{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "ant-research-antomnievo--evolve-agent-skill-directory",
 "repo": "ant-research/AntOmniEvo",
 "repo_url": "https://github.com/ant-research/AntOmniEvo",
 "repo_slug": "ant-research-antomnievo",
 "title": "Evolve an agent skill directory against your eval set",
 "page_title": "How to evolve an agent skill directory against your eval set with Ant Omni Evo",
 "summary": "Let agents rewrite SKILL.md, references and scripts until an evaluator scores the agent higher.",
 "who": "An engineer maintaining an AI agent whose skill files underperform on a known set of test tasks and who wants the files improved without hand-editing each failure.",
 "problem": "Skill files (SKILL.md, references, scripts) are tuned by hand, and each fix needs a person to read failures and guess which file to change.",
 "outcome": "A directory of optimized skill files with a change lineage that ties each edit to the failure evidence behind it.",
 "steps": [
  "Write a System that runs your agent on one eval instance and returns its output.",
  "Write an Evaluator that scores each output from 0 to 1; its scoring criteria become the optimization objective.",
  "Prepare train and validation instances that define what good means for your agent.",
  "Describe the skill directory as a TunableArtifactSchema: the file tree and what each file is for.",
  "Provide the starting skill files as initial tunable artifacts and start the evolution loop so the Proposer edits files from failure trajectories.",
  "Review the best candidate's directory and its change lineage before deploying the files."
 ],
 "agent_prompt": "Using the AntOmniEvo repo (ant-research/AntOmniEvo), set up an evolution run for the skill directory at <skill-dir> with an Evaluator that scores outputs from 0 to 1. Expected output: the best candidate's tunable artifacts as a directory plus its change lineage. Verify that the CandidateStore holds every candidate, run, analysis, and changelog.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 day",
 "basis": "readme",
 "caveat": "The README describes the framework and its docs but this excerpt shows no install commands, so check docs/quickstart.md for setup details before planning the run.",
 "category": "Software and DevOps",
 "tags": [
  "Software and DevOps"
 ],
 "lang": "python",
 "requirements": [
  "A Python environment (the repo language is Python)",
  "A system that can run on one eval instance and produce output",
  "An Evaluator that scores each output from 0 to 1",
  "Train and validation data that define what good looks like",
  "Starting tunable artifacts as a directory of files",
  "A coding-agent Proposer to make the edits (the README says the proposer must be agents)"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/ant-research-antomnievo/evolve-agent-skill-directory/",
 "md": "https://dedupedai.com/use-cases/ant-research-antomnievo/evolve-agent-skill-directory/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/ant-research-antomnievo--evolve-agent-skill-directory.json",
 "api_version": "v1"
}