Search
AI & LLM Engineering · LearnPrompt/cc-harness-skills
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use. | LearnPrompt/ | 237 | — | ~477 | Automated safety check: Pass | MIT | 3 mo ago |
| 2 | Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon. | LearnPrompt/ | 237 | — | ~334 | Automated safety check: Pass | MIT | 3 mo ago |
| 3 | Extract durable memories from recent conversation turns into user, feedback, project, and reference categories while avoiding stale code-state facts. | LearnPrompt/ | 237 | — | ~347 | Automated safety check: Pass | MIT | 3 mo ago |
| 4 | Compress a long agent conversation into a nine-part continuation summary that preserves request, files, errors, user messages, current work, and the next aligned step. | LearnPrompt/ | 237 | — | ~327 | Automated safety check: Pass | MIT | 3 mo ago |
| 5 | Coordinate multiple agents by splitting work into research, synthesis, implementation, and verification, assigning ownership, and keeping the coordinator focused on integration rather than raw… | LearnPrompt/ | 237 | — | ~346 | Automated safety check: Pass | MIT | 3 mo ago |
| 6 | Run a read-only verification pass after implementation to check whether completion claims are real, validation actually ran, and obvious edge cases or regressions were missed. | LearnPrompt/ | 237 | — | ~302 | Automated safety check: Pass | MIT | 3 mo ago |
