[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DDPZFWDCVAWNNA4RG0AP7N":3,"skill-same:01M6DDPZFWDCVAWNNA4RG0AP7N":83},{"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":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":61,"updatedAt":62,"install":63,"resources":76},"01M6DDPZFWDCVAWNNA4RG0AP7N","verification-gated-probes",null,"Build auditable capability probes with explicit gates.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F2d\u002F2df75b2ce742b9efbe2af6a033cea6ece8cbd759e1714444457fcfc2e839d80a\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"verification","gated","verification gated probes","testing","research","test","windows","development","code","integration","model","hermes","build","gates","software","driven","2026-11-10 10:12:30",false,"---\r\nname: verification-gated-probes\r\ndescription: Build auditable capability probes with explicit gates.\r\nversion: 1.0.0\r\nauthor: Nous Research\r\nlicense: MIT\r\nmetadata:\r\n  hermes:\r\n    tags: [verification, testing, probes, model-integration]\r\n    related_skills: [software-development\u002Ftest-driven-development, software-development\u002Fwindows-hermes-code-verification]\r\n---\r\n\r\n# Verification-Gated Capability Probes\r\n\r\n## When to Use\r\n\r\nUse for local model, embedding endpoint, or API compatibility work where a diagnostic probe must produce auditable evidence before production integration. This is a class-level workflow, not a provider-specific recipe.\r\n\r\n## Core contract\r\n\r\nSeparate three things:\r\n\r\n1. **Required base checks** — compatibility conditions that determine the base verdict: endpoint health, response shape\u002Fcount\u002Findex coverage, dimension, finite\u002Fnonzero vectors, normalization, repeatability, batch stability, and the primary semantic ordering check.\r\n2. **Observations** — informative measurements such as Japanese\u002Fcross-lingual retrieval, profile comparisons, margins, and latency. Record them, but do not silently promote them to gates.\r\n3. **Optional required checks** — checks such as soak\u002Fstress that become required only when explicitly requested.\r\n\r\nNever use a blanket `all(checks.values())` when a check can be not-run. Use an explicit required-check list and identity comparison (`is True`) so `None` remains distinct from `False`.\r\n\r\n## Opt-in soak pattern\r\n\r\nRepresent an unrequested soak explicitly:\r\n\r\n```python\r\nBASE_REQUIRED_CHECKS = (...)\r\n\r\n\r\ndef required_check_names(*, soak_requests: int) -> tuple[str, ...]:\r\n    if soak_requests \u003C 0:\r\n        raise ValueError(\"soak_requests must be non-negative\")\r\n    return BASE_REQUIRED_CHECKS + ((\"soak\",) if soak_requests > 0 else ())\r\n\r\n\r\ndef determine_verdict(checks, *, soak_requests: int) -> str:\r\n    required = required_check_names(soak_requests=soak_requests)\r\n    return \"pass_text_only\" if all(checks.get(name) is True for name in required) else \"fail_model_compatibility\"\r\n```\r\n\r\nOutput should distinguish `not_run`, `passed`, and `failed`; JSON `null` is acceptable when the schema also records `requested: false`. Requested soak should report requested count, completed count, failures, and pass\u002Ffail.\r\n\r\n## TDD and evidence sequence\r\n\r\n1. Inspect current code and commit boundary; do not rewrite the previous commit when a follow-up fix is appropriate.\r\n2. Add regression tests for zero-request non-failure, not-run serialization, successful requested soak, failed requested soak, and negative input rejection. Confirm RED, including collection failure for missing helpers, before implementation.\r\n3. Implement the smallest change while retaining production boundaries.\r\n4. Run focused tests, then the canonical project runner and adjacent existing retrieval\u002Fembedding tests.\r\n5. Run lint, compile, and `git diff --check`.\r\n6. Update the implementation log with observed results and missing evidence.\r\n7. Commit independently with a descriptive fix message; verify HEAD, commit subject, clean status, and post-commit tests.\r\n\r\n## Safety and readiness boundaries\r\n\r\n- A passing text-only probe is not a multimodal or VL compatibility claim.\r\n- Do not call a model live result observed unless a real pinned model\u002Fserver run occurred.\r\n- Keep raw vectors, raw responses, credentials, and absolute local paths out of summary JSON\u002Flogs.