Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →karanb192/scorecard
Show the CLAUDE.md compliance scorecard — which rules Claude actually follows vs ignores
Passed 11 of 21 test cases with the skill, and 8 of 21 without it.
and 5 more in the full report
6 fixed6 passed either way8 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
How does the compliance scorecard invocation handle stderr when running the dead-rules-audit script?
| Checked | Without skill | With skill |
|---|---|---|
| Redirects stderr to dev null during script execution | Missed | Passed |
The instructions your model reads when the skill loads.
!node "${CLAUDE_SKILL_DIR}/../../dead-rules-audit.js" --render 2>/dev/null || node "${CLAUDE_PLUGIN_ROOT}/dead-rules-audit.js" --render
The card above is a worst-first audit of your CLAUDE.md rules, aggregated across
your recent sessions: how often each rule was relevant to an edit, how often it was
violated, its heuristic compliance %, and a ⚠ promote→hook flag for rules Claude
chronically ignores. It is produced by the dead-rules-audit hook, which records
as you work.
Briefly call out the 1-3 worst offenders and, for any rule flagged
promote→hook, suggest making it deterministic (a PreToolUse/PostToolUse hook or
a lint rule) instead of relying on Claude to remember it. Keep it short; do not
re-run any commands.
test cases passed, vs 8 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.