← ClaudeAtlas

rjv-verify-skilllisted

Write or harden a repo's own `verify` skill - the smoke harness that boots, drives and inspects the running app before a commit. Use when a repo has an app but no verify skill, when a verify run is slow or flaky, or when asked to make an agent able to test its own changes end to end. When to run it lives in rjv-verify.
rjvim/ai-skills · ★ 0 · AI & Automation · score 58
Install: claude install-skill rjvim/ai-skills
# Writing a repo's verify skill A verify skill gives an agent hands and eyes on the running app. It lives in the repo, next to the code it checks, and every agent runs it before a commit. ## 1. Place and name it | Repo | Skill | |---|---| | one app | `.claude/skills/verify/SKILL.md` | | several apps | one per app: `.claude/skills/verify-<app>/SKILL.md` | Codex reads the same files when the repo's `AGENTS.md` points to them. An existing local-test skill (for example `carnelian-local-test`) is a verify skill already: harden it, never add a second one. ## 2. Write five sections 1. **Boot**: the exact command, port, env file, and the ready line to wait for. Reuse a server that is already running; check the port first. Seed data with one command. 2. **Drive**: the tool for this kind of app. Web: `agent-browser` with `rjv-agent-browser-notes`. Mobile: the simulator or emulator MCP. Backend: `curl` or the API harness. Desktop: computer use. 3. **Feature map**: each user flow as path, selectors or calls, and the expected result. This is the rubric the agent grades against. 4. **Inspect**: what counts as proof for each flow: a screenshot at a named width, a response body, a log line, a row in the database. 5. **Teardown**: kill every server, browser and emulator the run started. ## 3. Make it fast and reliable It is the smoke harness for every change, so a slow or flaky one gets skipped. - Time each section. Boot to ready stays under 2 minutes; one flow