Audit skills

Skill ronniepinnell/casper/skills/audit-skills

Efficiency audit of a skill library on four measured axes — token cost, ceremony/duplication bloat, trigger-description precision, and overlap clusters — plus usage axes when invocation telemetry exists. Every claim carries a number; findings land as diffs and budgets, not advice. Use before tightening skills, after adding many, or as a periodic library health check.From its SKILL.md

Install

npx -y skills add ronniepinnell/casper --skill audit-skills

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.7 KB, 549 tokens by cl100k_base, as published. Nobody here has run it

/audit-skills — A Number or It Didn't Happen

Skills are input tokens paid on every invocation. "This skill feels bloated" is a claim; this skill replaces it with measurements — and marks what it cannot measure UNVERIFIED instead of guessing.

Invocation

/audit-skills                       # audit the high-traffic set
/audit-skills --all                 # every skill in the library

Procedure

Measure (python3 scripts/audit_skills.py --json out.json — works on any skills/<name>/SKILL.md tree): per skill, token estimate, bloat % (preamble + cross-skill duplicated boilerplate), trigger-description flags, and overlap clusters (shingle Jaccard, no heavy deps).
Fold in usage only if real telemetry exists (an invocation log). Absent that, dead-weight and trigger-precision are reported UNVERIFIED — fire counts are never invented.
Classify before cutting — the heuristics lie sometimes: dense procedure (big, low ceremony) → keep; deliberate shared blocks → keep; extractable payload (verbatim templates, catalogs) → move to references/ with a read-on-demand stub; true overlap → merge.
Bank the result as a budget: record each audited skill's size + ~10% headroom and wire a lint check that fails on re-bloat. Prove the gate: append filler, watch it fail, revert.
Refute your own edit — measure the before/after token delta and run the library's full check suite before claiming "tighter, behavior unchanged". End with ONE verdict line, logged to the ledger:

AUDIT: skills | <n> in scope | <before>→<after> tok | tightened: <list> | UNVERIFIED: <axes or none>

Rules

Size alone is not bloat; dense forced procedure is the product.
"Dead" requires a fire count; "overlapping" requires a similarity score AND a human-verified same-job read.
UNVERIFIED axes stay UNVERIFIED until telemetry exists. Re-run then.

Composes with

/refute — step 5 is a forced refutation of the audit's own claim.
/gate — the per-skill budget is a standing gate.
/verdict — AUDIT: lines land in the ledger; the next audit diffs against the last.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most audit compliance skills give in 549 tokens

Counted across 960 of the 1,589 authors here whose files we hold, read 2026-09-06

Read product marketing context before asking questionsin 29 of 960, across 11 files
Rank findings by severityin 29 of 960, across 22 files
Generate audit reportin 22 of 960
Run the audit scriptin 20 of 960, across 19 files
Generate a prioritized action plan reportin 19 of 960, across 11 files
Ensure one H1 per pagein 15 of 960, across 5 files
Ensure sitemap exists and is accessiblein 14 of 960, across 4 files
Verify alt text on all imagesin 12 of 960, across 3 files
Determine the audit scope before startingin 12 of 960, across 4 files
Verify important pages allowed in robots.txtin 11 of 960, across 2 files
Detect business type from homepage signalsin 11 of 960, across 7 files
Delegate specialized tasks to subagentsin 11 of 960, across 7 files

Said here and by no other author read

Fold in usage only if real telemetry exists
Classify skills before cutting them
Record each audited skill's size plus headroom
Measure the before and after token delta
Run the library's full check suite

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.