# Skill Evolver

Analyze skill execution traces to identify issues and automatically evolve/improve skills.

- Repository: https://github.com/dp-archive/archive (1107 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-03-04
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add dp-archive/archive --skill skill-evolver -g -a claude-code -y`
Codex: `npx skills add dp-archive/archive --skill skill-evolver -g -a codex -y`
Cursor: `npx skills add dp-archive/archive --skill skill-evolver -g -a cursor -y`
Gemini CLI: `npx skills add dp-archive/archive --skill skill-evolver -g -a gemini-cli -y`

## Description

Analyze skill execution traces to identify issues and automatically evolve/improve skills. Use when users provide trace files (JSON) from skill runs and want to improve skill performance based on real execution data. Triggers on requests like "analyze traces", "evolve skill based on traces", "improve skill from execution history", "find issues in skill traces", or when working with skill trace/log files.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Skill Evolver

Analyze skill execution traces to discover issues, identify improvement opportunities, and apply fixes to skill files.

## Trace Format

Traces are JSON with this structure:

```json
{
  "id": "uuid",
  "request": "user's original request",
  "skills_used": ["skill-name"],
  "success": true/false,
  "total_turns": 2,
  "total_input_tokens": 5000,
  "total_output_tokens": 200,
  "duration_ms": 7000,
  "steps": [
    {"role": "assistant", "content": "...", "tool_name": null},
    {"role": "tool", "tool_name": "...", "tool_input": {}, "tool_result": "..."}
  ],
  "llm_calls": [
    {"turn": 1, "stop_reason": "tool_use", "input_tokens": 2500, "output_tokens": 50}
  ]
}
```

## Workflow

This skill can receive two types of input (at least one required):
- **Traces**: Execution trace data from real skill runs, provides data-driven problem discovery
- **Feedback**: User-written improvement suggestions, provides directed guidance for changes

When both are provided, combine insights: use traces to validate/discover issues and feedback to prioritize and guide fixes.

### Step 1: Analyze Inputs

**If traces are provided**, run the analysis script:

```bash
scripts/analyze_traces.py <traces.json> [--skill <name>] [--format json|text]
```

Output includes:
- Success rate
- Average turns, duration, tokens
- Common issues and warnings
- Recommendations

**If feedback is provided**, identify the user's improvement goals and map them to actionable changes.

**If both are provided**, cross-reference: does the feedback align with trace-discovered issues? Use feedback to prioritize which trace-identified problems to fix first.

### Step 2: Extract Issue Details

For failed or problematic traces, extract full context:

```bash
scripts/extract_issue_context.py <traces.json> --failed
scripts/extract_issue_context.py <traces.json> --trace-id <id> --show-llm
scripts/extract_issue_context.py <traces.json> --high-turns
```

The rest: https://github.com/dp-archive/archive/blob/HEAD/seed_skills/skill-evolver/SKILL.md