Free SKILL.md scraped from GitHub. Clone the repo or copy the file directly into your Claude Code skills directory.
npx versuz@latest install jamie-bitflight-claude-skills-plugins-agentskill-kaizen-skills-kaizen-improvementgit clone https://github.com/Jamie-BitFlight/claude_skills.gitcp claude_skills/SKILL.MD ~/.claude/skills/jamie-bitflight-claude-skills-plugins-agentskill-kaizen-skills-kaizen-improvement/SKILL.md---
name: kaizen-improvement
description: Transform transcript analysis findings into actionable improvements. Triggers on "generate hooks from findings", "improve agent", "fix anti-pattern", "kaizen improvement", "generate hook proposals", or "create improvement plan". Provides templates for hook generation, agent prompt refinement, skill patches, CLAUDE.md updates, and script automation from analysis data.
---
# Kaizen Improvement
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).
## Improvement Types
Five categories of output, each with a delegation template:
1. **Hook generation** — PreToolUse deny/redirect, SubagentStart context injection, Stop quality gates
2. **Agent prompt refinement** — surgical fixes to agent system prompts via @subagent-refactorer
3. **Skill patches** — add missing knowledge to skills via /plugin-creator:skill-creator
4. **CLAUDE.md updates** — project-wide behavioral rules
5. **Script automation** — replace repeated manual workflows with scripts or skills
For detailed templates and examples, see [Improvement Templates](./references/improvement-templates.md).
For the Autonomous Refinement Loop (ARL) knowledge base — Layer 3 implementation details, prerequisites, and research synthesis — see [ARL Knowledge](../../references/arl.md).
## Workflow
```mermaid
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]
```
## Hook Generation
Read findings → generate hook configuration + optional script. For patterns mapped to each anti-pattern type, guidelines, and examples, see [Hook Patterns](./references/hook-patterns.md).
## Delegation Protocol
Improvements are instruction sets for specialist agents, not direct edits. Follow outcome-focused delegation:
- Describe the problem with evidence (session IDs, tool calls, frequency)
- State the desired outcome
- Let the specialist agent determine the implementation approach
- Never prescribe specific code changes in the delegation prompt
## Output Modes
### Draft mode (default)
Write all proposals to `.planning/kaizen/improvements/` as markdown files. Each file contains:
- Finding summary with evidence
- Proposed improvement
- Delegation prompt for the appropriate specialist agent
- Priority score
### Install mode (--install flag)
For hooks only — write directly to `.claude/settings.json` or `hooks/hooks.json`. Other improvement types always produce delegation prompts (never direct edits).
## Priority Scoring
Rank improvements by:
1. **Frequency × Impact** — occurrences across sessions × cost per occurrence
2. **Automation potential** — hooks > scripts > documentation
3. **Blast radius** — project-wide > single-agent > single-session
4. **Implementation cost** — hook (minutes) < CLAUDE.md (minutes) < skill (hours) < agent (days)