[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M791VDYME0CXNFX89MB34DMB":3,"skill-same:01M791VDYME0CXNFX89MB34DMB":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},"01M791VDYME0CXNFX89MB34DMB","prompt-and-inference",null,"Build and debug OpenCompass prompt templates, PromptList dialogue prompts, retrievers, Gen\u002FPPL inferencers, reader_cfg answer masking, in-context examples, and meta_template role routing.","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\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prompt-and-inference\ndescription: \"Build and debug OpenCompass prompt templates, PromptList dialogue\n  prompts, retrievers, Gen\u002FPPL inferencers, reader_cfg answer masking,\n  in-context examples, and meta_template role routing.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# OpenCompass Prompt and Inference\n\nUse this sub-skill when an OpenCompass task involves prompt construction or inference config behavior: `PromptTemplate`, `RawPromptTemplate`, `PromptList` dialogue turns, `ice_template`, `prompt_template`, retrievers, `GenInferencer`, `PPLInferencer`, output-column masking, or `meta_template` role mapping.\n\n## Route the Task\n\n- For prompt syntax, answer masking, missing literal fields, dialogue `PromptList`, raw messages, or CoT wording, use `references\u002Fprompt-templates.md`.\n- For choosing `ZeroRetriever`\u002Ffew-shot retrievers and wiring `GenInferencer` vs `PPLInferencer`, use `references\u002Fretrievers-and-inferencers.md`.\n- For symptoms such as literal `{answer}`, leaked labels, missing system role handling, unsupported PPL candidate templates, or train split failures, use `references\u002Ftroubleshooting.md`.\n- For a no-download local preview of tiny samples and templates, run `python scripts\u002Frender_prompt_preview.py --help` from this sub-skill directory.\n\n## High-Value Defaults\n\n- Use `GenInferencer` for free-form answers and keep the dataset answer column in `reader_cfg.output_column` so it is replaced by `gen_field_replace_token` instead of leaking into the generation prompt.\n- Use `PPLInferencer` for multiple-choice\u002Fdiscriminative tasks and provide candidate templates keyed by label (`\"A\"`, `\"B\"`, etc.) in `prompt_template.template` or `ice_template.template`.\n- Use `ZeroRetriever` for 0-shot; use `FixKRetriever` only when the selected in-context examples exist in the dataset train\u002Findex split.\n- Put model-specific chat wrappers in the model `meta_template`; keep dataset prompt templates model-agnostic and role-based (`HUMAN`, `BOT`, `SYSTEM`).\n\n## Boundaries\n\n- Route dataset class creation, `reader_cfg` source columns, and config file structure to `configuration-and-datasets`.\n- Route tokenizer behavior, model chat templates, backend acceleration, and real HF\u002FAPI inference issues to `model-backends`.\n- Do not claim real model inference was verified from this sub-skill; the bundled script renders prompt construction only.\n","# OpenCompass Prompt and Inference\n\nUse this sub-skill when an OpenCompass task involves prompt construction or inference config behavior: `PromptTemplate`, `RawPromptTemplate`, `PromptList` dialogue turns, `ice_template`, `prompt_template`, retrievers, `GenInferencer`, `PPLInferencer`, output-column masking, or `meta_template` role mapping.\n\n## Route the Task\n\n- For prompt syntax, answer masking, missing literal fields, dialogue `PromptList`, raw messages, or CoT wording, use `references\u002Fprompt-templates.md`.\n- For choosing `ZeroRetriever`\u002Ffew-shot retrievers and wiring `GenInferencer` vs `PPLInferencer`, use `references\u002Fretrievers-and-inferencers.md`.\n- For symptoms such as literal `{answer}`, leaked labels, missing system role handling, unsupported PPL candidate templates, or train split failures, use `references\u002Ftroubleshooting.md`.\n- For a no-download local preview of tiny samples and templates, run `python scripts\u002Frender_prompt_preview.py --help` from this sub-skill directory.\n\n## High-Value Defaults\n\n- Use `GenInferencer` for free-form answers and keep the dataset answer column in `reader_cfg.output_column` so it is replaced by `gen_field_replace_token` instead of leaking into the generation prompt.\n- Use `PPLInferencer` for multiple-choice\u002Fdiscriminative tasks and provide candidate templates keyed by label (`\"A\"`, `\"B\"`, etc.) in `prompt_template.template` or `ice_template.template`.\n- Use `ZeroRetriever` for 0-shot; use `FixKRetriever` only when the selected in-context examples exist in the dataset train\u002Findex split.\n- Put model-specific chat wrappers in the model `meta_template`; keep dataset prompt templates model-agnostic and role-based (`HUMAN`, `BOT`, `SYSTEM`).\n\n## Boundaries\n\n- Route dataset class creation, `reader_cfg` source columns, and config file structure to `configuration-and-datasets`.\n- Route tokenizer behavior, model chat templates, backend acceleration, and real HF\u002FAPI inference issues to `model-backends`.\n- Do not claim real model inference was verified from this sub-skill; the bundled script renders prompt construction only.\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\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference",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 prompt-and-inference",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill prompt-and-inference",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill prompt-and-inference","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fprompt-templates.md","REFERENCE","参考文档",6612,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference\u002Freferences\u002Fprompt-templates.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fretrievers-and-inferencers.md",5575,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference\u002Freferences\u002Fretrievers-and-inferencers.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5771,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Frender_prompt_preview.py","SCRIPT","脚本",7905,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fopencompass\u002Fsub-skills\u002Fprompt-and-inference\u002Fscripts\u002Frender_prompt_preview.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",[],[]]