Skill Finder
Use ONLY when the user explicitly asks to discover or evaluate a skill from OUTSIDE the curated catalog — e.g., "find a Stripe skill", "is there a skill for X?", "evaluate this candidate before adopting". Meta-skill, complementary to skill-selector: do NOT auto-invoke on routine apm-management, project-init, or catalog-resident requests. Cross-source survey across vetted registries (Anthropic official, claude-skill-registry, VoltAgent/awesome-agent-skills, ComposioHQ, Superpowers, GitHub topic) with a mandatory waxa-eval adoption gate.
Install
npx skills add mizchi/skills --skill skill-findergit clone --depth 1 https://github.com/mizchi/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skill-finder ~/.claude/skills/skill-finderPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skill Finder Adopting a skill found outside the curated catalog has two failure modes the in-catalog flow does not carry: 1. **Low-quality content** — registries vary wildly in vetting; some are SEO scrapes. 2. **Registry blindness** — Tier-1 official sources can already cover the need; jumping to GitHub `grep` first wastes effort and lands in noisier listings. This skill exists to make the cross-source search deliberate and to refuse adoption of anything that has not passed a `waxa` eval. ## When to invoke Explicit user request only. Triggering phrases: - "find a `<X>` skill" - "is there a skill for `<X>`?" - "evaluate `<owner/repo>` as a skill before adopting" - "search the registries for `<X>`" When NOT to use: - The catalog already has a fit → **stop immediately** and tell the user to use `skill-selector` Phase 1 instead. Do NOT continue into Tier 1-4 search, do NOT propose install steps, do NOT survey other sources. Even if the catalog skill is plausibly improvable by something external, the existing fit is the answer; respect Phase 1. - One-off task with no recurrence → solve inline; do not adopt a skill you will trigger once. - The user did not ask for discovery → as a meta-skill, this never auto-fires (cf. user-level CLAUDE.md "Skill 利用方針"). ### Pre-flight check (mandatory first step) Before doing anything else, scan the `skill-selector/references/catalog.md` rows against the user's stated need. If any row matches:
Details
- Skill name
skill-finder- Repository
- mizchi/skills
- Path
skill-finder/SKILL.md- Repo updated
- 18 November 2026
FAQ
What does the Skill Finder skill do?
Use ONLY when the user explicitly asks to discover or evaluate a skill from OUTSIDE the curated catalog — e.g., "find a Stripe skill", "is there a skill for X?", "evaluate this candidate before adopting". Meta-skill, complementary to skill-selector: do NOT auto-invoke on routine apm-management, project-init, or catalog-resident requests. Cross-source survey across vetted registries (Anthropic official, claude-skill-registry, VoltAgent/awesome-agent-skills, ComposioHQ, Superpowers, GitHub topic) with a mandatory waxa-eval adoption gate.
How do I install the Skill Finder skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add mizchi/skills --skill skill-finder. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Skill Finder popular?
It lives in mizchi/skills, which has 423 GitHub stars and 6 forks.
Related skills
Actions CI Tuning
423mizchi/skills
Use when auditing or improving GitHub Actions workflows for a project. Covers cache setup (npm/pnpm/yarn), job parallelism, shard-based test splitting, artifact handling pitfalls, and Playwright-specific patterns. Trigger on: slow CI, cache miss, flaky shard jobs, merge-reports failures, or an explicit 'tune CI' request.
AI Index
423mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English. Two layers — a deterministic lint for removable surface tells (scripts/slopscore.py, no API) and a judgment layer of typed probabilistic questions (Jev noul/score) for the tells that survive editing. Includes measured human/AI baselines, a gap-first calibration procedure, and labeled fixtures. Use when building or calibrating an AI-likeness score, or when a draft needs a defensible number rather than a vibe. For writing guidance use natural-writing-ja / natural-writing-en instead.
Apm Usage
423mizchi/skills
Reference for APM manifests, installation, targeted updates, deployment paths and lockfiles. Invoke when the user explicitly asks about APM or apm.yml, or an unfamiliar APM command/error needs exact CLI details. Do not automatically invoke for every project that happens to have installed skills.
Waxa Eval
423mizchi/skills
Use when iterating on a skill's prompt with the waxa CLI (https://github.com/mizchi/skills/tree/main/tools/waxa) — authoring scenarios, choosing graders, interpreting unclear-points, advancing a ledger, and judging convergence. Encodes the four-stage iteration pattern observed in real iter loops (structural fix → grader breadth → surface-form coverage → residual unclear) and the scenario-design pitfalls (blank-slate executor's network limit, prompt expectation explicitness, regex coverage of Japanese/English surface forms). Meta-skill: do NOT auto-invoke for routine skill edits; fires only whe
Retrospective Codify
423mizchi/skills
Pair "what failed first" with "what finally worked" and codify the should-have-known-it insight as an ast-grep rule, a skill, or a CLAUDE.md rule. Meta-skill: invoke ONLY when the user explicitly says "codify today's lessons," "make it a skill," "drop it into lint," or asks to extract a reusable rule from a trial-and-error fix. Do NOT auto-invoke at every task completion. Spares future-you (or another agent) the same trap.
Benchmark Model
213modular/skills
Benchmark a model served on MAX with the `max benchmark` command: measure throughput (tokens/sec), latency (TTFT, TPOT, inter-token latency), and GPU utilization by driving load against a running `max serve` endpoint. Use this whenever the user wants to benchmark, load-test, or measure the performance of a MAX model, get tokens-per-second / TTFT / TPOT numbers, run a concurrency or request-rate sweep, compare latency vs throughput, size a deployment, or produce benchmark JSON, even if they don't say "benchmark" by name. Also use when a `max benchmark` run fails to connect or reports zero/garba
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.