{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "YuyaoGe/doc2harness",
 "name": "doc2harness",
 "owner": "YuyaoGe",
 "slug": "yuyaoge-doc2harness",
 "github": "https://github.com/YuyaoGe/doc2harness",
 "what": "Doc2Harness is a Python benchmark that measures how well a model builds a working coding agent harness, then tests that harness against a scripted mock model using 94 released scenarios.",
 "why": "",
 "language": "Python",
 "requirements": [
  "Python 3.11 or newer",
  "Docker installed and running",
  "The repo cloned locally",
  "For building a new harness only: the builder image, a local LiteLLM gateway, and your own API key"
 ],
 "audience_note": "Coding agent developers and AI researchers who need to score a harness they built or a harness a model generated.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "yuyaoge-doc2harness--score-existing-agent-harness",
   "title": "Score an existing coding agent harness",
   "best": true,
   "url": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/score-existing-agent-harness/",
   "json": "https://dedupedai.com/use-cases/u/yuyaoge-doc2harness/score-existing-agent-harness.json"
  },
  {
   "id": "yuyaoge-doc2harness--debug-one-scenario-family",
   "title": "Re-run one scenario family to debug a harness",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/debug-one-scenario-family/",
   "json": "https://dedupedai.com/use-cases/u/yuyaoge-doc2harness/debug-one-scenario-family.json"
  },
  {
   "id": "yuyaoge-doc2harness--check-catalog-integrity-before-scoring",
   "title": "Confirm the scenario catalog is intact before scoring",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/check-catalog-integrity-before-scoring/",
   "json": "https://dedupedai.com/use-cases/u/yuyaoge-doc2harness/check-catalog-integrity-before-scoring.json"
  },
  {
   "id": "yuyaoge-doc2harness--build-and-score-new-harness",
   "title": "Build a new agent harness and score it",
   "best": false,
   "url": "https://dedupedai.com/use-cases/yuyaoge-doc2harness/build-and-score-new-harness/",
   "json": "https://dedupedai.com/use-cases/u/yuyaoge-doc2harness/build-and-score-new-harness.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}