skill-fitnesslisted

Use when asking whether installed skills are actually working — why a skill never fires or fires on the wrong requests, which two skills compete for the same request, what the skill listing is costing in context and which skill loses its description first, which skills have never been invoked at all, or which repeated one-off scripts an agent keeps writing should become code inside a skill. Also for scoring a skill against the published quality rubric before shipping it, and for deciding whether a skill that has grown too big, or covers several different things at once, should be broken up or split into separate skills. Measures an installed set from frontmatter and from the session transcript store; it does not teach how to write or deploy a skill.
TheodoreAD/agent-skills · ★ 0 · AI & Automation · score 75

Install: claude install-skill TheodoreAD/agent-skills

# Skill fitness Measures whether a set of skills works, so the fix is chosen from numbers rather than from a hunch. Authoring guidance is `skill-authoring`'s job and this skill does not repeat it; Bash-usage auditing is `session-bash-audit`'s. Evidence behind the rules below, loaded only when you need it: [`references/measurements.md`](references/measurements.md) for what was measured here — the 119-run trigger ledger, the listing budget read from the binary, and the ledger of five heuristics that failed; [`references/research.md`](references/research.md) for published work and other people's tools — SkillsBench, the quality rubric, `skill-creator`, and what the scanners in this space do and do not detect. ## What this skill reads, runs and writes - **Reads**: skills directories — `./skills` in a checkout, `~/.agents/skills`, `~/.claude/skills`, or whatever `--root` names; Claude Code's `~/.claude/projects/*.jsonl` and `~/.claude.json` for usage and the listings actually sent; a git ref through `git archive` for `--ref`. - **Runs**: `git archive` for `--ref`. `trigger.py` runs `claude -p` in a temporary directory — the only thing in this skill that spends tokens, and it is refused for a suite whose skills you do not have. - **Writes**: a derivable baseline, only where `derivable --save-baseline <path>` says. `trigger.py` writes a candidate command file into a temporary directory it deletes on exit. Nothing into any skill, any repo, or the install hub. - **Netw