Search
Agent Workflows · Python · By HKUDS
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution. | HKUDS/ | 16k | 1 repo | ~2.1k | Automated safety check: Notes | MIT | 4 mo ago |
| 2 | Lets Codex build, refine, test, validate and list CLI-Anything harnesses for GUI applications or source repositories, following the project's full methodology. | HKUDS/ | 52k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 19 days ago |
| 3 | Guides Hermes Agent through building, refining and testing a CLI-Anything harness that wraps a GUI application or source repository in a scriptable command line. | HKUDS/ | 52k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 19 days ago |
| 4 | Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead. | HKUDS/ | 7.8k | — | ~588 | Automated safety check: Pass | MIT | 2 mo ago |
| 5 | A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output. | HKUDS/ | 7.8k | — | ~652 | Automated safety check: Pass | MIT | 2 mo ago |
| 6 | Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place. | HKUDS/ | 7.8k | — | ~1.1k | Automated safety check: Pass | MIT | 2 mo ago |
