[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78XXQMHDR8CDYKWFPTMEHCS":3,"skill-same:01M78XXQMHDR8CDYKWFPTMEHCS":75},{"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},"01M78XXQMHDR8CDYKWFPTMEHCS","analyze-publish",null,"Inspect, compare, regrade, export, share, upload, and publish Harbor results, trajectories, artifacts, Hub records, and versioned task or dataset packages with mutation and credential gates.","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\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: analyze-publish\ndescription: \"Inspect, compare, regrade, export, share, upload, and publish\n  Harbor results, trajectories, artifacts, Hub records, and versioned task or\n  dataset packages with mutation and credential gates.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# Analyze and publish Harbor outcomes\n\nUse this skill when a Harbor run already exists and the task is to inspect its\nresults, understand trajectories or artifacts, compare runs, regrade a recorded\nexecution, browse the local viewer or Hub, export traces, upload\u002Fshare job\nresults, or publish and version task\u002Fdataset packages. Keep the source record\nimmutable unless a command below explicitly creates a derived result or asks for\nconfirmation.\n\n## Route by intent\n\n- **Inspect result files, rewards, retries, artifacts, ATIF, or native sessions:**\n  read [results-and-trajectories.md](references\u002Fresults-and-trajectories.md).\n- **Run a rubric analysis or quality check, browse locally, query Hub records, or\n  compare jobs:** read [analysis-viewer-hub.md](references\u002Fanalysis-viewer-hub.md).\n- **Download, share, upload, publish, inspect package versions, or move a tag:**\n  read [publish-upload-versioning.md](references\u002Fpublish-upload-versioning.md).\n- **Summarize benchmark parity records:** read\n  [parity-reporting.md](references\u002Fparity-reporting.md).\n- **Diagnose malformed outputs, missing artifacts, auth, viewer, or version\n  failures:** start with [troubleshooting.md](references\u002Ftroubleshooting.md).\n\nRoute task\u002Fschema\u002Fverifier authoring to `author-benchmarks`, job\u002Fprovider\u002Fagent\nexecution failures to `run-evaluate`, and custom framework or plugin code to\n`integrations`. Do not relaunch an evaluation merely to inspect a recorded run.\n\n## Safety and mutation gates\n\n1. Identify whether the input is a local trial directory, local job directory,\n   Hub job\u002Ftrial UUID, task package, or dataset package before selecting a\n   command. Check `harbor --version` when command behavior may be version-sensitive.\n2. Prefer local parsing, `--json`, `harbor hub ... show\u002Flist\u002Ftasks\u002Ftrials\u002Fshares`,\n   `harbor version list\u002Fshow`, and `harbor view` for read-only inspection.\n3. Treat `harbor analyze` and `harbor check` as **source-preserving but not\n   cost-free**: they create derived Harbor jobs, may run an evaluator agent and\n   environment, and write reports. Show rubric, agent\u002Fmodel, environment,\n   attempts, filters, and output directory before running them.\n4. Never run `harbor upload`, Hub copy\u002Fshare\u002Fretry\u002Fcancel\u002Fdelete, visibility or\n   access changes, `harbor publish`, or `harbor version tag` without explicit\n   approval for the exact target, credentials, visibility, recipients, and\n   mutation. `harbor traces export` is local by default; `--push` or OTLP\n   endpoint upload is an external mutation and needs the same gate.\n5. Keep credentials in the CLI's auth flow or environment. Do not print tokens,\n   copy private result contents into prompts, or infer that a local login grants\n   access to another organization.\n\n## Safe operating sequence\n\n1. Inventory the local tree (`config.json`, `lock.json`, `result.json`,\n   `job.log`\u002F`trial.log`, `artifacts\u002Fmanifest.json`, `agent\u002Ftrajectory.json`,\n   native session files, retry folders) and preserve a digest or copy when an\n   audit needs reproducibility.\n2. Read result and manifest JSON before opening large logs. Separate the recorded\n   agent\u002Fmodel\u002Fconfiguration from verifier rewards, exceptions, costs, retries,\n   and post-hoc analysis. A retry is a new attempt; a regrade is a new derived\n   trial that does not rerun the agent.\n3. Use the narrowest read-only command or local parser. For a Hub record, inspect\n   with `harbor hub job show`, `tasks`, `trials`, `shares`, `compare`, or `hub\n   trial show`; use `--json` for machine processing and `--include-retries` when\n   retry history changes the conclusion.\n4. For a regrade, verify the source has readable `result.json`, a trustworthy\n   artifact manifest and bytes, and that the replacement verifier is\n   single-step and separate-mode. Use `harbor job regrade` or `harbor trial\n   regrade`; record the new output path and compare the printed reward delta.\n5. For any external operation, preview the exact command and expected side\n   effects, obtain confirmation, check authentication, then verify the returned\n   ID, visibility, revision, digest, or URL. Record partial failures and retry\n   only the failed\u002Fidempotent portion.\n\n## What this skill does not claim\n\nHelp\u002Fparser checks and mocked\u002Funit evidence validate command contracts only.\nDocker, cloud providers, model APIs, Hub\u002Fregistry credentials, Hugging Face,\nOTLP endpoints, GPU, and frontend build toolchains are optional capabilities and\nmust remain explicitly unverified unless actually exercised with approval.\n","# Analyze and publish Harbor outcomes\n\nUse this skill when a Harbor run already exists and the task is to inspect its\nresults, understand trajectories or artifacts, compare runs, regrade a recorded\nexecution, browse the local viewer or Hub, export traces, upload\u002Fshare job\nresults, or publish and version task\u002Fdataset packages. Keep the source record\nimmutable unless a command below explicitly creates a derived result or asks for\nconfirmation.