# Evolve

> Distill Skill Autopilot's accumulated usage evidence into personalized rules — the self-evolution step. Use when the autopilot announces an evolution window, or the user says "evolve", "学习一下我的习惯", "update your instincts", "distill autopilot".

- **Type:** Skill
- **Install:** `agentstack add skill-winterddo-claude-code-skill-autopilot-evolve`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [WinterDDo](https://agentstack.voostack.com/s/winterddo)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [WinterDDo](https://github.com/WinterDDo)
- **Source:** https://github.com/WinterDDo/claude-code-skill-autopilot/tree/main/plugins/skill-autopilot/skills/evolve

## Install

```sh
agentstack add skill-winterddo-claude-code-skill-autopilot-evolve
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Evolution pass (prompt-space gradient descent)

You are updating this system's weights: the personalized rules injected into every prompt. Be conservative — a wrong learned rule costs the user on every message.

## Procedure

1. Read `~/.claude/command-autopilot/events.jsonl`. Also read `learned.json` if present (schema below).
2. Cluster events by task-type × command/skill. Look for consistent patterns, for example:
   - a command suggested repeatedly and consistently dismissed → candidate negative rule
   - a skill invoked on the same kind of task again and again → candidate positive rule ("invoke X early for Y-type tasks")
   - a habit self-used regularly → mastered, teaching for it should stop
3. Apply the discipline:
   - **Promote** only patterns with ≥3 consistent observations and no contradicting evidence → `status: "in_force"`.
   - **Demote** existing in_force rules contradicted by new evidence (decrement `evidence`; at 0, set `status: "candidate"`).
   - **Decay**: rules not reconfirmed for ~60 days → delete.
   - Max 5 in_force rules; each `text` ≤ 25 tokens, English, imperative, generic phrasing ("research-type tasks: offer /fork early").
   - NEVER write rules that override the safety net (/rewind) or the one-suggestion contract.
4. Write `learned.json`:

```json
{
  "updated": "",
  "rules": [
    {"text": "...", "evidence": 4, "first": "", "last": "", "status": "in_force"}
  ]
}
```

5. Archive processed events — rotate FIRST to avoid racing concurrent appends: rename `events.jsonl` to `events-archive-.jsonl`, and only then read the renamed file for the distillation. New events land in a fresh `events.jsonl` untouched. (If you already read before rotating, rotate anyway and accept the tiny overlap.)
6. Report to the user in their language: what was learned (each rule + its evidence), what was demoted or deleted, and one line on what will change. If nothing met the bar, say so plainly — no fabricated learnings.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [WinterDDo](https://github.com/WinterDDo)
- **Source:** [WinterDDo/claude-code-skill-autopilot](https://github.com/WinterDDo/claude-code-skill-autopilot)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-winterddo-claude-code-skill-autopilot-evolve
- Seller: https://agentstack.voostack.com/s/winterddo
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.