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.
Install
$ agentstack add skill-winterddo-claude-code-skill-autopilot-profile ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-winterddo-claude-code-skill-autopilot-profile) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →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)
- 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.
- 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.
- 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."
- Mastered — habits with self-use evidence; note that teaching for them has naturally stopped.
- 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
- Source: WinterDDo/claude-code-skill-autopilot
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.