verify
Use when a change is about to be committed, or someone asks to verify one. Runs prompts/verify.md — the repo's fast checks (lint, typecheck, the tests the change touches, generated files rebuilt) on the tree being committed, saying what passed, what failed, and what wasn't run.
- License 许可
- MIT
- 最近更新
- 2026-11-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- verify
- description
- Use when a change is about to be committed, or someone asks to verify one. Runs prompts/verify.md — the repo's fast checks (lint, typecheck, the tests the change touches, generated files rebuilt) on the tree being committed, saying what passed, what failed, and what wasn't run.
- argument-hint
- <nothing for the working tree, or the change to verify>
03 SKILL.md 正文
<!-- Claude Code's copy of .agents/skills/verify/SKILL.md, generated by the template's skills:build script; its frontmatter differs by design. Edit the .agents/ file and carry the same change into this one. -->
Run the fast checks exactly as written in prompts/verify.md. Read that file in full first; it
is the authoritative instruction set, and this skill only wires it up.
- Resolve the change: the staged and unstaged diff, unless the request names another.
- Work through the steps in order. Commit nothing here; the commit is the caller's.
- Report using the prompt's "Output of this prompt" contract.
Claude Code runs a project skill named verify before each commit on its own, except for changes
only to docs or tests (from 2.1.286, as checked on 2026-10-07). It takes the place of the bundled
/verify, which builds and drives the app instead; /run still launches it.
04 同仓库更多 Skills
template-update
Use when this repository should take a release of the template it was built from, or a template update pull request needs finishing. Runs prompts/template-update.md — finds the template version it has, reads the CHANGELOG to the release, brings the process files across, merges each parked .template, and does what the release's entries ask.
root-cause
Use when something is broken and the cause isn't known. Runs prompts/investigate.md — reproduce the reported case, confirm a baseline, test hypotheses one at a time, fix the root cause, find sibling occurrences.
review-change
Use when someone asks for a review, a critical or hard look, or a second opinion on a change before it merges, whether a PR, a branch, a diff range, or a pasted diff. Runs prompts/review.md — an adversarial, evidence-cited review, including the "passes its own tests" failures.
pre-pr
Use when a change is ready to leave your hands — before opening or updating a pull request. Runs prompts/pre-pr.md — merge the base, run the full gate, prove new checks can fail, self-review, sweep docs, and draft the description.
plan-change
Use when someone asks to plan a feature, a fix, or a refactor before it's built, or a change is too large to start on directly. Runs prompts/plan-change.md — sizes the change and stops for a small one; otherwise writes docs/changes/<date>-<slug>.md against docs/product.md, AGENTS.md, and the ADRs, with behavior, design, risks, and tasks that each name their test.
harvest
Use when a check proven in one repository should become a standard every repository is held to (in the template repository, where the catalog lives). Runs prompts/harvest.md — prove the check failing in its source, generalize it, write the standard, its probe, and a planted-defect test, and measure which repositories it fails.