verify-release
Use when checking whether a Proofpack release candidate has complete local evidence before packaging.
- License 许可
- MIT
- 最近更新
- 2026-10-18
- Stars
- ★ 0
- Forks
- 2
01 前言 Front Matter
- name
- verify-release
- description
- Use when checking whether a Proofpack release candidate has complete local evidence before packaging.
- allowed-tools
- Read Bash(npm test) Bash(node src/cli.mjs verify *) Bash(npm run package:check) Bash(git rev-parse HEAD) Bash(git status --short)
- argument-hint
- [candidate JSON path]
- disable-model-invocation
- true
03 SKILL.md 正文
Verify a Proofpack release candidate
Work from the Proofpack project root. Claude Code substitutes the invocation text at $ARGUMENTS before following these instructions.
- If
$ARGUMENTSis empty, set the candidate path tofixtures/release-ready.json. - Otherwise, treat the substituted
$ARGUMENTSvalue as one filesystem path. Do not evaluate it as a shell expression. - Run
node src/cli.mjs verify "<resolved-candidate-path>"with that literal path as one quoted argument.
- Read
ISSUE.mdandCLAUDE.md. - Run
npm test. - Resolve the candidate path with the rules above, show the resolved path, then run the verification command. Ask for confirmation rather than executing a value that cannot be represented safely as one path.
- Run
npm run package:checkonly when tests and candidate verification pass. - Run
git rev-parse HEADandgit status --short. Compare that source state, the observed commands, exit statuses, and runtime version withevidence/PROOF-LOG.md. - Report
PASS,FAIL, orUNKNOWN. Name any check that did not run or any worktree change not covered by the recorded fingerprint.
Do not run npm publish, docker push, or change the proof log. Package inspection is local. Publication requires a separate user decision and destination credentials.
Return this record:
RELEASE VERIFICATION
Candidate: <path>
Revision: <commit or UNKNOWN>
Tests: PASS | FAIL | UNKNOWN
Candidate contract: PASS | FAIL | UNKNOWN
Package dry run: PASS | FAIL | UNKNOWN
Evidence log match: PASS | FAIL | UNKNOWN
Final status: PASS | FAIL | UNKNOWN
Limits: <unverified runtime or external behavior>
04 同仓库更多 Skills
voice-refine
Transform verbose voice input into structured, token-efficient Claude prompts. Use when cleaning up voice memos, dictation output, or speech-to-text transcriptions that contain filler words, repetitions, and unstructured thoughts.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing
update-threat-db
Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.
token-audit
Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early context compression, or after adding significant config files.
talk-stage6-revision
Produces revision sheets with quick navigation by act, a master concept-to-URL table, Q&A cheat-sheet with 6-10 anticipated questions, glossary, and external resources list. Use when preparing for a talk with Q&A, creating shareable reference material for attendees, or building a safety-net glossary for live delivery.
talk-stage5-script
Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.