\r\n- Keep Semantic Graph data canonical; vector indexes remain reproducible derived data.\r\n- Do not start an associative adapter or production embedding backend until control\u002Fcandidate live evidence and a fixed serializer\u002Fdimension profile exist.\r\n\r\n## Common pitfalls\r\n\r\n- `all(checks.values())` treats `None` as failure even when a check was intentionally not requested.\r\n- Adding observational checks to `checks` makes future consumers accidentally treat them as gates.\r\n- A test summary that reports only exit code hides pass\u002Fskip counts; prefer runner output with counts.\r\n- A requested test path may be absent; report that fact rather than claiming it ran.\r\n- “Pending live validation” is the correct status when no pinned real model was run; it is not a failure and not a pass.\r\n\r\n## Support files\r\n\r\n- See `references\u002Fllama-embedding-probe-follow-up.md` for the reusable regression matrix and evidence checklist.\r\n","# Verification-Gated Capability Probes\r\n\r\n## When to Use\r\n\r\nUse for local model, embedding endpoint, or API compatibility work where a diagnostic probe must produce auditable evidence before production integration. This is a class-level workflow, not a provider-specific recipe.\r\n\r\n## Core contract\r\n\r\nSeparate three things:\r\n\r\n1. **Required base checks** — compatibility conditions that determine the base verdict: endpoint health, response shape\u002Fcount\u002Findex coverage, dimension, finite\u002Fnonzero vectors, normalization, repeatability, batch stability, and the primary semantic ordering check.\r\n2. **Observations** — informative measurements such as Japanese\u002Fcross-lingual retrieval, profile comparisons, margins, and latency. Record them, but do not silently promote them to gates.\r\n3. **Optional required checks** — checks such as soak\u002Fstress that become required only when explicitly requested.\r\n\r\nNever use a blanket `all(checks.values())` when a check can be not-run. Use an explicit required-check list and identity comparison (`is True`) so `None` remains distinct from `False`.\r\n\r\n## Opt-in soak pattern\r\n\r\nRepresent an unrequested soak explicitly:\r\n\r\n```python\r\nBASE_REQUIRED_CHECKS = (...)\r\n\r\n\r\ndef required_check_names(*, soak_requests: int) -> tuple[str, ...]:\r\n    if soak_requests \u003C 0:\r\n        raise ValueError(\"soak_requests must be non-negative\")\r\n    return BASE_REQUIRED_CHECKS + ((\"soak\",) if soak_requests > 0 else ())\r\n\r\n\r\ndef determine_verdict(checks, *, soak_requests: int) -> str:\r\n    required = required_check_names(soak_requests=soak_requests)\r\n    return \"pass_text_only\" if all(checks.get(name) is True for name in required) else \"fail_model_compatibility\"\r\n```\r\n\r\nOutput should distinguish `not_run`, `passed`, and `failed`; JSON `null` is acceptable when the schema also records `requested: false`. Requested soak should report requested count, completed count, failures, and pass\u002Ffail.\r\n\r\n## TDD and evidence sequence\r\n\r\n1. Inspect current code and commit boundary; do not rewrite the previous commit when a follow-up fix is appropriate.\r\n2. Add regression tests for zero-request non-failure, not-run serialization, successful requested soak, failed requested soak, and negative input rejection. Confirm RED, including collection failure for missing helpers, before implementation.\r\n3. Implement the smallest change while retaining production boundaries.\r\n4. Run focused tests, then the canonical project runner and adjacent existing retrieval\u002Fembedding tests.\r\n5. Run lint, compile, and `git diff --check`.\r\n6. Update the implementation log with observed results and missing evidence.\r\n7. Commit independently with a descriptive fix message; verify HEAD, commit subject, clean status, and post-commit tests.\r\n\r\n## Safety and readiness boundaries\r\n\r\n- A passing text-only probe is not a multimodal or VL compatibility claim.\r\n- Do not call a model live result observed unless a real pinned model\u002Fserver run occurred.\r\n- Keep raw vectors, raw responses, credentials, and absolute local paths out of summary JSON\u002Flogs.\r\n- Keep Semantic Graph data canonical; vector indexes remain reproducible derived data.\r\n- Do not start an associative adapter or production embedding backend until control\u002Fcandidate live evidence and a fixed serializer\u002Fdimension profile exist.