[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6ESXJSJ409QN85M12Y3Q0T4":3,"skill-same:01M6ESXJSJ409QN85M12Y3Q0T4":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6ESXJSJ409QN85M12Y3Q0T4","aeon-skill-evals",null,"Validate the output of any installed skill against an assertion manifest — word counts, required\npatterns, forbidden phrases, required sections, source citation. Detects regressions by diffing\nvs prior runs (NEW_FAIL \u002F NEW_PASS \u002F CHRONIC \u002F STABLE_FAIL). Bootstrap mode generates a starter\nmanifest from a skill's recent successful runs so manifests aren't written speculatively.\nTriggers: \"evaluate this skill's output\", \"check skill X for regressions\", \"bootstrap evals\nfor Y\", \"did this skill output pass quality gates\".","Eskyee\u002Fagentbot-opensource","Eskyee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30862925?v=4","01M6ESSG1VB0FYP310V08SY08K","Esky33","01M6ESSG5ZR55BV28APEN3Y2P6",17,"MIT","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fskills\u002Faeon-skill-evals\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"aeon","evals","aeon skill evals","validate","bootstrap","quality gates","manifest","Word","quality","check","patterns","Citation","gates","triggers","starter","output","2026-11-10 10:12:30",false,"---\nname: aeon-skill-evals\ndescription: |\n  Validate the output of any installed skill against an assertion manifest — word counts, required\n  patterns, forbidden phrases, required sections, source citation. Detects regressions by diffing\n  vs prior runs (NEW_FAIL \u002F NEW_PASS \u002F CHRONIC \u002F STABLE_FAIL). Bootstrap mode generates a starter\n  manifest from a skill's recent successful runs so manifests aren't written speculatively.\n  Triggers: \"evaluate this skill's output\", \"check skill X for regressions\", \"bootstrap evals\n  for Y\", \"did this skill output pass quality gates\".\n---\n\n# aeon-skill-evals\n\nQuality net for installed skills. Each skill can declare an assertion manifest; outputs are checked against it; failing assertions surface regressions and route concrete fixes.\n\n## Manifest format\n\n```yaml\ntoken-movers:\n  min_words: 200\n  required_patterns: [\"Top movers\", \"24h\"]\n  forbidden_patterns: [\"I cannot\", \"as an AI\"]\n  must_cite_source: true\n  min_distinct_items: 5\n\nnarrative-tracker:\n  min_words: 400\n  required_sections: [\"TRANSITIONS\", \"POSITIONS\", \"MAP\"]\n  forbidden_patterns: [\"exciting\", \"consider\"]\n  must_have_position_call: true\n```\n\nSupported assertions: `min_words` \u002F `max_words`, `required_patterns` \u002F `forbidden_patterns`, `required_sections`, `must_cite_source`, `min_distinct_items`, `output_pattern` (regex), and per-skill-family custom binary checks.\n\n## Operations\n\n- `eval` — run every manifest-defined skill against its latest output.\n- `eval --skill=NAME` — one skill.\n- `bootstrap --skill=NAME` — generate a starter manifest from recent successful runs.\n\n## Regression states\n\n| State | Action |\n|---|---|\n| `NEW_FAIL` | Passing last run, failing now. Severity scales with pass streak. |\n| `NEW_PASS` | Failing last run, passing now. Log the win. |\n| `CHRONIC` | Failing > 3 consecutive runs. Recommend operator review. |\n| `STABLE_FAIL` | Always failing. Manifest assertion mismatch — flag for review. |\n\nState in local `evals-state.json`.\n\n## Bootstrap mode\n\nSamples last 5 successful runs of a skill. Computes:\n\n- `min_words` at p25 of historical runs.\n- Required patterns from common section headers.\n- Forbidden patterns from default list (refusals, hedging filler).\n\nEmits the proposed manifest for review. Never auto-commits — assertions need a human signoff.\n\n## Rules\n\n- Assertions are observations, not specifications. Bootstrap before writing speculatively.\n- Forbidden patterns catch hallucination markers and refusals. Keep the list tight; don't lint stylistic choices.\n- Chronic failures get a recommendation, not a re-file.\n- Manifest changes are reviewed; never auto-edited by this skill.\n","# aeon-skill-evals\n\nQuality net for installed skills. Each skill can declare an assertion manifest; outputs are checked against it; failing assertions surface regressions and route concrete fixes.\n\n## Manifest format\n\n```yaml\ntoken-movers:\n  min_words: 200\n  required_patterns: [\"Top movers\", \"24h\"]\n  forbidden_patterns: [\"I cannot\", \"as an AI\"]\n  must_cite_source: true\n  min_distinct_items: 5\n\nnarrative-tracker:\n  min_words: 400\n  required_sections: [\"TRANSITIONS\", \"POSITIONS\", \"MAP\"]\n  forbidden_patterns: [\"exciting\", \"consider\"]\n  must_have_position_call: true\n```\n\nSupported assertions: `min_words` \u002F `max_words`, `required_patterns` \u002F `forbidden_patterns`, `required_sections`, `must_cite_source`, `min_distinct_items`, `output_pattern` (regex), and per-skill-family custom binary checks.\n\n## Operations\n\n- `eval` — run every manifest-defined skill against its latest output.\n- `eval --skill=NAME` — one skill.\n- `bootstrap --skill=NAME` — generate a starter manifest from recent successful runs.\n\n## Regression states\n\n| State | Action |\n|---|---|\n| `NEW_FAIL` | Passing last run, failing now. Severity scales with pass streak. |\n| `NEW_PASS` | Failing last run, passing now. Log the win. |\n| `CHRONIC` | Failing > 3 consecutive runs. Recommend operator review. |\n| `STABLE_FAIL` | Always failing. Manifest assertion mismatch — flag for review. |\n\nState in local `evals-state.json`.