Audit skills

Skill ronniepinnell/casper/skills/audit-skills

👻 The friendly ghost in your git. Your AI said done — Casper makes it prove it. Claim-evidence hooks + a verdict ledger for Claude Code.

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.

2 things to look at

27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
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.

What its author says it does

Copied from the file, not written here

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.

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.

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

Counted across 936 of the 1,487 authors here whose files we hold, read 2026-08-06

group findings by severityin 44 of 936
Fetch latest guidelines before each reviewin 43 of 936, across 3 files
Check files against all fetched rulesin 42 of 936, across 2 files
Output findings in terse file:line formatin 41 of 936, across 3 files
Ask user which files to review if none specifiedin 41 of 936, across 3 files
Read specified files or prompt user for filesin 39 of 936, across 1 file
generate the audit reportin 39 of 936, across 36 files
assign a severity to every findingin 25 of 936
run automated accessibility scansin 23 of 936, across 13 files
map findings to WCAG criteriain 20 of 936, across 10 files
confirm audit scopein 19 of 936, across 9 files
check title tags and meta descriptions for uniquenessin 19 of 936, across 5 files

Said here and by no other author read

measure token cost and bloat per skill
mark axes without telemetry as UNVERIFIED
never invent fire counts
move extractable payload to references
merge true overlaps
record audited skill sizes with ten percent headroom

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.