\n\n## Route by intent\n\n- **Inspect result files, rewards, retries, artifacts, ATIF, or native sessions:**\n  read [results-and-trajectories.md](references\u002Fresults-and-trajectories.md).\n- **Run a rubric analysis or quality check, browse locally, query Hub records, or\n  compare jobs:** read [analysis-viewer-hub.md](references\u002Fanalysis-viewer-hub.md).\n- **Download, share, upload, publish, inspect package versions, or move a tag:**\n  read [publish-upload-versioning.md](references\u002Fpublish-upload-versioning.md).\n- **Summarize benchmark parity records:** read\n  [parity-reporting.md](references\u002Fparity-reporting.md).\n- **Diagnose malformed outputs, missing artifacts, auth, viewer, or version\n  failures:** start with [troubleshooting.md](references\u002Ftroubleshooting.md).\n\nRoute task\u002Fschema\u002Fverifier authoring to `author-benchmarks`, job\u002Fprovider\u002Fagent\nexecution failures to `run-evaluate`, and custom framework or plugin code to\n`integrations`. Do not relaunch an evaluation merely to inspect a recorded run.\n\n## Safety and mutation gates\n\n1. Identify whether the input is a local trial directory, local job directory,\n   Hub job\u002Ftrial UUID, task package, or dataset package before selecting a\n   command. Check `harbor --version` when command behavior may be version-sensitive.\n2. Prefer local parsing, `--json`, `harbor hub ... show\u002Flist\u002Ftasks\u002Ftrials\u002Fshares`,\n   `harbor version list\u002Fshow`, and `harbor view` for read-only inspection.\n3. Treat `harbor analyze` and `harbor check` as **source-preserving but not\n   cost-free**: they create derived Harbor jobs, may run an evaluator agent and\n   environment, and write reports. Show rubric, agent\u002Fmodel, environment,\n   attempts, filters, and output directory before running them.\n4. Never run `harbor upload`, Hub copy\u002Fshare\u002Fretry\u002Fcancel\u002Fdelete, visibility or\n   access changes, `harbor publish`, or `harbor version tag` without explicit\n   approval for the exact target, credentials, visibility, recipients, and\n   mutation. `harbor traces export` is local by default; `--push` or OTLP\n   endpoint upload is an external mutation and needs the same gate.\n5. Keep credentials in the CLI's auth flow or environment. Do not print tokens,\n   copy private result contents into prompts, or infer that a local login grants\n   access to another organization.\n\n## Safe operating sequence\n\n1. Inventory the local tree (`config.json`, `lock.json`, `result.json`,\n   `job.log`\u002F`trial.log`, `artifacts\u002Fmanifest.json`, `agent\u002Ftrajectory.json`,\n   native session files, retry folders) and preserve a digest or copy when an\n   audit needs reproducibility.\n2. Read result and manifest JSON before opening large logs. Separate the recorded\n   agent\u002Fmodel\u002Fconfiguration from verifier rewards, exceptions, costs, retries,\n   and post-hoc analysis. A retry is a new attempt; a regrade is a new derived\n   trial that does not rerun the agent.\n3. Use the narrowest read-only command or local parser. For a Hub record, inspect\n   with `harbor hub job show`, `tasks`, `trials`, `shares`, `compare`, or `hub\n   trial show`; use `--json` for machine processing and `--include-retries` when\n   retry history changes the conclusion.\n4. For a regrade, verify the source has readable `result.json`, a trustworthy\n   artifact manifest and bytes, and that the replacement verifier is\n   single-step and separate-mode. Use `harbor job regrade` or `harbor trial\n   regrade`; record the new output path and compare the printed reward delta.\n5. For any external operation, preview the exact command and expected side\n   effects, obtain confirmation, check authentication, then verify the returned\n   ID, visibility, revision, digest, or URL. Record partial failures and retry\n   only the failed\u002Fidempotent portion.\n\n## What this skill does not claim\n\nHelp\u002Fparser checks and mocked\u002Funit evidence validate command contracts only.\nDocker, cloud providers, model APIs, Hub\u002Fregistry credentials, Hugging Face,\nOTLP endpoints, GPU, and frontend build toolchains are optional capabilities and\nmust remain explicitly unverified unless actually exercised with approval.\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\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish",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 analyze-publish",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill analyze-publish",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill analyze-publish","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002FSKILL.md",[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fanalysis-viewer-hub.md","REFERENCE","参考文档",4975,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002Freferences\u002Fanalysis-viewer-hub.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fparity-reporting.md",3767,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002Freferences\u002Fparity-reporting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fpublish-upload-versioning.md",5595,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002Freferences\u002Fpublish-upload-versioning.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fresults-and-trajectories.md",6954,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002Freferences\u002Fresults-and-trajectories.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Ftroubleshooting.md",6356,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002Freferences\u002Ftroubleshooting.md",{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fgenerate_parity_summary.py","SCRIPT","脚本",7209,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fharbor\u002Fsub-skills\u002Fanalyze-publish\u002Fscripts\u002Fgenerate_parity_summary.py",[76,83,90,97,104,111],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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",[],[]]