Search
OpenAI · By agentsope
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Lifecycle SOP for per-model prompt artifacts — the compiled prompts, instructions, few-shot demos, edit-format pins, and embedding-bound indices that change behavior when the underlying LM, dataset… | agentsope/ | 436 | — | ~8k | Automated safety check: Pass | MIT | 2 days ago |
| 2 | Tool skill — the first move in any LM-debugging session: dump the actual rendered prompt the framework sent to the model, before changing anything else. | agentsope/ | 436 | — | ~8.4k | Automated safety check: Pass | MIT | 2 days ago |
| 3 | Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load (e.g. | agentsope/ | 436 | — | ~7k | Automated safety check: Pass | MIT | 2 days ago |
| 4 | Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, framework resume, user re-run, model duplicate emit), the second call is a no-op… | agentsope/ | 436 | — | ~8.4k | Automated safety check: Pass | MIT | 2 days ago |