\r\n\r\n## Common pitfalls\r\n\r\n- `all(checks.values())` treats `None` as failure even when a check was intentionally not requested.\r\n- Adding observational checks to `checks` makes future consumers accidentally treat them as gates.\r\n- A test summary that reports only exit code hides pass\u002Fskip counts; prefer runner output with counts.\r\n- A requested test path may be absent; report that fact rather than claiming it ran.\r\n- “Pending live validation” is the correct status when no pinned real model was run; it is not a failure and not a pass.\r\n\r\n## Support files\r\n\r\n- See `references\u002Fllama-embedding-probe-follow-up.md` for the reusable regression matrix and evidence checklist.\r\n",{"name":5,"author":45,"license":15,"version":46,"metadata":47,"description":7},"Nous Research","1.0.0",{"hermes":48},{"tags":49,"related_skills":52},[24,27,50,51],"probes","model-integration",[53,54],"software-development\u002Ftest-driven-development","software-development\u002Fwindows-hermes-code-verification","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002F2d\u002F2df75b2ce742b9efbe2af6a033cea6ece8cbd759e1714444457fcfc2e839d80a",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add zapabob\u002FSkills --skill verification-gated-probes",{"tool":69,"command":70},"bunx","bunx skills add zapabob\u002FSkills --skill verification-gated-probes",{"tool":72,"command":73},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill verification-gated-probes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002F2d\u002F2df75b2ce742b9efbe2af6a033cea6ece8cbd759e1714444457fcfc2e839d80a\u002FSKILL.md",true,[77],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"REFERENCE.md","REFERENCE","参考文档",14005,"https:\u002F\u002Fgithub.com\u002Ferwin-flores-ucb\u002Fproyecto-hoteles\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkiss-dry-yagni\u002FREFERENCE.md",[84,118,151,177,204,221],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":101,"publishedAt":40},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[90,93,96],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[86,102,103,104,105,106,30,107,108,109,110,111,112,35,113,114,55,115,116,117],"openclaw","macos","cli","github","linux","official","search","https","social-media","api","Media","hermes agent","twitter","social","via","post",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":135,"publishedAt":40},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[124,127,130,131,132],{"categoryNo":125,"categoryName":126,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":128,"categoryName":129,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},{"categoryNo":133,"categoryName":134,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000036","内容创作者",[136,137,138,139,103,140,106,141,30,142,143,31,32,144,145,146,147,148,149,150],"writing","writing plans","plans","design","review","workflow","documentation","tasks","planning","code-review","subagent","write","superpowers","paths","test-driven-development",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":160,"publishedAt":40},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[157],{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[153,103,106,161,162,163,164,165,166,167,34,168,169,170,171,172,173,174,175,176],"openai","speech","multimodal","Transformers","ASR","Audio","text","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":40},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[183],{"categoryNo":184,"categoryName":185,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[187,103,188,189,30,190,191,192,193,194,195,34,196,197,198,199,200,201,202,203],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":205,"name":206,"nameZh":6,"description":207,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":208,"categories":209,"keywords":211,"publishedAt":40},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[210],{"categoryNo":94,"categoryName":95,"taxonomyType":21,"taxonomyTypeDesc":22},[206,103,212,105,106,213,214,215,216,217,218,35,113,219,220],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":229,"publishedAt":40},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[227,228],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},[230,231,232,106,28,161,233,234,235,164,236,111,237,238,239,240,241,242,243,244],"llms","vLLM","serving llms vllm","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]