发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
Feature Requests
> Capability gaps noticed during work. Review weekly — build or find a skill.
Errors
> Track failures and their fixes. Patterns here become prevention rules in SOUL.md.
QA Gates
> Every deliverable passes through a gate before reaching the human or going external.
Battle-Tested Agent — AGENTS.md Additions
> Merge these into your existing AGENTS.md. Don't replace — add.
⚔️ Battle-Tested Agent
**16 patterns that keep OpenClaw agents alive in production. Every one earned from failure.**
Wishes
> Format: `[YYYY-MM-DD] CAPABILITY | what was wanted | workaround if any | requested:N` > Dedup: grep before adding. Increment count if exists.
Learnings
> Format: `[YYYY-MM-DD] CATEGORY | what was learned | action to take | count:N` > Categories: correction, knowledge, pattern, gotcha, optimization > Dedup: grep before adding. Increment count if exists. Promote at count:3+.
Errors
> Format: `[YYYY-MM-DD] COMMAND_OR_TOOL | what failed | fix or workaround | count:N` > Dedup: grep before adding. Increment count if exists. Promote at count:3+.
🧠 Agent Memory Loop
**Your agent forgets everything between sessions. This skill gives it a learning system that actually works.**