본문으로 건너뛰기
cccskills
무료GitHub에 공개

skill-release-gate

Evaluate an Agent Skill bundle before release by checking structure, activation conditions, output quality, scripts, safety, file integrity, and host compatibility. Receive a detailed JSON report that distinguishes local evidence checks from production readiness backed by external attestation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.

설치 방법 보기

이럴 때 유용합니다

  • Reviewing a skill bundle before distribution
  • Evaluating activation accuracy and output improvements
  • Checking scripts, safety, and distributed files
  • Assessing host compatibility and release evidence

포함된 파일(8)

  • SKILL.md3.9 KB
  • assets/hosts.json752 B
  • assets/manifest.json782 B
  • evals/artifacts.json316 B
  • evals/cases.json866 B
  • evals/evidence.json606 B
  • references/eval-contract.md3.6 KB
  • scripts/evaluate_skill.py37.6 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Skill release gate

Use this skill before publishing or distributing an Agent Skill directory bundle.

Workflow

  1. Resolve SKILL_ROOT to the absolute directory containing this installed SKILL.md. Do not assume the process cwd is the installed bundle.
  2. Resolve TARGET_ROOT from the original workspace working directory and resolve the user-supplied candidate as an absolute TARGET_BUNDLE.
  3. Read references/eval-contract.md from SKILL_ROOT.
  4. Inspect the positive and near-miss trigger cases in evals/cases.json under TARGET_BUNDLE.
  5. Inspect the shared baseline and with-skill assertions in evals/artifacts.json under TARGET_BUNDLE.
  6. Inspect the explicit script and safety results in evals/evidence.json under TARGET_BUNDLE.
  7. Inspect the declared runtime capabilities in assets/hosts.json under TARGET_BUNDLE and verify the target file hashes against its assets/manifest.json.
  8. For production, replace deterministic predictions, artifacts, evidence, and host capabilities with captured results; set all four captured modes; and bind every raw trigger observation, both artifacts, the complete evidence set, and the non-empty host matrix to non-empty sources and matching SHA-256 provenance digests. These local checks can set localEvidenceReady, but locally recomputable hashes do not prove capture.
  9. Obtain an external JSON attestation whose evidenceRoot matches the report, plus the SHA-256 of its exact bytes from a separate trusted policy or release channel. The attestation must be a regular file outside the target bundle.
  10. Before execution, show the exact resolved argv. The installed evaluator is scripts/evaluate_skill.py under SKILL_ROOT. For the shipped lesson fixture, build argv from python3, that absolute evaluator path, --fixture-demo, and the absolute TARGET_BUNDLE. For production, use the same installed script with --attestation, --trusted-attestation-sha256, and the absolute TARGET_BUNDLE, without --fixture-demo.
  11. Return checksPassed, fixturePassed, localEvidenceReady, trustAnchorValid, productionReady, and passed with the evidence root, evaluation modes, failed checks, precision, recall, every raw trigger observation, per-case repeated-run rates, artifact comparison, script and safety evidence, installed-tree verification, and portability matrix. Include the resolved script path, resolved target path, cwd, exact argv, and exit code. Mark unavailable observations unverified.

Output contract

Return the complete JSON evaluation report. Preserve every layer-specific check and its evidence so a passing aggregate cannot hide a routing, artifact, script, safety, installed-tree, or portability failure. fixturePassed reports a successful teaching fixture. localEvidenceReady reports only local digest integrity. passed is true only when productionReady also has a valid out-of-bundle trust anchor.

Failure behavior

If configuration is invalid, provenance is absent or mismatched, the trusted attestation is missing or invalid, a file hash differs, a required capability is absent, or any production gate fails, stop with a nonzero result and report the failed layer. The explicit --fixture-demo path may exit successfully only when fixturePassed is true, and it never makes a release claim. Never publish, install elsewhere, repair evidence, create the trust decision, or weaken a threshold automatically.

Do not publish a bundle merely because SKILL.md parses or one positive prompt activates. Do not label a package portable when a target drops required companion files or ignores required runtime extensions.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Create static SVG diagrams, scalable images for lessons, READMEs, and manuals. It uses real system names, nine diagram types, and consistent colors and arrows, with checks for readable labels, accessible descriptions, and valid markup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Add a diagram of system interactions to a README
  • Explain state transitions in a manual
  • Illustrate data flow from logs or specifications
rohitg00/ai-engineering-from-scratch7.1만2026년 10월 19일 업데이트

Learn AI engineering by building a project one stage at a time. The tutor guides predictions, learner-written code, automated checks, and reflection, then records progress so the next session can continue from the right stage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Learn AI engineering through hands-on projects
  • Resume a project from the next unfinished stage
  • Find coding mistakes with step-by-step hints
rohitg00/ai-engineering-from-scratch7.1만2026년 10월 19일 업데이트

Run a local check of test evidence and retain source paths in the result. The workflow stops when required evidence is missing, keeping the findings tied to their sources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Checking local test evidence
  • Keeping source paths in check results
  • Stopping a check when evidence is missing
rohitg00/ai-engineering-from-scratch7.1만2026년 10월 19일 업데이트

Test your understanding of a phase in AI Engineering from Scratch through eight multiple-choice questions. Receive a score, explanations for incorrect answers, and specific lessons to review before continuing your studies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Checking your understanding after completing a phase
  • Assessing readiness for the next phase
  • Finding lessons to review from incorrect answers
rohitg00/ai-engineering-from-scratch7.1만2026년 10월 19일 업데이트

Prepare for four Claude certification tracks through guided lessons, practical exercises, quizzes, and mock exams. The tutor checks understanding and learner-created work, records progress, and uses assessment results to guide review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Choosing a certification track for a learning goal
  • Resuming lessons from saved progress
  • Completing guided exercises without writing code
rohitg00/ai-engineering-from-scratch7.1만2026년 10월 19일 업데이트

Find relevant lessons in AI Engineering from Scratch from a topic, question, or bug. Get a short selection of lessons, necessary prerequisites, and the next learning command, with dedicated routes for specialized subjects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Finding lessons on a topic you want to learn
  • Locating lessons that explain a bug's underlying cause
  • Choosing what to study next based on your progress
rohitg00/ai-engineering-from-scratch7.1만2026년 10월 19일 업데이트

rohitg00의 스킬 모두 보기

이 스킬의 문제 신고