[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78TYSAGPRQZD8V72HXP8AXA":3,"skill-same:01M78TYSAGPRQZD8V72HXP8AXA":110},{"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},"01M78TYSAGPRQZD8V72HXP8AXA","code-review-graph",null,"Use code-review-graph for local-first CLI\u002FMCP code knowledge graphs, graph-backed code review, structural search, and repository-analysis integrations.","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\u002Fcode-review-graph\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-review-graph\ndescription: \"Use code-review-graph for local-first CLI\u002FMCP code knowledge\n  graphs, graph-backed code review, structural search, and repository-analysis\n  integrations.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# code-review-graph\n\nUse this repo skill when a task names `code-review-graph`, CRG, graph-backed code review, local MCP graph tools, blast-radius analysis, structural code search, risk-scored PR review, custom language parsing, or multi-repo code graph operations.\n\n`code-review-graph` is a Python package and CLI\u002FMCP server that builds a local SQLite code knowledge graph from Tree-sitter parses, updates it incrementally, and exposes token-efficient review\u002Fsearch workflows to coding agents.\n\n## Fast route\n\n1. For first-time setup, read [references\u002Fstart-here.md](references\u002Fstart-here.md), then route to `install-and-setup`.\n2. For changed-code review or PR review, route to `review-changes`.\n3. For graph queries, architecture, flows, communities, or refactors, route to `graph-exploration`.\n4. For optional custom languages, embeddings, wiki, registry\u002Fdaemon, GitHub Action, or eval, route to `integrations-and-extensions`.\n\n## Minimal install and smoke check\n\n```bash\npip install code-review-graph\ncode-review-graph install\ncode-review-graph build\ncode-review-graph status\n```\n\nFor an existing install, the bundled [scripts\u002Fcheck_crg_install.py](scripts\u002Fcheck_crg_install.py) verifies import, package version, CLI discovery, and packaged docs without creating or updating a graph.\n\n## Sub-skill routes\n\n| Sub-skill | Read when |\n| --- | --- |\n| [install-and-setup](sub-skills\u002Finstall-and-setup\u002FSKILL.md) | Installing CRG, configuring MCP clients, building\u002Fupdating the graph, checking status, running the MCP server, visualizing, watching, or uninstalling. |\n| [review-changes](sub-skills\u002Freview-changes\u002FSKILL.md) | Reviewing a diff or PR, computing blast radius, risk scoring, test gaps, token savings, affected flows, or rendering a PR review comment. |\n| [graph-exploration](sub-skills\u002Fgraph-exploration\u002FSKILL.md) | Finding callers\u002Fcallees\u002Ftests\u002Fimports, searching graph nodes, inspecting flows\u002Fcommunities\u002Farchitecture, finding large functions, or previewing refactors. |\n| [integrations-and-extensions](sub-skills\u002Fintegrations-and-extensions\u002FSKILL.md) | Custom languages, embeddings\u002Fproviders, wiki generation, multi-repo registry, daemon watch workflows, GitHub Action setup, or eval\u002Fbenchmark reproduction. |\n\n## Shared references\n\n- [references\u002Fcli-reference.md](references\u002Fcli-reference.md) maps common CLI commands and flags.\n- [references\u002Fmcp-tools.md](references\u002Fmcp-tools.md) maps MCP tools and token-discipline rules.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers cross-cutting install, graph freshness, optional dependency, provider, and SQLite issues.\n- [references\u002Farchitecture-and-schema.md](references\u002Farchitecture-and-schema.md) summarizes graph node\u002Fedge semantics.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) records the source snapshot used to create this skill and when to refresh it.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured metadata for managed repo-skill routing.\n\n## Operating principles\n\n- Prefer graph tools over broad file reads when the user asks a structural question.\n- Start with compact context (`get_minimal_context_tool`) when an MCP session is available.\n- Use `detail_level=\"minimal\"` unless the next step requires source snippets or full graph details.\n- Keep optional extras optional; do not install embeddings, communities, wiki, eval, enrichment, or `all` unless the task needs them.\n- Treat cloud embeddings and external services as opt-in because code-derived text may leave the machine.\n- Rebuild or update the graph before trusting review\u002Fsearch answers after a branch switch, rebase, or large edit.\n\n## Boundaries and non-fits\n\nDo not use this skill as a general-purpose LSP replacement, full source-code reading strategy, or benchmark runner unless the user explicitly asks for CRG workflows. This skill covers the Python CLI\u002FMCP package and public integrations, not detailed development of the separate VS Code extension package.\n\n## Verification expectations\n\nThis runtime skill is grounded by package metadata, public docs, installed-package inspection, existing repo-local CRG skills, and native test candidates spanning install, CLI, MCP, review, search, flows, communities, refactor, optional integrations, and CI workflow safety. Final verification artifacts live outside this runtime skill under the review\u002Ftest artifact directory.","# code-review-graph\n\nUse this repo skill when a task names `code-review-graph`, CRG, graph-backed code review, local MCP graph tools, blast-radius analysis, structural code search, risk-scored PR review, custom language parsing, or multi-repo code graph operations.\n\n`code-review-graph` is a Python package and CLI\u002FMCP server that builds a local SQLite code knowledge graph from Tree-sitter parses, updates it incrementally, and exposes token-efficient review\u002Fsearch workflows to coding agents.\n\n## Fast route\n\n1. For first-time setup, read [references\u002Fstart-here.md](references\u002Fstart-here.md), then route to `install-and-setup`.\n2. For changed-code review or PR review, route to `review-changes`.\n3. For graph queries, architecture, flows, communities, or refactors, route to `graph-exploration`.\n4. For optional custom languages, embeddings, wiki, registry\u002Fdaemon, GitHub Action, or eval, route to `integrations-and-extensions`.\n\n## Minimal install and smoke check\n\n```bash\npip install code-review-graph\ncode-review-graph install\ncode-review-graph build\ncode-review-graph status\n```\n\nFor an existing install, the bundled [scripts\u002Fcheck_crg_install.py](scripts\u002Fcheck_crg_install.py) verifies import, package version, CLI discovery, and packaged docs without creating or updating a graph.