发现优质的 AI Agent 技能

> What I know, how well I know it, and where the gaps are. > Confidence: 🟢 High (0.8+) | 🟡 Medium (0.5-0.8) | 🔴 Low (<0.5) > Updated by nightly consolidation. Reviewed weekly.

> Commitments, scheduled actions, and deferred intentions. > Scanned every session start + every heartbeat. Execute when triggered. Archive when done. > > Format: > ```

Schedule: `0 4 * * 0` (Sunday 4 AM) Recommended model: Any model with reliable tool use Timeout: 600 seconds

Copy-paste these into your AGENTS.md.

Add these settings to your `openclaw.json` under `agents.defaults`.

Give your agent a mind, not just memory.

> Insights, corrections, and best practices. Promote recurring patterns to SOUL.md or AGENTS.md.

> Capability gaps noticed during work. Review weekly — build or find a skill.

> Track failures and their fixes. Patterns here become prevention rules in SOUL.md.

> Every deliverable passes through a gate before reaching the human or going external.

> Merge these into your existing AGENTS.md. Don't replace — add.

> Format: `[YYYY-MM-DD] CAPABILITY | what was wanted | workaround if any | requested:N` > Dedup: grep before adding. Increment count if exists.