← ClaudeAtlas

verifylisted

Validate that the implementation satisfies the spec's acceptance criteria. Runs the configured test/lint/build commands, evaluates against spec.md, and produces verify-report.md. Required before /specclaw:pr. Run after all tasks in /specclaw:build are complete.
chan4lk/specclaw · ★ 12 · AI & Automation · score 64
Install: claude install-skill chan4lk/specclaw
# specclaw verify **First, run** `specclaw-ensure-init .specclaw` — idempotently creates `.specclaw/` if it doesn't exist (silent if already initialized; auto-inits using the current directory's basename as the project name). Validate that the implementation satisfies the spec. ## Step 0 — Validate ```bash specclaw-validate-change .specclaw <change> verify ``` If it fails (tasks not all complete), report and stop. **If `.specclaw/context.md` exists**, read it before evaluating — the verifier must check that the implementation respects the project's coding rules, patterns, and constraints documented there, in addition to the spec's acceptance criteria. ## Step 1 — Collect evidence ```bash specclaw-verify collect .specclaw <change> ``` Gathers acceptance criteria from `spec.md`, current contents of changed files, and configured lint/build/test command results — run in that order — followed by the e2e tier when configured. ### E2E tier (`build.e2e_command` + `verify.e2e`) `build.e2e_command` is the slow tier (browser/e2e); `build.test_command` stays the fast tier. `verify.e2e` decides when the slow tier runs: | Policy | Behaviour | |--------|-----------| | `last` (default) | Run e2e only after `lint_command`, `build_command` and `test_command` all pass. An unset fast-tier command is vacuously passing. | | `skip` | Never run e2e. | | `always` | Run e2e even when an earlier gate failed. | An absent `verify.e2e` means `last`; an unrecognised value warns on stderr and f