verify
An integrated skill that runs the combined validation of build / typecheck / test / lint in one shot. The `verify.mjs` engine auto-discovers validation commands via a discovery chain (AGENTS.md's 「検証」 section → package.json scripts → justfile/Makefile/lefthook → language heuristics), executes them serially with their source attached, and returns a result summary. If a higher-priority stage produces a hit, only that stage is executed (no crossing stages).
- License 许可
- MIT
- 所属仓库
- ozzy-labs/skills
- 最近更新
- 2026-07-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- description
- An integrated skill that runs the combined validation of build / typecheck / test / lint in one shot. The `verify.mjs` engine auto-discovers validation commands via a discovery chain (AGENTS.md's 「検証」 section → package.json scripts → justfile/Makefile/lefthook → language heuristics), executes them serially with their source attached, and returns a result summary. If a higher-priority stage produces a hit, only that stage is executed (no crossing stages).
- allowed-tools
- Bash, Read
- argument-hint
- [--dry-run] [--json] [--repo-root=<dir>]
02 资源文件 1
- 脚本verify.mjs18.1 KB
03 SKILL.md 正文
verify
Read .agents/skills/verify/SKILL.md and follow the workflow procedure.
Important: The discovery chain of validation commands, serial execution, and rendering of the result summary are handled by the verify.mjs engine. Present the engine's stdout as-is; do not reformat or reinterpret it.
Claude Code-specific additions
Running the engine
Execute verify.mjs in the same directory via Bash (passing $ARGUMENTS as-is). In user-scope it's ~/.claude/skills/verify/verify.mjs, in dogfood it's <repo>/.claude/skills/verify/verify.mjs:
node ~/.claude/skills/verify/verify.mjs $ARGUMENTS
Argument parsing
Determine the presence of --dry-run (alias --discover) / --json / --repo-root=<dir>. Since the engine interprets all of these, it's sufficient to simply pass $ARGUMENTS as-is.
Completion report / next-action suggestion
End once the engine output has been presented. Even if there are failed commands, do not automatically fix or re-run here (leave that to the caller's judgment). Do not suggest next actions either.
04 同仓库更多 Skills
usage-guard
Monitors Claude Code's Usage Limit (5-hour = Current / weekly = Weekly), pauses work when it exceeds 95%, and automatically resumes once the reset restores headroom. Bundles an engine form that a caller such as drive Reads at a checkpoint, and a standalone form, `/usage-guard "<continuation command>"`, that guards arbitrary work. Claude-only (depends on the OAuth usage-rate endpoint + ScheduleWakeup).
topics
Selects GitHub topic candidates by having the `topics.mjs` engine perform constraint validation, popularity measurement, broad+narrow / singular-plural comparison, and hardcoded ozzy-labs conventions, then applies them via `gh repo edit --add-topic` following the policy's `externally-visible` gate (default batch-confirm). Scope is limited to use within ozzy-labs.
skill-observability
Defines the skill observability event contract (event.schema.json) and emit substrate (obs-emit.mjs). The SSOT for the measurement layer of the skill improvement loop. Referenced by other skills and hooks.
skill-metrics
Aggregates the local observability event log (~/.agents/observability/events.jsonl) and presents, read-only, per-skill invocation counts and notable events (fallback / HITL rejection / loop cap reached / abort). Fires on "show me the skill metrics," "aggregate the observability results," "which skills get used the most?" Does not send anything.
ship
Runs verification, commit, and PR creation all at once. An integrated pipeline that runs verify (build + type + test + lint) → commit → PR creation in sequence against the changes.
review
Reviews code changes or PRs across 11 perspectives, reporting via JSON structured output plus a human-readable report. Supports switching between quick and deep modes. Takes a PR number or working-tree diff as input.