10 skills · sorted by relevance
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
The English summary is being prepared. Showing the original description.
Evolve new skills from project experience. Use when a repeating pattern, useful workflow, or hard-won knowledge should be captured as a reusable skill for the current project.
The English summary is being prepared. Showing the original description.
Use when running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.
The English summary is being prepared. Showing the original description.
Self-evolving skill system. Skills are scored after execution (0-100) on 5 dimensions. Score 90+ over 5 runs = crystallized (locked). Score below 30 = auto-repair attempted. Skills improve themselves through usage feedback.
The English summary is being prepared. Showing the original description.
[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead.
The English summary is being prepared. Showing the original description.
[Deprecated] skill lifecycle merged. Use `cm-skill-evolution` instead.
The English summary is being prepared. Showing the original description.
Repair or extend CodyMaster skills with a three-mode loop: FIX, DERIVED, and CAPTURED, grounded in current repo tooling.
The English summary is being prepared. Showing the original description.
Evolve SKILL.md files from agent execution traces using a three-stage pipeline: trajectory collection from observed runs, parallel multi-agent patch proposal for error and success analysis, and conflict-free consolidation of overlapping edits via prevalence-weighting. Based on the Trace2Skill methodology.
The English summary is being prepared. Showing the original description.
基于域健康报告和沙盘Gap记录，识别断裂模式，生成具体的补全行动方案：新Skill提案/现有Skill修改建议/缺失触发链路描述。与 skill-evolution-planner-meta 的区别：后者基于历史日志做宏观演进规划；本Skill基于具体Gap证据做定向修复。触发词：「优化[域名]域」「修复[域名]域Gap」「[域名]域自优化」「根据健康报告生成修复方案」。通常由 skill-closure-verifier-meta 调用，也可独立触发。
The English summary is being prepared. Showing the original description.
Skill体系演进规划 Skill。基于CO-BUILD-LOG（决策轨迹）、PENDING-EXPERIENCES（踩坑模式）、PENDING-SKILLS（需求积压）和SYSTEM-BLUEPRINT（体系蓝图），主动分析Skill体系的演进方向——哪些Skill应该新建、哪些应该合并/拆分、哪些描述需要重写、哪些触发词需要调整、整体编排架构是否需要升级。对应产品侧的 product-evolution-planner。触发词：「Skill体系怎么演进」「Skill体系应该怎么完善」「有没有新的Skill需要建」「Skill体系演进建议」「主动分析Skill体系」「Skill体系下一步」。
The English summary is being prepared. Showing the original description.