[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7955HTG7SAJC22D7EGDAWZD":3,"skill-same:01M7955HTG7SAJC22D7EGDAWZD":82},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M7955HTG7SAJC22D7EGDAWZD","r1v4-api-testing",null,"Draft, inspect, parse, and summarize Skywork R1V4 API batch tests without leaking API keys.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: r1v4-api-testing\ndescription: \"Draft, inspect, parse, and summarize Skywork R1V4 API batch tests\n  without leaking API keys.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# R1V4 API Testing\n\nUse this sub-skill when you need to prepare Skywork R1V4 API batch tests, dry-run request payloads, parse tagged tool-use responses, summarize result JSONL, or troubleshoot the batch viewer safely.\n\n## Start here\n\n1. Read `references\u002Fapi-batch-workflows.md` for the four batch modes and Chinese terminology.\n2. Check `references\u002Fdata-formats.md` for `test_cases.jsonl`, request payload, and result JSONL schemas.\n3. Validate input cases with `scripts\u002Fvalidate_cases.py` before any API run.\n4. Build a no-network payload preview with `scripts\u002Fbuild_api_payload.py`.\n5. Parse a tagged response or a result file with `scripts\u002Fparse_r1v4_response.py`.\n6. Summarize a result JSONL with `scripts\u002Fsummarize_results.py`.\n\n## Bundled files\n\n- `references\u002Fapi-batch-workflows.md` — workflow map for `batch_nonstream.py`, `batch_stream.py`, `batch_planner_nonstream.py`, and `batch_planner_stream.py`.\n- `references\u002Fdata-formats.md` — input\u002Foutput schemas and tagged response grammar.\n- `references\u002Fresult-analysis.md` — safe headless analysis path and visualizer guidance.\n- `references\u002Ftroubleshooting.md` — API, image, stream, parse, and viewer failure modes.\n- `scripts\u002Fvalidate_cases.py` — schema and optional image-path validation.\n- `scripts\u002Fbuild_api_payload.py` — OpenAI-compatible payload builder with data URL support.\n- `scripts\u002Fparse_r1v4_response.py` — tagged response parser and JSONL parser CLI.\n- `scripts\u002Fsummarize_results.py` — batch result counters and response-length summary.\n\n## Routing notes\n\n- Use `skywork\u002Fr1v4-lite` for the regular batch modes and `skywork\u002Fr1v4-vl-planner-lite` for planner batch modes.\n- Keep the message order as image first, then text.\n- Bundled helpers do not make live API calls by default.\n- Leave API keys to env or caller config; do not hard-code them in payloads or scripts.\n- Use the bundled summary helper instead of copying the full Flask viewer into a workflow.\n- Route local Transformers\u002FvLLM inference, CUDA setup, and model-weight issues to the sibling `local-inference` sub-skill.\n- Route VLMEvalKit, EMMA, MMK12, and benchmark reproduction tasks to the sibling `evaluation-reproduction` sub-skill.\n","# R1V4 API Testing\n\nUse this sub-skill when you need to prepare Skywork R1V4 API batch tests, dry-run request payloads, parse tagged tool-use responses, summarize result JSONL, or troubleshoot the batch viewer safely.\n\n## Start here\n\n1. Read `references\u002Fapi-batch-workflows.md` for the four batch modes and Chinese terminology.\n2. Check `references\u002Fdata-formats.md` for `test_cases.jsonl`, request payload, and result JSONL schemas.\n3. Validate input cases with `scripts\u002Fvalidate_cases.py` before any API run.\n4. Build a no-network payload preview with `scripts\u002Fbuild_api_payload.py`.\n5. Parse a tagged response or a result file with `scripts\u002Fparse_r1v4_response.py`.\n6. Summarize a result JSONL with `scripts\u002Fsummarize_results.py`.\n\n## Bundled files\n\n- `references\u002Fapi-batch-workflows.md` — workflow map for `batch_nonstream.py`, `batch_stream.py`, `batch_planner_nonstream.py`, and `batch_planner_stream.py`.\n- `references\u002Fdata-formats.md` — input\u002Foutput schemas and tagged response grammar.\n- `references\u002Fresult-analysis.md` — safe headless analysis path and visualizer guidance.\n- `references\u002Ftroubleshooting.md` — API, image, stream, parse, and viewer failure modes.\n- `scripts\u002Fvalidate_cases.py` — schema and optional image-path validation.\n- `scripts\u002Fbuild_api_payload.py` — OpenAI-compatible payload builder with data URL support.\n- `scripts\u002Fparse_r1v4_response.py` — tagged response parser and JSONL parser CLI.\n- `scripts\u002Fsummarize_results.py` — batch result counters and response-length summary.\n\n## Routing notes\n\n- Use `skywork\u002Fr1v4-lite` for the regular batch modes and `skywork\u002Fr1v4-vl-planner-lite` for planner batch modes.\n- Keep the message order as image first, then text.\n- Bundled helpers do not make live API calls by default.\n- Leave API keys to env or caller config; do not hard-code them in payloads or scripts.\n- Use the bundled summary helper instead of copying the full Flask viewer into a workflow.\n- Route local Transformers\u002FvLLM inference, CUDA setup, and model-weight issues to the sibling `local-inference` sub-skill.\n- Route VLMEvalKit, EMMA, MMK12, and benchmark reproduction tasks to the sibling `evaluation-reproduction` sub-skill.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill r1v4-api-testing",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill r1v4-api-testing",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill r1v4-api-testing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002FSKILL.md",[46,52,56,60,64,70,74,78],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fapi-batch-workflows.md","REFERENCE","参考文档",3216,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Freferences\u002Fapi-batch-workflows.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fdata-formats.md",3244,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Freferences\u002Fdata-formats.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fresult-analysis.md",3044,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Freferences\u002Fresult-analysis.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Ftroubleshooting.md",3992,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Freferences\u002Ftroubleshooting.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fbuild_api_payload.py","SCRIPT","脚本",5719,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Fscripts\u002Fbuild_api_payload.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fparse_r1v4_response.py",12314,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Fscripts\u002Fparse_r1v4_response.py",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fsummarize_results.py",5094,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Fscripts\u002Fsummarize_results.py",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fvalidate_cases.py",5994,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fskywork-r1v\u002Fsub-skills\u002Fr1v4-api-testing\u002Fscripts\u002Fvalidate_cases.py",[83,91,98,105,112,119],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"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.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"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":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":87,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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",[],[]]