

    Write .mmd files to temp dir: ~/.claude/skills/<skill-name>/tmp-diagrams/.

    line 59
  7. Distinctive:

    Keep node labels short (≤6 words)

    line 68
  8. Very specific:

    Use meaningful node IDs (e.g.

    line 69
  9. Distinctive:

    If mmdc fails, check error and report to user.

    line 90
  10. Very specific:

    If multiple diagram PDFs, invoke the pdf skill to merge them into one diagrams PDF.

    line 92
  11. Very specific:

    Write summary.md in tmp-diagrams/ — list all diagrams with brief descriptions.

    line 96
  12. Very specific:

    Write suggestions.md in tmp-diagrams/ covering:

    line 98
  13. Distinctive:

    Keep suggestions concise and actionable — bullet points, not essays.

    line 105
  14. Distinctive:

    If user wants changes, help edit the skill based on suggestions

    line 132

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Visualizer

Analyzes any skill's structure and generates Mermaid diagrams, rendered into a single timestamped PDF.

When to Use

  • User says "visualize X skill", "diagram X skill", "show me X skill's flow"
  • User wants to understand a skill's structure visually
  • User asks for structural analysis of a skill

When NOT to Use

  • User only wants to read/review skill code without visualization
  • User asks about skill functionality without requesting diagrams
  • Target skill directory does not exist

Process

Step 0 — Verify prerequisites

Check mmdc is installed:

which mmdc || echo "NOT_INSTALLED"

If not installed, inform user:

mmdc (mermaid-cli) is required. Install with:
npm install -g @mermaid-js/mermaid-cli

Check target skill exists:

ls ~/.claude/skills/<skill-name>/SKILL.md

If not found, list available skills and ask user to confirm.

Step 1 — Read the skill

  • ls the target skill directory to understand file structure
  • Read SKILL.md + all scripts/configs/templates in the directory
  • Note: skill directories live at ~/.claude/skills/<name>/

Step 2 — Analyze & generate Mermaid

Comprehend the skill's full logic, then decide scope:

ComplexityCriteriaAction
Simple≤3 sections, no scripts, linear flowOne comprehensive flowchart
ComplexMultiple scripts, multi-phase, DOT blocksMultiple diagrams: overview + per-phase

Write .mmd files to temp dir: ~/.claude/skills/<skill-name>/tmp-diagrams/.

Mermaid guidelines

  • flowchart TD for overviews and decision trees
  • flowchart LR for linear phase sequences
  • {{"Decision"}} diamond nodes for conditional branches
  • -.-> dashed arrows for loops/backtracking
  • subgraph to group related steps
  • Keep node labels short (≤6 words)
  • Use meaningful node IDs (e.g. parse_input not A)

Example template

flowchart TD
    start([Start]) --> check_input{{"Input valid?"}}
    check_input -->|Yes| process[Process data]
    check_input -->|No| error[Show error]
    process --> output[Generate output]
    output --> done([End])
    error -.-> start

Step 3 — Render diagrams to PDF

Render each .mmd directly to PDF:

mmdc -i X.mmd -o X.pdf -b white -t default

If mmdc fails, check error and report to user.

If multiple diagram PDFs, invoke the pdf skill to merge them into one diagrams PDF.

Step 4 — Write summary & suggestions

Write summary.md in tmp-diagrams/ — list all diagrams with brief descriptions.

Write suggestions.md in tmp-diagrams/ covering:

  • Clarity: Are instructions unambiguous? Any contradictions?
  • Completeness: Missing edge cases, error handling, or "when NOT to use"?
  • Structure: Could sections be reordered or split for better flow?
  • Actionability: Are steps concrete enough for Claude to follow without guessing?

Keep suggestions concise and actionable — bullet points, not essays.

Step 5 — Finalize & cleanup

  1. Convert both .md files to PDF via the pdf skill.
  2. Merge all PDFs (diagrams + summary + suggestions) into one final PDF via the pdf skill. Order: diagrams → summary → suggestions.
  3. Move final PDF to skill root with timestamp: ~/.claude/skills/<skill-name>/<skill-name>-YYYYMMDD-HHMMSS.pdf
  4. Optionally move summary/suggestions .md files to skill root (timestamped).
  5. Clean up — delete tmp-diagrams/.

Note: Historical PDFs are preserved (timestamp naming prevents overwrite).

Output Structure

~/.claude/skills/<skill-name>/
├── SKILL.md
├── <skill-name>-YYYYMMDD-HHMMSS.pdf           # all-in-one PDF
├── <skill-name>-YYYYMMDD-HHMMSS-summary.md    # optional
└── <skill-name>-YYYYMMDD-HHMMSS-suggestions.md # optional

After Running

  1. Present diagram descriptions from summary to the user
  2. Share structural suggestions
  3. If user wants changes, help edit the skill based on suggestions

Requirements

  • mmdc (mermaid-cli): npm install -g @mermaid-js/mermaid-cli
  • pdf skill for merging PDFs

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.