Smoke
Verifies real, rendered behavior on this project's frontend (local/preview/staging/prod, unauthed or authed) via a real headless-Chromium Playwright browser — the DEFAULT way to check "does this render correctly / does this look right / is this actually live" for any coding agent, not just Claude Code. Use when asked to "smoke test", "verify the live/prod page", "check if X actually rendered", "run a browser smoke", "does this look right on preview", "verify an authed role's flow", or as a post-merge/pre-PR verification step. Wraps the project's scripts/live-smoke.mjs — a real screenshot + JSO
Install
npx skills add danybgoode/golden-frijoles --skill smokegit clone --depth 1 https://github.com/danybgoode/golden-frijoles.git /tmp/golden-frijoles
mkdir -p ~/.claude/skills
cp -r /tmp/golden-frijoles/skills/plugins/golden-frijoles/skills/smoke ~/.claude/skills/smokePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# smoke — the scripted default for verifying rendered behavior
> **Running this skill's scripts.** Each `node scripts/<name>.mjs <args>` below means, from the project root:
> `if [ -f scripts/<name>.mjs ]; then node scripts/<name>.mjs <args>; else npx -y @golden-frijoles/kit@1.17.5 <name> <args>; fi`
> The project's own copy always wins. The kit needs no install and copies nothing into the repo. If npx fails on
> the network or the registry (ENOTFOUND, ECONNREFUSED, ETIMEDOUT, E404, a proxy error), report **could not
> look: the kit is unreachable**, not a broken project, and offer to retry online or to copy the script into
> `scripts/`. This covers the scripts the kit carries (`frijoles-kit --list`). Any other `scripts/` command here is
> project tooling: if the project lacks it, say so and stop. Never re-implement a script's logic inline.
> If a script prints `GF-NEEDS-SETTING {"key",…}`, ask the user that question once, save the answer with
> `npx -y @golden-frijoles/kit@1.17.5 config set <key> <value>` (always the kit, never local-wins: a project
> may own an unrelated `scripts/config.mjs`), tell them they can change it later the same way, and run the
> script again if it exited 7.
> It drives the app's own Playwright `browser` project. A project spawned from `template/` gets a runnable
> `apps/example-app` harness with the ad-hoc spec and an auth-helper stub to fill in. **If its config or theDetails
- Skill name
smoke- Repository
- danybgoode/golden-frijoles
- Path
skills/plugins/golden-frijoles/skills/smoke/SKILL.md- Repo updated
- 17 November 2026
- Listed in
- karanb192/awesome-claude-skills
FAQ
What does the Smoke skill do?
Verifies real, rendered behavior on this project's frontend (local/preview/staging/prod, unauthed or authed) via a real headless-Chromium Playwright browser — the DEFAULT way to check "does this render correctly / does this look right / is this actually live" for any coding agent, not just Claude Code. Use when asked to "smoke test", "verify the live/prod page", "check if X actually rendered", "run a browser smoke", "does this look right on preview", "verify an authed role's flow", or as a post-merge/pre-PR verification step. Wraps the project's scripts/live-smoke.mjs — a real screenshot + JSO
How do I install the Smoke skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add danybgoode/golden-frijoles --skill smoke. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Related skills
Babysit PR
danybgoode/golden-frijoles
Advisory PR watch for a single open PR — retries flaky CI (re-runs failed workflow runs) and surfaces merge conflicts via one comment; never merges, never a required check. Use when the product owner asks to "babysit this PR", "check on open PRs", "retry flaky CI", "is this PR stuck", "why isn't this PR moving", or as the nightly ops routine's third step (once per open PR across the project's repos). Runs scripts/babysit-pr.mjs, which does the gh reads, the retry, and the comment post. A clean PR (no conflict, no failing checks) gets NO comment — this tool never adds nightly noise to a healthy
Build Order Sync
danybgoode/golden-frijoles
Regenerates Roadmap/00-ideas/BUILD-ORDER.md when it has drifted from the SSOT (each epic README's frontmatter status:) and opens a claude/ docs PR with the fix — never hand-edits the board. Use when the product owner asks to "sync the build order", "regenerate BUILD-ORDER.md", "check board drift", "is the build-order board stale", "open a build-order PR", or as the nightly ops routine's first step. Runs scripts/build-order-sync.mjs, which does the check, the regen, and (on real drift) the branch/commit/ push/PR — this skill just invokes it and reports the result.
Doc Hygiene
danybgoode/golden-frijoles
Keeps the always-read session-start docs (this project's AGENTS.md, Roadmap/WAYS-OF-WORKING.md, Roadmap/LEARNINGS.md, Roadmap/README.md poster) from re-bloating after the one-time de-noise sweep. Use when the product owner asks to "check doc hygiene", "measure LEARNINGS size", "is LEARNINGS bloated again", "run the doc hygiene report", or as the weekly Routine C hygiene pass. Runs scripts/doc-hygiene.mjs, reviews its flagged candidates against the source docs, and emits a dated advisory report. Never edits Roadmap docs — proposals only, the product owner or the builder hand-merges.
Prove It Ran
agentkitco/agentkit-dev-skills
Verify that tests, builds and checks actually ran and exercised the changed code, before claiming a task is done. Use before reporting completion, or when asked to prove tests ran or verify a fix.
Wreck Personas
miyannishar/wreck-it
Derive realistic user personas (the app's ideal customers plus built-in normal-user, rushed-beginner and chaos-monkey) and their missions for wreck-it testing, saved to .wreck-it/personas.md. Use as stage 3 of a wreck-it run, or when the user asks "who would use my app", "make test personas", or wants to edit the personas used for testing.
Wreck Load
miyannishar/wreck-it
Page speed and load testing for a local web app with the wreck-it CLI. It measures each page with Lighthouse on a simulated phone (LCP, CLS, TBT), diagnoses slow pages with Chrome DevTools performance traces when available, runs ramp, spike and soak load profiles (p50/p90/p99 latency, error rate, breaking point, memory trend), then traces slow endpoints to causes such as N+1 queries, missing indexes or blocking work. Use as stage 7 of a wreck-it run, or when the user asks to "stress test my API", "load test", "how many users can my app handle", "find slow endpoints", "check page speed", or "ru
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.