# Profile

> Show the Skill Autopilot dashboard — what it did for you, before/after comparison, learned rules with evidence, mastered commands. Also drafts a feedback issue. Use when the user asks "what has the autopilot done", "show my profile", "驾驶舱", "autopilot 报告", "学到了什么", or wants to give feedback about suggestions.

- **Type:** Skill
- **Install:** `agentstack add skill-winterddo-claude-code-skill-autopilot-profile`
- **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/profile

## Install

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

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

## About

# Autopilot dashboard

Every number MUST be traceable to a real entry in the data files. Never fabricate or extrapolate a value claim. If a number is zero, show zero.

## Data sources
Read from `~/.claude/command-autopilot/`: `state.json` (counters, milestones, config), `events.jsonl` + `events-archive.jsonl` (the ledger), `learned.json` (rules), `skills-index.json`.

## Report (user's language, compact)

1. **Value ledger** — counts from events: auto plan-mode entries, skills auto-invoked (top 3 by count, with names), suggestions accepted vs made. One line each, with the period covered.
2. **Before/after** — compare the oldest 7 days of events against the newest 7 (only if ≥14 days of data; otherwise say "still collecting"): self-used commands per week then vs now. This is the user's own growth, shown from their own data.
3. **Learned rules** — each in_force rule with its evidence count and last-confirmed date. If none: "still observing, first rules typically appear after ~10 sessions."
4. **Mastered** — habits with self-use evidence; note that teaching for them has naturally stopped.
5. **Controls** — one line: config skill to quiet/mute, evolve skill to re-distill, "delete rule N" works right here.

## Feedback draft
If the user is dissatisfied with any suggestion behavior, offer to draft a GitHub issue for `WinterDDo/claude-code-skill-autopilot`: title, what happened, expected behavior, and (only with explicit consent) the relevant anonymized evidence lines. Show the draft; the user files it themselves.

## Rule deletion
"Delete rule N" → remove it from learned.json, confirm in one line.

## 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-profile
- 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%.