skill-evolution
$
npx mdskill add yonatangross/orchestkit/skill-evolutionAnalyzes skill usage patterns to suggest improvements, apply changes, or roll back versions.
- Helps review skill performance and manage version control for automated enhancements.
- Integrates with Read, Write, Edit, Grep, and Glob tools for data processing.
- Decides recommendations based on usage patterns, user edits, and success rates.
- Presents results through evolution reports, version history, and command outputs.
SKILL.md
.github/skills/skill-evolutionView on GitHub ↗
---
name: skill-evolution
license: MIT
compatibility: "Claude Code 2.1.76+."
description: "Analyzes skill usage patterns and suggests improvements. Use when reviewing skill performance, applying auto-suggested changes, or rolling back versions."
argument-hint: "[subcommand] [skill-id]"
context: inherit
version: 1.0.0
author: OrchestKit
tags: [skill-management, evolution, versioning, analytics]
user-invocable: false
disable-model-invocation: true
allowed-tools: [Read, Write, Edit, Grep, Glob]
complexity: medium
persuasion-type: collaborative
metadata:
category: document-asset-creation
---
# Skill Evolution Manager
Enables skills to automatically improve based on usage patterns, user edits, and success rates. Provides version control with safe rollback capability.
## Overview
- Reviewing how skills are performing across sessions
- Identifying patterns in user edits to skill outputs
- Applying learned improvements to skill templates
- Rolling back problematic skill changes
- Tracking skill version history and success rates
## Quick Reference
| Command | Description |
|---------|-------------|
| `/ork:skill-evolution` | Show evolution report for all skills |
| `/ork:skill-evolution analyze <skill-id>` | Analyze specific skill patterns |
| `/ork:skill-evolution evolve <skill-id>` | Review and apply suggestions |
| `/ork:skill-evolution history <skill-id>` | Show version history |
| `/ork:skill-evolution rollback <skill-id> <version>` | Restore previous version |
---
## How It Works
The skill evolution system operates in three phases:
```
COLLECT ANALYZE ACT
─────── ─────── ───
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ PostTool │──────────▶│ Evolution │──────────▶│ /ork:skill- │
│ Edit │ patterns │ Analyzer │ suggest │ evolution │
│ Tracker │ │ Engine │ │ command │
└─────────────┘ └─────────────┘ └─────────────┘
│ │ │
▼ ▼ ▼
┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ edit- │ │ evolution- │ │ versions/ │
│ patterns. │ │ registry. │ │ snapshots │
│ jsonl │ │ json │ │ │
└─────────────┘ └─────────────┘ └─────────────┘
```
Load details: `Read("${CLAUDE_SKILL_DIR}/rules/pattern-detection-heuristics.md")` for tracked edit patterns and detection regexes. Load details: `Read("${CLAUDE_SKILL_DIR}/rules/confidence-scoring.md")` for suggestion thresholds.
---
## Subcommands
Each subcommand is documented with implementation details, shell commands, and sample output. Load details: `Read("${CLAUDE_SKILL_DIR}/references/evolution-commands.md")`
### Report (Default)
`/ork:skill-evolution` — Shows evolution report for all tracked skills with usage counts, success rates, and pending suggestions.
### Analyze
`/ork:skill-evolution analyze <skill-id>` — Deep-dives into edit patterns for a specific skill, showing frequency, sample counts, and confidence scores.
### Evolve
`/ork:skill-evolution evolve <skill-id>` — Interactive review of improvement suggestions. Uses `AskUserQuestion` for each suggestion (Apply / Skip / Reject). Creates version snapshot before applying.
### History
`/ork:skill-evolution history <skill-id>` — Shows version history with performance metrics per version.
### Rollback
`/ork:skill-evolution rollback <skill-id> <version>` — Restores a previous version after confirmation. Current version is backed up automatically.
---
## Data Files
| File | Purpose | Format |
|------|---------|--------|
| `.claude/feedback/edit-patterns.jsonl` | Raw edit pattern events | JSONL (append-only) |
| `.claude/feedback/evolution-registry.json` | Aggregated suggestions | JSON |
| `.claude/feedback/metrics.json` | Skill usage metrics | JSON |
| `skills/<cat>/<name>/versions/` | Version snapshots | Directory |
| `skills/<cat>/<name>/versions/manifest.json` | Version metadata | JSON |
---
## Auto-Evolution Safety
Load details: `Read("${CLAUDE_SKILL_DIR}/rules/auto-evolution-triggers.md")` for full safety mechanisms, health monitoring, and trigger criteria.
Key safeguards: version snapshots before changes, auto-alert on >20% success rate drop, human review required, rejected suggestions never re-suggested.
---
## References
Load on demand with `Read("${CLAUDE_SKILL_DIR}/references/<file>")`:
| File | Content |
|------|---------|
| `evolution-commands.md` | Subcommand implementation, shell commands, and sample output |
| `evolution-analysis.md` | Evolution analysis methodology |
| `version-management.md` | Version management guide |
## Rules
Load on demand with `Read("${CLAUDE_SKILL_DIR}/rules/<file>")`:
| File | Content |
|------|---------|
| `pattern-detection-heuristics.md` | Edit pattern categories and regex detection |
| `confidence-scoring.md` | Suggestion thresholds and confidence criteria |
| `auto-evolution-triggers.md` | Safety mechanisms and trigger criteria |
---
## Related Skills
- `ork:configure` - Configure OrchestKit settings
- `ork:doctor` - Diagnose OrchestKit issues
- `feedback-dashboard` - View comprehensive feedback metrics
More from yonatangross/orchestkit
- agent-orchestrationAgent orchestration patterns for agentic loops, multi-agent coordination, alternative frameworks, and multi-scenario workflows. Use when building autonomous agent loops, coordinating multiple agents, evaluating CrewAI/AutoGen/Swarm, or orchestrating complex multi-step scenarios.
- ai-ui-generationAI-assisted UI generation patterns for json-render, v0, Bolt, and Cursor workflows. Covers prompt engineering for component generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality assurance. Use when generating UI components with AI tools, rendering multi-surface MCP visual output, reviewing AI-generated code, or integrating AI output into design systems.
- analyticsQuery cross-project usage analytics. Use when reviewing agent, skill, hook, or team performance across OrchestKit projects. Also replay sessions, estimate costs, and view model delegation trends.
- animation-motion-designAnimation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, page transitions, micro-interactions, gesture-driven UIs, or ensuring motion accessibility with prefers-reduced-motion.
- architecture-patternsArchitecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right architecture tier for project scope.
- ascii-visualizerASCII diagram patterns for architecture, workflows, file trees, and data visualizations. Use when creating terminal-rendered diagrams, box-drawing layouts, progress bars, swimlanes, or blast radius visualizations.
- assessAssesses and rates quality 0-10 with pros/cons analysis. Use when evaluating code, designs, or approaches.
- async-jobsAsync job processing patterns for background tasks, Celery workflows, task scheduling, retry strategies, and distributed task execution. Use when implementing background job processing, task queues, or scheduled task systems.
- audit-fullFull-codebase audit using 1M context window. Security, architecture, and dependency analysis in a single pass. Use when you need whole-project analysis.
- audit-skillsAudits all OrchestKit skills for quality, completeness, and compliance with authoring standards. Use when checking skill health, before releases, or after bulk skill edits to surface SKILL.md files that are too long, have missing frontmatter, lack rules/references, or are unregistered in manifests.