- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add coco-research/coco --skill agent-self-eval -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add coco-research/coco --skill agent-self-eval -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add coco-research/coco --skill agent-self-eval -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add coco-research/coco --skill agent-self-eval -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/coco-research/coco/tree/HEAD/skills/agent-self-evalDe l'éditeur
@agents/PROMPT-DEFENSE.md
Score your own output (or another agent's output) across four axes to identify quality gaps and feed improvements into the learning system.
/team:* pipeline run/gsd-execute-phase for quality tracking5 — Exceptional: no reasonable improvement possible
4 — Good: minor nits only, no substantive gaps
3 — Adequate: meets request but has notable weakness on ≥1 axis
2 — Weak: clear gap affecting usability or correctness
1 — Poor: fundamentally misses request or contains significant errors
Every score below 5 MUST cite specific evidence. A score of 3 cannot just say "could be better" — it must say exactly what is missing or wrong. "Show the gap, don't just name it."
Gather:
Rate 1-5 with mandatory evidence for scores <5.
SELF-EVALUATION REPORT
======================
Task: {brief description}
Overall: {weighted average}/5
CORRECTNESS: {score}/5
Evidence: {specific finding or "No issues found"}
CLARITY: {score}/5
Evidence: {specific finding or "No issues found"}
ACTIONABILITY: {score}/5
Evidence: {specific finding or "No issues found"}
CONCISENESS: {score}/5
Evidence: {specific finding or "No issues found"}
IMPROVEMENT INSTINCTS:
- {trigger} → {action} (confidence: {0.3-0.9})
If learning system is active (PR-27+), auto-generate instinct YAML from findings:
---
id: eval-{task-slug}-{axis-lowercase}
trigger: "when {task type}"
action: "{specific improvement}"
confidence: 0.6
domain: quality
source: self-eval
scope: project
---
/team:verify invokes self-eval on Layer 2 output before Layer 3 review/gsd-execute-phase runs self-eval per subagent, aggregates in SUMMARY.mdPost-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output qu
---name: agent-self-evaldescription: Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and…---# skills/agent-self-eval/SKILL.mdVue d'ensemble
Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output quality.
FAQ
Téléchargez skills/agent-self-eval/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/coco-research/coco.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.