[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Z2YYMRJ1FS42JRC4268NT":3,"skill-same:01M78Z2YYMRJ1FS42JRC4268NT":67},{"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},"01M78Z2YYMRJ1FS42JRC4268NT","writer-review",null,"Guides LazyLLM writer artifact models, writer tools, revision\u002Fstream workflows, Feishu adapter boundaries, and review CLI planning.","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\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: writer-review\ndescription: \"Guides LazyLLM writer artifact models, writer tools,\n  revision\u002Fstream workflows, Feishu adapter boundaries, and review CLI\n  planning.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# LazyLLM Writer and Review\n\nUse this sub-skill for LazyLLM writer workflows, writer intermediate representation (IR), artifact JSON envelopes, writer tools, revision\u002Fstream utilities, Feishu adapter boundaries, `lazyllm review`, `review-local`, and git review examples.\n\n## Start here when\n\n- The task mentions writer data models such as `WriterDocument`, `WriterBlock`, `WriterSpan`, `WritingContext`, or `ResourceProfile`.\n- The user wants to run or adapt writer tools, revision tools, stream tools, or a writer pipeline.\n- The task involves Feishu document bindings, provider payloads, or local artifact stores.\n- The user wants to plan LazyLLM PR review commands or local code-review output without posting remotely.\n\n## Files to read\n\n- [writer-review-workflows.md](references\u002Fwriter-review-workflows.md) for local writer artifact, tool, and review command workflows.\n- [artifact-formats.md](references\u002Fartifact-formats.md) for writer IR fields and artifact envelope expectations.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for artifact, provider adapter, review CLI, and posting failures.\n- [scripts\u002Fwriter_artifact_smoke.py](scripts\u002Fwriter_artifact_smoke.py) for a no-network artifact round-trip check.\n\n## Safe workflow\n\n1. **Start with local artifacts.** Build a tiny `WriterDocument` and `WritingContext`; round-trip them through JSON before using provider adapters.\n2. **Keep provider bindings as metadata.** `provider_binding` and `provider_payload` should be preserved but not dereferenced unless the user supplies provider access.\n3. **Validate tool outputs.** Writer tools should return artifact paths, context paths, schema names, counts, and summaries that downstream steps can inspect.\n4. **Treat review commands as side-effecting.** `lazyllm review` may post or call providers; `review-local` can inspect git state and write reports. Ask before posting remote comments.\n5. **Route LLM\u002Fprovider configuration** to [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md) when a writer pipeline calls an online model.\n\n## Key local facts\n\nLazyLLM writer tests verify:\n\n- nested `WriterDocument`\u002F`WriterBlock`\u002F`WriterSpan` fields survive JSON round trips,\n- `iter_blocks()` traverses depth-first and `block_by_id()` finds nested blocks,\n- artifact envelopes contain `schema`, `schema_version`, `data`, and `meta`,\n- `save_artifact_json` \u002F `load_artifact_json` support models and lists,\n- `WriterToolBase._save_artifacts` records primary artifact path, context path, schema names, counts, and metadata,\n- writer adapter, revision, stream, and tool tests are mostly local; provider-backed writer pipeline is optional.\n\n## Review CLI boundaries\n\nUse review workflows for planning and local output unless the user explicitly asks to post:\n\n```text\nlazyllm review --pr \u003Cnumber> [--repo owner\u002Fname] [--model ...] [--post] ...\nlazyllm review-local [--repo-path .] [--base main] [--output review.json] ...\n```\n\nDo not post comments, call a provider, or inspect private repositories without user approval and credentials.\n\n## Handoff checklist\n\nWhen you finish a writer\u002Freview task, include:\n\n- artifact schema and file paths created or expected,\n- whether provider bindings are preserved or used,\n- local round-trip\u002Ftool smoke result,\n- review command plan and side-effect status,\n- model\u002Fprovider\u002Fbackend status if a writer pipeline uses an LLM.\n","# LazyLLM Writer and Review\n\nUse this sub-skill for LazyLLM writer workflows, writer intermediate representation (IR), artifact JSON envelopes, writer tools, revision\u002Fstream utilities, Feishu adapter boundaries, `lazyllm review`, `review-local`, and git review examples.