Auto-Improve Skill
Automatische Selbst-Verbesserung durch Fehler-Lernen und Pattern-Erkennung
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- Auto-Improve Skill
- description
- Automatische Selbst-Verbesserung durch Fehler-Lernen und Pattern-Erkennung
03 SKILL.md 正文
Auto-Improve Skill
Kernprinzip: Jede Aktion macht mich besser für die nächste.
Wann aktivieren
- Session-Start (automatisch)
- Nach jedem Task-Abschluss
- Bei Fehlern
Der Improvement Loop
┌─────────────────────────────────────────────────┐
│ AUTO-IMPROVE LOOP │
├─────────────────────────────────────────────────┤
│ │
│ SESSION START │
│ │ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ 1. Load Context │ │
│ │ .antigravity │ │
│ │ + MEMORY │ │
│ └────────┬────────┘ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ 2. Check │ │
│ │ Past Mistakes│ ← "Was hab ich falsch │
│ └────────┬────────┘ gemacht?" │
│ ▼ │
│ ┌─────────────────┐ │
│ │ 3. EXECUTE TASK │ │
│ └────────┬────────┘ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ 4. Verify │ ← Tests + Lint │
│ └────────┬────────┘ │
│ ▼ │
│ ┌─────────────┐ │
│ │ Erfolgreich?│ │
│ └──────┬──────┘ │
│ JA │ NEIN │
│ ↓ │ ↓ │
│ ┌───────┐ │ ┌──────────┐ │
│ │Pattern│ │ │ Learn │ │
│ │Save │ │ │ Mistake │ │
│ └───┬───┘ │ └────┬─────┘ │
│ └─────┼──────┘ │
│ ▼ │
│ ┌─────────────────┐ │
│ │ 5. Update │ │
│ │ .antigravity │ │
│ └─────────────────┘ │
│ │
│ → NÄCHSTER TASK IST BESSER │
│ │
└─────────────────────────────────────────────────┘
Phase 1: Session Start
# Automatisch bei Session-Start ausführen
# 1. Projekt-Kontext laden
project_root = detect_project_root()
antigravity_file = f"{project_root}/.antigravity.md"
if exists(antigravity_file):
load_context(antigravity_file)
# 2. Globales Memory laden
recall_memory(tags=["mistakes", project_name])
# 3. Warnung bei bekannten Fehlern
if relevant_mistakes:
warn(f"⚠️ Bekannte Fehler für {project}: {mistakes}")
Phase 2: Pre-Action Check
Vor JEDER Code-Änderung:
## Pre-Action Checklist
- [ ] Habe ich das schon mal falsch gemacht?
- [ ] Gibt es ein gespeichertes Pattern dafür?
- [ ] Verstehe ich das Projekt-Architektur?
- [ ] Kenne ich die Coding-Standards?
Phase 3: Post-Action Learn
Nach JEDER Aktion:
Bei Erfolg
save_pattern(
situation=task.context,
action=task.approach,
outcome="success",
pattern=extract_reusable_pattern(task)
)
Bei Fehler
learn_from_mistake(
mistake=error.description,
cause=error.root_cause,
lesson=error.how_to_avoid,
tags=["mistakes", project, domain]
)
# Auto-Update .antigravity.md
update_antigravity_mistakes(project, error)
Integration mit bestehenden Skills
| Skill | Integration |
|---|---|
mistake-tracker |
Liefert Fehler-Daten |
verification-loops |
Triggert Post-Action Learn |
context-management |
Session Context laden |
self-check |
Pre-Action Validation |
Triggers
Automatische Trigger
session_start:
- load_project_context
- recall_mistakes
- warn_known_issues
post_code_edit:
- run_verification_loop
- if_error: learn_from_mistake
- if_success: save_pattern
session_end:
- summarize_learnings
- update_antigravity
Manuelle Trigger
/improve- Force Learning aus letzter Aktion/mistakes- Zeige alle gelernten Fehler/patterns- Zeige erfolgreiche Patterns
Metriken
Track diese Werte über Zeit:
| Metrik | Beschreibung |
|---|---|
mistakes_repeated |
Sollte → 0 gehen |
first_time_right |
Sollte → 100% gehen |
patterns_reused |
Sollte steigen |
verification_failures |
Sollte sinken |
Anti-Patterns
| ❌ DON'T | ✅ DO |
|---|---|
| Fehler ignorieren | Jeden Fehler speichern |
| Nur aktuelle Session | Cross-Session lernen |
| Generische Lessons | Spezifische, actionable Lessons |
| Zu viel speichern | Nur Relevantes speichern |
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.