utility-self-improving

utility-self-improving is a Session review & learning skill for AI agents, published by skanehira in the dotfiles repository on GitHub. Skillspace rates utility-self-improving D (63/100) and it passed the safety scan; the rating is based on static analysis only.

過去セッション履歴 (~/.claude/archive/) からユーザーが繰り返し指摘したパターン (3 回以上観測) を抽出し、dotfiles の Claude 設定 (CLAUDE.md/rules/skills/agents/hooks) を改善する Draft PR を作成する。launchd からの週次無人実行も想定。「自己改善」「過去履歴から改善を抽出」「最近の指摘を rules に反映したい」「ハーネスを継続改善」などで起動。引数で解析期間 (日数、省略時は直近 7 日) を指定可能。

Grade
D
Quality
63 / 100
Safety
Passed
GitHub stars
87

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

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

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

View source on GitHubskanehira/dotfiles

Our review

Architecture
86 / 100
Maturity
Structured: ships references or scripts
Security scan
Low-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • mentions secrets in text

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

Better-rated skills in Session review & learning

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