\n\n## Start here when\n\n- The task mentions writer data models such as `WriterDocument`, `WriterBlock`, `WriterSpan`, `WritingContext`, or `ResourceProfile`.\n- The user wants to run or adapt writer tools, revision tools, stream tools, or a writer pipeline.\n- The task involves Feishu document bindings, provider payloads, or local artifact stores.\n- The user wants to plan LazyLLM PR review commands or local code-review output without posting remotely.\n\n## Files to read\n\n- [writer-review-workflows.md](references\u002Fwriter-review-workflows.md) for local writer artifact, tool, and review command workflows.\n- [artifact-formats.md](references\u002Fartifact-formats.md) for writer IR fields and artifact envelope expectations.\n- [troubleshooting.md](references\u002Ftroubleshooting.md) for artifact, provider adapter, review CLI, and posting failures.\n- [scripts\u002Fwriter_artifact_smoke.py](scripts\u002Fwriter_artifact_smoke.py) for a no-network artifact round-trip check.\n\n## Safe workflow\n\n1. **Start with local artifacts.** Build a tiny `WriterDocument` and `WritingContext`; round-trip them through JSON before using provider adapters.\n2. **Keep provider bindings as metadata.** `provider_binding` and `provider_payload` should be preserved but not dereferenced unless the user supplies provider access.\n3. **Validate tool outputs.** Writer tools should return artifact paths, context paths, schema names, counts, and summaries that downstream steps can inspect.\n4. **Treat review commands as side-effecting.** `lazyllm review` may post or call providers; `review-local` can inspect git state and write reports. Ask before posting remote comments.\n5. **Route LLM\u002Fprovider configuration** to [model-deployment](..\u002Fmodel-deployment\u002FSKILL.md) when a writer pipeline calls an online model.\n\n## Key local facts\n\nLazyLLM writer tests verify:\n\n- nested `WriterDocument`\u002F`WriterBlock`\u002F`WriterSpan` fields survive JSON round trips,\n- `iter_blocks()` traverses depth-first and `block_by_id()` finds nested blocks,\n- artifact envelopes contain `schema`, `schema_version`, `data`, and `meta`,\n- `save_artifact_json` \u002F `load_artifact_json` support models and lists,\n- `WriterToolBase._save_artifacts` records primary artifact path, context path, schema names, counts, and metadata,\n- writer adapter, revision, stream, and tool tests are mostly local; provider-backed writer pipeline is optional.\n\n## Review CLI boundaries\n\nUse review workflows for planning and local output unless the user explicitly asks to post:\n\n```text\nlazyllm review --pr \u003Cnumber> [--repo owner\u002Fname] [--model ...] [--post] ...\nlazyllm review-local [--repo-path .] [--base main] [--output review.json] ...\n```\n\nDo not post comments, call a provider, or inspect private repositories without user approval and credentials.\n\n## Handoff checklist\n\nWhen you finish a writer\u002Freview task, include:\n\n- artifact schema and file paths created or expected,\n- whether provider bindings are preserved or used,\n- local round-trip\u002Ftool smoke result,\n- review command plan and side-effect status,\n- model\u002Fprovider\u002Fbackend status if a writer pipeline uses an LLM.\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\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review",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 writer-review",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill writer-review",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill writer-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fartifact-formats.md","REFERENCE","参考文档",2000,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review\u002Freferences\u002Fartifact-formats.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",1789,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fwriter-review-workflows.md",2541,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review\u002Freferences\u002Fwriter-review-workflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fwriter_artifact_smoke.py","SCRIPT","脚本",3196,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flazy-llm\u002Fsub-skills\u002Fwriter-review\u002Fscripts\u002Fwriter_artifact_smoke.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]