jamie-bitflight/kaizen-improvement

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.

For the Autonomous Refinement Loop (ARL) knowledge base — Layer 3 implementation details, prerequisites, and research synthesis — see ARL Knowledge.

Workflow

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.

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)