agentleFS
Vix0007Vix0007/vixero-skills/skills/skill-graph/SKILL.md

skill-graph

Skill1 starsChanged 7 months agoMITView on GitHub

Map how multiple SKILL.md files interact, conflict, or compose. Use when the user pastes a list of skills, a skills directory structure, or asks to audit a skill collection for redundancy, trigger-keyword overlap, or composition gaps. Returns a conflict matrix, redundancy flags, and recommended merges or splits.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do not rewrite skills. That is skill-compress's job.

    line 70
  2. Distinctive:

    When trigger keywords conflict, recommend specificity in descriptions, not deletion of skills.

    line 71
  3. Distinctive:

    If the collection has < 3 skills, return a lightweight report and suggest growing the collection before graphing.

    line 72
  4. Distinctive:

    If two skills score 3 (redundant), pick the leaner one by token count to keep.

    line 73

≈ “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-graph

Analyze a skills collection as a system. Find overlaps, gaps, and composition patterns.

Trigger on

  • "audit my skills folder / collection"
  • "do these skills conflict"
  • "which skills overlap"
  • User pastes two or more SKILL.md frontmatters together
  • "how do my skills work together"

Input shapes accepted

  1. Multiple pasted SKILL.md files
  2. A list of name: description pairs
  3. A directory listing (names only) — treat as partial analysis, warn about missing descriptions

Analysis passes

Pass 1 — trigger keyword extraction

For each skill, extract the trigger verbs and synonym nouns from its description.

Pass 2 — overlap matrix

Build a matrix. Two skills overlap when ≥ 2 trigger keywords match AND the stated output is similar. Score 0–3:

scoremeaning
0disjoint
1minor keyword overlap, different output
2significant overlap — user intent ambiguous
3redundant — merge or delete one

Pass 3 — composition chains

Flag skills that naturally compose. If skill A's output is skill B's input, note it. Example: token-audit → skill-compress → token-budget-check.

Pass 4 — coverage gaps

Identify intent categories the collection does not cover. Compare trigger verbs against common agentic task verbs (draft, review, audit, compose, generate, plan, debug, refactor, summarize, translate, explain, compare, rank).

Output

skills: {n}
total trigger keywords: {n}
unique trigger keywords: {n} ({ratio}% unique — higher is healthier)

overlap matrix (only scores ≥ 2 shown):
  {skill-a} × {skill-b}: {score}  — {reason}
  ...

composition chains:
  {a} → {b} → {c}
  {d} → {e}

redundancy flags:
  MERGE: {a} + {b}  (overlap 3)
  SPLIT: {x}  (does >1 job)

coverage gaps:
  {missing-intent-1}
  {missing-intent-2}

Hard rules

  • Do not rewrite skills. That is skill-compress's job.
  • When trigger keywords conflict, recommend specificity in descriptions, not deletion of skills.
  • If the collection has < 3 skills, return a lightweight report and suggest growing the collection before graphing.
  • If two skills score 3 (redundant), pick the leaner one by token count to keep. Name both in the output.

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.