[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TWSQRSMW2BJTS571JDMAG":3,"skill-same:01M78TWSQRSMW2BJTS571JDMAG":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78TWSQRSMW2BJTS571JDMAG","speechscore-metrics",null,"Choose, validate, and run SpeechScore objective metrics for intrusive and non-intrusive speech quality assessment.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speechscore-metrics\ndescription: \"Choose, validate, and run SpeechScore objective metrics for\n  intrusive and non-intrusive speech quality assessment.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# SpeechScore Metrics\n\nUse this sub-skill when a task asks for objective speech quality assessment with SpeechScore: selecting metrics, scoring one enhanced\u002Fdegraded file against a clean reference, scoring matched test\u002Freference directories, scoring reference-free MOS-style metrics, tuning `window`\u002F`score_rate`\u002F`return_mean`, or interpreting nested result dictionaries.\n\nStart here:\n\n- Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for the `SpeechScore` factory, import-layout rules, call parameters, result shapes, and important `window`\u002F`score_rate` caveats.\n- Read [references\u002Fmetric-catalog.md](references\u002Fmetric-catalog.md) before choosing metrics or deciding whether `reference_path` is required.\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for copyable dry-run, single-file, matched-directory, reference-free, and nested-result interpretation recipes.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when imports, metric dependencies, model-backed metrics, references, directory basenames, or windowed scoring fail.\n- Use [scripts\u002Fspeechscore_metric_recipe.py](scripts\u002Fspeechscore_metric_recipe.py) to validate requested metric names\u002Freference behavior or to run scoring without assuming bundled sample paths.\n\nOperating rules:\n\n1. Use this sub-skill only for SpeechScore objective metric selection and scoring.\n2. Route audio enhancement, separation, super-resolution, or target-speaker extraction generation to `..\u002Fclearvoice-inference\u002F` before scoring.\n3. Route benchmark list creation, dataset manifests, training launchers, or training\u002Fevaluation data preparation to `..\u002Ftraining-and-data-prep\u002F`.\n4. Decide `reference_path` from the metric catalog, not from each source class's `intrusive` attribute; that attribute is inconsistent in this snapshot.\n5. For dry runs, validate metric names, whether any selected metric requires a reference, and matching directory basenames before reading audio.\n6. For real source-layout runs from outside the SpeechScore component directory, pass `--speechscore-dir \u003Cspeechscore_component_dir>` so the helper can import `speechscore.py` and resolve metric assets.\n7. Prefer `window=None` for direct source API calls. Use the bundled helper when windowed scoring or explicit non-fixed metric resampling is required, because the inspected source window branch has a `maxlen` bug and the direct `score_rate` argument is not reliably honored for non-fixed metrics.\n","# SpeechScore Metrics\n\nUse this sub-skill when a task asks for objective speech quality assessment with SpeechScore: selecting metrics, scoring one enhanced\u002Fdegraded file against a clean reference, scoring matched test\u002Freference directories, scoring reference-free MOS-style metrics, tuning `window`\u002F`score_rate`\u002F`return_mean`, or interpreting nested result dictionaries.\n\nStart here:\n\n- Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for the `SpeechScore` factory, import-layout rules, call parameters, result shapes, and important `window`\u002F`score_rate` caveats.\n- Read [references\u002Fmetric-catalog.md](references\u002Fmetric-catalog.md) before choosing metrics or deciding whether `reference_path` is required.\n- Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for copyable dry-run, single-file, matched-directory, reference-free, and nested-result interpretation recipes.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when imports, metric dependencies, model-backed metrics, references, directory basenames, or windowed scoring fail.\n- Use [scripts\u002Fspeechscore_metric_recipe.py](scripts\u002Fspeechscore_metric_recipe.py) to validate requested metric names\u002Freference behavior or to run scoring without assuming bundled sample paths.\n\nOperating rules:\n\n1. Use this sub-skill only for SpeechScore objective metric selection and scoring.\n2. Route audio enhancement, separation, super-resolution, or target-speaker extraction generation to `..\u002Fclearvoice-inference\u002F` before scoring.\n3. Route benchmark list creation, dataset manifests, training launchers, or training\u002Fevaluation data preparation to `..\u002Ftraining-and-data-prep\u002F`.\n4. Decide `reference_path` from the metric catalog, not from each source class's `intrusive` attribute; that attribute is inconsistent in this snapshot.\n5. For dry runs, validate metric names, whether any selected metric requires a reference, and matching directory basenames before reading audio.\n6. For real source-layout runs from outside the SpeechScore component directory, pass `--speechscore-dir \u003Cspeechscore_component_dir>` so the helper can import `speechscore.py` and resolve metric assets.\n7. Prefer `window=None` for direct source API calls. Use the bundled helper when windowed scoring or explicit non-fixed metric resampling is required, because the inspected source window branch has a `maxlen` bug and the direct `score_rate` argument is not reliably honored for non-fixed metrics.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill speechscore-metrics",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill speechscore-metrics",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill speechscore-metrics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",5551,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fmetric-catalog.md",5134,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002Freferences\u002Fmetric-catalog.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5514,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fworkflows.md",5197,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002Freferences\u002Fworkflows.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fspeechscore_metric_recipe.py","SCRIPT","脚本",9038,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fclearer-voice-studio\u002Fsub-skills\u002Fspeechscore-metrics\u002Fscripts\u002Fspeechscore_metric_recipe.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]