\n\n## Bootstrap mode\n\nSamples last 5 successful runs of a skill. Computes:\n\n- `min_words` at p25 of historical runs.\n- Required patterns from common section headers.\n- Forbidden patterns from default list (refusals, hedging filler).\n\nEmits the proposed manifest for review. Never auto-commits — assertions need a human signoff.\n\n## Rules\n\n- Assertions are observations, not specifications. Bootstrap before writing speculatively.\n- Forbidden patterns catch hallucination markers and refusals. Keep the list tight; don't lint stylistic choices.\n- Chronic failures get a recommendation, not a re-file.\n- Manifest changes are reviewed; never auto-edited by this skill.\n",{"name":5,"description":7},"main","82fb6583c8457bf1cbf87293c95642f184e9dbaf","skills\u002Faeon-skill-evals",2,"https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource","https:\u002F\u002Fagentbot-studio.vercel.app","https:\u002F\u002Fgithub.com\u002FEskyee","https:\u002F\u002Fagentbot.sh","London-based indie founder. \r\nCreator of Agentbot.sh - BaseFM.space","2026-11-05 10:56:50",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Eskyee\u002Fagentbot-opensource --skill aeon-skill-evals",{"tool":61,"command":62},"bunx","bunx skills add Eskyee\u002Fagentbot-opensource --skill aeon-skill-evals",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Eskyee\u002Fagentbot-opensource --skill aeon-skill-evals","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fskills\u002Faeon-skill-evals\u002FSKILL.md",true,[],[70,79,114,136,161,169],{"skillNo":71,"name":72,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":76,"publishedAt":40},"01M6ET5WZACASAB0WXF3RWEA00","provisioning-v1","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fweb\u002Fskills\u002Fprovisioning-v1\u002FSKILL.md",[75],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[77,78],"provisioning v1","provisioning",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":93,"publishedAt":40},"01M6ET5R7WW7NHX7BBH6RR41SH","get-api-docs","Use this skill when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, \"use the OpenAI API\", \"call the Stripe API\", \"use the Anthropic SDK\", \"query Pinecone\", or any time the user asks you to write code against an external service and you need current API reference. Fetch the docs with chub before answering, rather than relying on training knowledge.","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fweb\u002Fskills\u002Fget-api-docs\u002FSKILL.md",[85,88],{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"docs","api","get api docs","get","writing","documentation","training","code","openai","openai api","library","knowledge","write","fetch","example","pinecone","stripe","query","time","anthropic sdk",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":40},"01M6ET5MHC01R668JHR5N0HGA1","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial deterministic subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fskills\u002Fzyfai\u002FSKILL.md",[],[116,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135],"passive","non-custodial","arbitrum","yield","withdraw","Optimization","deposit","defi","deterministic","base","Wallet","use","user","safe","ethereum",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":143,"publishedAt":40},"01M6ET5FA594JNMY39RN003ANW","zerion","Interpreted crypto wallet data for AI agents. Use when an agent needs portfolio values, token positions, DeFi positions, NFT holdings, transaction history, PnL data, token prices, charts, gas prices, swap quotes, or DApp information across 41+ chains. Zerion transforms raw blockchain data into agent-ready JSON with USD values, protocol labels, and enriched metadata. Supports x402 pay-per-request ($0.01 USDC on Base) and API key access. Triggers on mentions of portfolio, wallet analysis, positions, transactions, PnL, profit\u002Floss, DeFi, token balances, NFTs, swap quotes, gas prices, or Zerion.","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fskills\u002Fzerion\u002FSKILL.md",[142],{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},[138,144,145,146,147,148,149,150,151,152,153,154,131,155,156,157,158,159,160,95],"information","data","ai agents","analysis","x402","transforms","nfts","token","nft","across","usd","ready","portfolio","gas","access","transactions","Charts",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":40},"01M6ET5C758AY90H4E0AWAJ9JR","zapper","Placeholder for Zapper skill.","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fskills\u002Fzapper\u002FSKILL.md",[],[163,168],"placeholder",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":40},"01M6ET5965RAA4BZNSWEVK3MGW","yoink","Play Yoink, an onchain capture-the-flag game on Base. Yoink the flag from the current holder, check game stats and leaderboards, view player scores, and compete for the trophy. Uses Bankr for transaction execution.","https:\u002F\u002Fgithub.com\u002FEskyee\u002Fagentbot-opensource\u002Fblob\u002Fmain\u002Fskills\u002Fyoink\u002FSKILL.md",[],[171,176,177,178,179,180,130,181,33,182,183,184,185,186,187,188,189],"view","org","compete","transaction","bankr","onchain","capture","jq","curl","game","execution","stats","https","play"]