From agentskill-kaizen
Transforms analysis findings into hooks, agent prompt refinements, skill patches, CLAUDE.md updates, and automation scripts. Activates on kaizen/improvement requests or manual /kaizen-improvement.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentskill-kaizen:kaizen-improvementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Transform analysis findings from `.planning/kaizen/` into actionable improvements — hooks, agent patches, skill refinements, CLAUDE.md updates, and automation scripts.
Transform analysis findings from .planning/kaizen/ into actionable improvements — hooks, agent patches, skill refinements, CLAUDE.md updates, and automation scripts.
Prerequisite: Analysis findings must exist in .planning/kaizen/ (generated by the transcript-analysis skill).
Five categories of output, each with a delegation template:
For detailed templates and examples, see Improvement Templates.
For the Autonomous Refinement Loop (ARL) knowledge base — Layer 3 implementation details, prerequisites, and research synthesis — see ARL Knowledge.
flowchart TD
Start([Read analysis findings]) --> Parse[Extract anti-patterns with frequency and evidence]
Parse --> Score[Score by frequency × impact]
Score --> Top[Select top findings]
Top --> Type{Improvement type?}
Type -->|Repeated tool misuse| Hook[Generate hook — deny/redirect]
Type -->|Agent behavior issue| Agent[Generate agent patch instruction set]
Type -->|Knowledge gap| Skill[Generate skill patch instruction set]
Type -->|Project-wide issue| Claude[Generate CLAUDE.md addition]
Type -->|Manual workflow| Script[Generate automation proposal]
Hook --> Output[Write to .planning/kaizen/improvements/]
Agent --> Output
Skill --> Output
Claude --> Output
Script --> Output
Output --> Install{--install flag?}
Install -->|Yes| Apply[Write hooks to settings, apply patches]
Install -->|No| Draft[Leave as proposals for review]
Read findings → generate hook configuration + optional script. For patterns mapped to each anti-pattern type, guidelines, and examples, see Hook Patterns.
Improvements are instruction sets for specialist agents, not direct edits. Follow outcome-focused delegation:
Write all proposals to .planning/kaizen/improvements/ as markdown files. Each file contains:
For hooks only — write directly to .claude/settings.json or hooks/hooks.json. Other improvement types always produce delegation prompts (never direct edits).
Rank improvements by:
npx claudepluginhub jamie-bitflight/claude_skills --plugin agentskill-kaizenConverts failed runs, confusing transcripts, or user feedback about autoresearch-skill into a bounded improvement plan, eval scenario, and patch checklist without automatically applying changes.
Reviews completed coding sessions to extract actionable improvements: DX friction, documentation gaps, architecture issues, anti-patterns, bug prevention, and tooling updates.
Reads improvement plans generated by skill-quality-reviewer and automatically applies changes to Claude Skills. Useful for executing structured improvements from quality reviews.