AGENT SKILL

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 $ARGUMENTS is empty, set the candidate path to fixtures/release-ready.json.
  • Otherwise, treat the substituted $ARGUMENTS value 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.
  1. Read ISSUE.md and CLAUDE.md.
  2. Run npm test.
  3. 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.
  4. Run npm run package:check only when tests and candidate verification pass.
  5. Run git rev-parse HEAD and git status --short. Compare that source state, the observed commands, exit statuses, and runtime version with evidence/PROOF-LOG.md.
  6. Report PASS, FAIL, or UNKNOWN. 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

313DEVGRP
313DEVGRP/Java-Service-Tree-Framework-Multi-Agent-Workspace

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.

★ 0
313DEVGRP
313DEVGRP/Java-Service-Tree-Framework-Multi-Agent-Workspace

validate-changes

Evaluate staged changes using LLM-as-a-Judge before committing

★ 0
313DEVGRP
313DEVGRP/Java-Service-Tree-Framework-Multi-Agent-Workspace

update-threat-db

Delegate threat-intelligence research and updates to AgentSec, then validate the guide and landing mirrors.

★ 0
313DEVGRP
313DEVGRP/Java-Service-Tree-Framework-Multi-Agent-Workspace

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.

★ 0
313DEVGRP
313DEVGRP/Java-Service-Tree-Framework-Multi-Agent-Workspace

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.

★ 0
313DEVGRP
313DEVGRP/Java-Service-Tree-Framework-Multi-Agent-Workspace

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.

★ 0