- name
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add naodeng/awesome-qa-skills --skill skill-evaluation-zh -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add naodeng/awesome-qa-skills --skill skill-evaluation-zh -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add naodeng/awesome-qa-skills --skill skill-evaluation-zh -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add naodeng/awesome-qa-skills --skill skill-evaluation-zh -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/naodeng/awesome-qa-skills/tree/HEAD/evidence/skill-quality/2026-10-03-codex-pilot/reproduction/packages/skill-evaluation-zhFrom the publisher
skill-up 验证/运行评测并解释结果和限制。evals/、历史失败和本次变更范围。rule_based;可执行工件使用 script;只有需要语义判断时使用校准后的 agent_judge。skill-up validate;有授权凭据和目标时再运行 skill-up run 或本地 trace runner。记录 run metadata、trace、judge、产物和限制。skill-up 是主 Eval Engine;trace checks 只是深证据层,不得再造 Engine、Judge、Benchmark 或 Quality Score。skill.selection trace 时标记 BLOCKED。skill-up validate 不是 runtime 语义验证;静态、CLI smoke、Project Done 和单次语义观察不能自动升级为发布或业务结论。unknown;证据不足保留 NOT_RUN、UNASSESSED、BLOCKED 或 INSUFFICIENT_EVIDENCE。NOT_RUN、BLOCKED、UNASSESSED 或 INSUFFICIENT_EVIDENCE。prompts/skill-evaluation.md。evals/ 和 fixtures。skill-up validate 或 dry-run 当成 runtime 或语义效果证据。BLOCKED。prompts/skill-evaluation.md。evals/,再按需读取 fixtures、examples 和脚本。Use this skill when designing, running, interpreting, or reporting Agent Skill evaluations, selecting cases or judges, and analyzing trigger, benchmark, or regression evidence; triggers include Skill
---name: skill-evaluationdescription: Use this skill when designing, running, interpreting, or reporting Agent Skill evaluations, selecting cases or…---# evidence/skill-quality/2026-10-03-codex-pilot/reproduction/packages/skill-evaluation-zh/SKILL.mdOverview
Use this skill when designing, running, interpreting, or reporting Agent Skill evaluations, selecting cases or judges, and analyzing trigger, benchmark, or regression evidence; triggers include Skill 评测、评测设计、回归评测。
FAQ
Download evidence/skill-quality/2026-10-03-codex-pilot/reproduction/packages/skill-evaluation-zh/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/naodeng/awesome-qa-skills.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.