[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7981YVFP5ZMJS7S5F0QAD3Q":3,"skill-same:01M7981YVFP5ZMJS7S5F0QAD3Q":54},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7981YVFP5ZMJS7S5F0QAD3Q","cot_prompt_templates",null,"Build standard, chain-of-thought, and ablation few-shot prompts with auditable prompt structure metadata.","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\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fchain_of_thought_prompting\u002Fcot_prompt_templates\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cot_prompt_templates\ndescription: Build standard, chain-of-thought, and ablation few-shot prompts with auditable prompt structure metadata.\n---\n\n# Chain-of-Thought Prompt Templates\n\nUse this skill when you need to construct prompts for the chain-of-thought prompting paper or for a recovery experiment that compares direct few-shot answers against reasoning-before-answer exemplars. Do not use it to run an LLM, compute a task answer, or score a prediction.\n\n## Inputs\n\n- A JSON list of exemplars. Every exemplar needs `question` and `answer`; chain-of-thought and ablation modes also need `reasoning`.\n- A target question string.\n- A mode: `standard`, `chain_of_thought`, `equation_only`, `variable_compute_only`, or `reasoning_after_answer`.\n\n## Outputs\n\n- Prompt text containing rendered exemplars and the target question.\n- Metadata describing mode, exemplar count, reasoning placement, and whether final-answer markers are present.\n\n## Workflow\n\n1. Select the prompt mode that matches the comparison being run.\n2. Validate exemplar fields before rendering; reject missing reasoning in chain-of-thought modes.\n3. Render exemplars as `Q:` and `A:` blocks.\n4. For `chain_of_thought`, place reasoning before `The answer is ...`.\n5. For `standard`, omit reasoning and include only the direct answer.\n6. For ablations, preserve the structural difference being tested: equations only, useless variable-compute padding, or reasoning after the answer.\n7. Append the target question and `A:` prefix without including the target answer.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fcot_prompt_templates.py --self-test\npython -m unittest discover -s tests\n```\n\nThe tests verify that standard prompts omit reasoning, chain-of-thought prompts include reasoning before the final answer, and ablation modes are structurally distinct.\n\n## Limitations\n\nThis skill does not infer missing reasoning, call a model, or canonicalize answers. Pair it with `cot_answer_extraction` and `cot_equation_calculator` for evaluation or recovery work.\n","# Chain-of-Thought Prompt Templates\n\nUse this skill when you need to construct prompts for the chain-of-thought prompting paper or for a recovery experiment that compares direct few-shot answers against reasoning-before-answer exemplars. Do not use it to run an LLM, compute a task answer, or score a prediction.\n\n## Inputs\n\n- A JSON list of exemplars. Every exemplar needs `question` and `answer`; chain-of-thought and ablation modes also need `reasoning`.\n- A target question string.\n- A mode: `standard`, `chain_of_thought`, `equation_only`, `variable_compute_only`, or `reasoning_after_answer`.\n\n## Outputs\n\n- Prompt text containing rendered exemplars and the target question.\n- Metadata describing mode, exemplar count, reasoning placement, and whether final-answer markers are present.\n\n## Workflow\n\n1. Select the prompt mode that matches the comparison being run.\n2. Validate exemplar fields before rendering; reject missing reasoning in chain-of-thought modes.\n3. Render exemplars as `Q:` and `A:` blocks.\n4. For `chain_of_thought`, place reasoning before `The answer is ...`.\n5. For `standard`, omit reasoning and include only the direct answer.\n6. For ablations, preserve the structural difference being tested: equations only, useless variable-compute padding, or reasoning after the answer.\n7. Append the target question and `A:` prefix without including the target answer.\n\n## Validation\n\nRun:\n\n```bash\npython scripts\u002Fcot_prompt_templates.py --self-test\npython -m unittest discover -s tests\n```\n\nThe tests verify that standard prompts omit reasoning, chain-of-thought prompts include reasoning before the final answer, and ablation modes are structurally distinct.\n\n## Limitations\n\nThis skill does not infer missing reasoning, call a model, or canonicalize answers. Pair it with `cot_answer_extraction` and `cot_equation_calculator` for evaluation or recovery work.\n",{"name":5,"description":7},"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fchain_of_thought_prompting\u002Fcot_prompt_templates",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill cot_prompt_templates",{"tool":36,"command":37},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill cot_prompt_templates",{"tool":39,"command":40},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill cot_prompt_templates","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fchain_of_thought_prompting\u002Fcot_prompt_templates\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"scripts\u002Fcot_prompt_templates.py","SCRIPT","脚本",4960,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fchain_of_thought_prompting\u002Fcot_prompt_templates\u002Fscripts\u002Fcot_prompt_templates.py",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"tests\u002Ftest_cot_prompt_templates.py",1558,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPaperBench\u002Fskills\u002Fbbox\u002Fskill\u002Fchain_of_thought_prompting\u002Fcot_prompt_templates\u002Ftests\u002Ftest_cot_prompt_templates.py",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":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},"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":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},"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":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},"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",[],[]]