self-refinement

self-refinement is a Session review & learning skill for AI agents, published by davidYichengWei in the agentic-engineering-framework repository on GitHub. Skillspace rates self-refinement C (70/100) and it passed the safety scan; the rating is based on static analysis only.

将纠错经验沉淀为持久化的 Rules/Skills 更新，构建反馈闭环。当被用户纠正且错误具有模式性时自动触发，或通过 /reflect 命令手动触发回顾。

Grade
C
Quality
70 / 100
Safety
Passed
GitHub stars
155

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubdavidYichengWei/agentic-engineering-framework

Our review

Architecture
92 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

More Session review & learning skills

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.