Search
AI & LLM Engineering · By undefined-ui
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Audit an agent's context layout against the four places: system prompt, tools, history, tail. | undefined-ui/ | 1k | — | ~802 | Automated safety check: Pass | MIT | yesterday |
| 2 | Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner. | undefined-ui/ | 1k | — | ~786 | Automated safety check: Pass | MIT | yesterday |
| 3 | Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing. | undefined-ui/ | 1k | — | ~854 | Automated safety check: Pass | MIT | yesterday |
| 4 | Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent. | undefined-ui/ | 1k | — | ~754 | Automated safety check: Pass | MIT | yesterday |
| 5 | Audit an agent's harness against the four rings: containment, guides, sensors, permissions. | undefined-ui/ | 1k | — | ~855 | Automated safety check: Pass | MIT | yesterday |