\n\n## Sub-skill routes\n\n| Sub-skill | Read when |\n| --- | --- |\n| [install-and-setup](sub-skills\u002Finstall-and-setup\u002FSKILL.md) | Installing CRG, configuring MCP clients, building\u002Fupdating the graph, checking status, running the MCP server, visualizing, watching, or uninstalling. |\n| [review-changes](sub-skills\u002Freview-changes\u002FSKILL.md) | Reviewing a diff or PR, computing blast radius, risk scoring, test gaps, token savings, affected flows, or rendering a PR review comment. |\n| [graph-exploration](sub-skills\u002Fgraph-exploration\u002FSKILL.md) | Finding callers\u002Fcallees\u002Ftests\u002Fimports, searching graph nodes, inspecting flows\u002Fcommunities\u002Farchitecture, finding large functions, or previewing refactors. |\n| [integrations-and-extensions](sub-skills\u002Fintegrations-and-extensions\u002FSKILL.md) | Custom languages, embeddings\u002Fproviders, wiki generation, multi-repo registry, daemon watch workflows, GitHub Action setup, or eval\u002Fbenchmark reproduction. |\n\n## Shared references\n\n- [references\u002Fcli-reference.md](references\u002Fcli-reference.md) maps common CLI commands and flags.\n- [references\u002Fmcp-tools.md](references\u002Fmcp-tools.md) maps MCP tools and token-discipline rules.\n- [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) covers cross-cutting install, graph freshness, optional dependency, provider, and SQLite issues.\n- [references\u002Farchitecture-and-schema.md](references\u002Farchitecture-and-schema.md) summarizes graph node\u002Fedge semantics.\n- [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) records the source snapshot used to create this skill and when to refresh it.\n- [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json) is structured metadata for managed repo-skill routing.\n\n## Operating principles\n\n- Prefer graph tools over broad file reads when the user asks a structural question.\n- Start with compact context (`get_minimal_context_tool`) when an MCP session is available.\n- Use `detail_level=\"minimal\"` unless the next step requires source snippets or full graph details.\n- Keep optional extras optional; do not install embeddings, communities, wiki, eval, enrichment, or `all` unless the task needs them.\n- Treat cloud embeddings and external services as opt-in because code-derived text may leave the machine.\n- Rebuild or update the graph before trusting review\u002Fsearch answers after a branch switch, rebase, or large edit.\n\n## Boundaries and non-fits\n\nDo not use this skill as a general-purpose LSP replacement, full source-code reading strategy, or benchmark runner unless the user explicitly asks for CRG workflows. This skill covers the Python CLI\u002FMCP package and public integrations, not detailed development of the separate VS Code extension package.\n\n## Verification expectations\n\nThis runtime skill is grounded by package metadata, public docs, installed-package inspection, existing repo-local CRG skills, and native test candidates spanning install, CLI, MCP, review, search, flows, communities, refactor, optional integrations, and CI workflow safety. Final verification artifacts live outside this runtime skill under the review\u002Ftest artifact directory.",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph",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 code-review-graph",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill code-review-graph",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill code-review-graph","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002FSKILL.md",[46,52,56,60,64,68,72,76,80,84,88,92,96,100,104],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Farchitecture-and-schema.md","REFERENCE","参考文档",482,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Farchitecture-and-schema.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fcli-reference.md",2798,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fcli-reference.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fcustom-languages.md",473,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fcustom-languages.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fembeddings.md",468,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fembeddings.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Feval.md",389,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Feval.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fgithub-action.md",433,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fgithub-action.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fmcp-tools.md",2477,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fmcp-tools.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fregistry-and-daemon.md",655,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fregistry-and-daemon.md",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Frepo-provenance.md",2349,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Frepo-provenance.md",{"path":85,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Frepo-routing-metadata.json",423,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Frepo-routing-metadata.json",{"path":89,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Freview-workflows.md",982,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Freview-workflows.md",{"path":93,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fsearch-and-analysis.md",760,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fsearch-and-analysis.md",{"path":97,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fstart-here.md",2152,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Fstart-here.md",{"path":101,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Ftroubleshooting.md",1776,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Freferences\u002Ftroubleshooting.md",{"path":105,"resourceType":106,"resourceTypeDesc":107,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Fcheck_crg_install.py","SCRIPT","脚本",3804,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fcode-review-graph\u002Fscripts\u002Fcheck_crg_install.py",[111,119,126,133,140,147],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":115,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"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":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":115,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"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":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":115,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"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":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":115,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"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":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":115,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"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":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":115,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"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",[],[]]