본문으로 건너뛰기
cccskills
무료GitHub에 공개

jevaluate-harness

Use when running a jevaluate rating round, re-rating after a rubric change, changing the jevaluate rubric, or publishing ratings to the jev-mode ratings folder.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tiffygk/jev-mode
설치 방법 보기

포함된 파일(23)

  • SKILL.md2.4 KB
  • fixtures/bad-rating-evidence/files/src__x.py103 B
  • fixtures/bad-rating.md1.5 KB
  • fixtures/bad-rating.md.steps.json517 B
  • fixtures/good-rating-evidence/files/src__x.py103 B
  • fixtures/good-rating.md1.5 KB
  • fixtures/good-rating.md.steps.json517 B
  • freeze_tag_check.py2.6 KB
  • images/skills-dark.png407.6 KB
  • images/skills-light.png364.7 KB
  • publish.md900 B
  • rater-brief.md2.1 KB
  • rating-round.md4.3 KB
  • README.md3.7 KB
  • rubric-change.md3.3 KB
  • scan_transcripts.py2.8 KB
  • scripts/check_release.py3.3 KB
  • scripts/dispute_packet.py3.6 KB
  • scripts/harness_status.py2.9 KB
  • test_dispute_packet.py2.3 KB
  • test_release.py2.1 KB
  • test_scan.py4.9 KB
  • test_status.py2.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Jevaluate Harness

The maintainer's process for jevaluate. One rating is jevaluate/read.md; testing the rubric is the jevaluate-eval skill. If $JEVALUATE_OVERLAY is set, read that file first; its rules override the defaults here.

Settings (yours, not in this skill)

  • $JEVALUATE_LIBRARY: the private ratings library (default ~/.claude/jevaluate-library if it exists, else ~/.jevaluate-library).
  • $PRIVATE_TERMS: your never-publish regexes, one per line. library.py export reads only $JEVALUATE_LIBRARY/private-terms.txt, so keep the file there (or symlink it) and have your pre-push hook read the same file.
  • $JEVALUATE_OVERLAY: a markdown note of your own rules for these workflows, read first; no required format.

Two principles

  • Code checks, text explains: every rule has a row in jevaluate/enforcement.md naming the check that refuses a wrong answer, or why it stays judgment.
  • Ask for what is observed: raters record type, the calls-Jev line, each decision's stakes as read and the verdict; library.py add derives kind and every n.a.

Workflows

Open the file for the workflow and follow it in order; each step names the gate that must pass.

WorkflowFileDone when
Change the rubricrubric-change.mdjevaluate-eval passes and the owner approves the version
Rate or re-rate projectsrating-round.md (rater prompt: rater-brief.md)every rating logged by library.py add, scan clean
Publish ratingspublish.mdone pull request, reviewed

To see where you are: python3 jevaluate-harness/scripts/harness_status.py <ledger> --workflow rubric|round (round runs through publishing). It reruns the scripted gates it has (the materials check), reads the other steps from the ledger, and names the file to open next. Ledger lines: done: <step> <YYYY-MM-DD> <evidence>. Steps: rubric = rules-written, materials-checked, quiz-passed, eval-passed, owner-approved, frozen; round = picked, sized, costs-approved, rated, scanned, adjudicated, final-gate, release-check, published.

Keep a ledger per workflow: each step, each ruling with its cost if wrong, and tokens per agent. Record rulings and handoffs where your overlay says, or in the ledger.

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

jev-lens

무료

Legacy. Use only when images (photos, illustrations, screenshots) must reach TypeSafe's Jev (System One) model as text, because the request can't send the `TypeSafe-Danger-Zone-Images` header that lets Jev read images directly. Triggers on "turn this photo into a Jev state", "describe these images for Jev", "decode images for System One", or a Jev project whose decision depends on what a picture shows. Handles 1 to about 100 images; produces a neutral, complete decode and a JSON state, checked against Jev.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tiffygk/jev-mode122026년 10월 16일 업데이트

jev-sources

무료

Finds and quotes TypeSafe's docs on Jev, including Noul, Choice, Score and Box questions, models and limits. Use when a question, review, design or claim involves Jev or System One, when briefing a subagent on Jev work, or when relaying a subagent's Jev finding.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tiffygk/jev-mode122026년 10월 16일 업데이트

jevaluate

무료

Use when rating whether a project, repo, skill, workflow, plugin, agent product or post uses TypeSafe's Jev (System One) model well -- "is this a good use of Jev?", "rate this Jev integration", "jevaluate <url>", or a link to something named after Jev; also when checking whether something that calls itself Jev actually uses it.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tiffygk/jev-mode122026년 10월 16일 업데이트

jevaluate-eval

무료

Use when testing whether the jevaluate rubric and instructions lead graders to the right answers: after a rubric or instruction change, before freezing a rubric, before publishing ratings, or when a grader's calls look wrong.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tiffygk/jev-mode122026년 10월 16일 업데이트

jevaluate-private

무료

Rates a project with Jevaluate and keeps the rating private, with the same rubric and checks, a private library that export refuses, and nothing pushed or published. Use when a rating must stay private, such as "/jevaluate-private" followed by a link or folder, "rate this privately", "evaluate my own project", a client's or employer's code, a design doc or a local folder that isn't public, or any rating that must not reach the public ratings or the repo.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

tiffygk/jev-mode122026년 10월 16일 업데이트

tiffygk의 스킬 모두 보기

이 스킬의 문제 신고