- 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 -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 -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 -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 -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/skills/en/skill-engineering/skill-evaluationFrom the publisher
skill-up and interpret results and limitations.evals/, historical failures, and the current change scope.rule_based; use script for executable artifacts; use a calibrated agent_judge only when semantic judgment is necessary.skill-up validate; run skill-up run or the local trace runner only with authorized credentials and targets. Record run metadata, traces, judges, artifacts, and limitations.skill-up is the primary Eval Engine. Trace checks are a deep-evidence layer; do not create another Engine, Judge, Benchmark, or Quality Score.skill.selection trace evidence is BLOCKED.skill-up validate is not runtime semantic validation. Static checks, CLI smoke, Project Done, and one semantic observation cannot be promoted automatically to release or business claims.unknown for unknown values; preserve NOT_RUN, UNASSESSED, BLOCKED, or INSUFFICIENT_EVIDENCE when evidence is incomplete.NOT_RUN, BLOCKED, UNASSESSED, or INSUFFICIENT_EVIDENCE with natural language such as “not verified.”prompts/skill-evaluation.md for the complete execution and report contract.evals/ and its fixtures before selecting a judge.skill-up validate or a dry-run as proof of runtime or semantic effectiveness.BLOCKED.prompts/skill-evaluation.md before producing the report.evals/ first, then load fixtures, examples, and scripts as needed.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…---# skills/en/skill-engineering/skill-evaluation/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 evaluation and evaluation design.
FAQ
Download skills/en/skill-engineering/skill-evaluation/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.