[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797KQ52YC55GFPRXZYECH63":3,"skill-same:01M797KQ52YC55GFPRXZYECH63":71},{"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},"01M797KQ52YC55GFPRXZYECH63","prompt-automation",null,"Configure YiVal data generators and prompt variation generators for synthetic examples, document questions, chain-of-density prompts, and self-exemplar prompts.","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\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prompt-automation\ndescription: \"Configure YiVal data generators and prompt variation generators\n  for synthetic examples, document questions, chain-of-density prompts, and\n  self-exemplar prompts.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# YiVal prompt automation\n\nUse this sub-skill when the task involves generating input examples, generating prompt variations, caching generated prompts\u002Fdata, using `yival gen`\u002F`yival task`, or wiring OpenAI\u002Fdocument\u002Fchain-of-density\u002Fself-exemplar generators into a YiVal config.\n\n## Read first\n\n- [Generators reference](references\u002Fgenerators-reference.md): built-in data and variation generators, config fields, and registry ids.\n- [Prompt workflows](references\u002Fprompt-workflows.md): common auto-prompt experiment patterns.\n- [Provider and cache notes](references\u002Fprovider-cache-notes.md): credentials, output paths, rate limits, and offline alternatives.\n- [Prompt automation troubleshooting](references\u002Ftroubleshooting.md): generation-specific failures.\n\nUseful helper:\n\n- `python sub-skills\u002Fprompt-automation\u002Fscripts\u002Finspect_prompt_components.py` prints built-in generator ids and default configs after importing their modules.\n\n## Built-in generator map\n\n| Need | YAML location | Registry id |\n| --- | --- | --- |\n| Generate synthetic input examples from a function\u002Ftask description | `dataset.data_generators` | `openai_prompt_data_generator` |\n| Generate questions from text\u002Ffile\u002FGoogle Drive document content | `dataset.data_generators` | `document_data_generator` |\n| Generate optimized prompt strings with OpenAI | `variations[].generator_name` | `openai_prompt_based_variation_generator` |\n| Use the fixed chain-of-density summarization prompt | `variations[].generator_name` | `chain_of_density_prompt_generator` |\n| Use a self-exemplar prompt template | `variations[].generator_name` | `self_exemplar` |\n\n## Minimal auto-prompt shape\n\n```yaml\ndescription: Auto prompt experiment\ncustom_function: my_task.headline\ndataset:\n  source_type: machine_generated\n  data_generators:\n    openai_prompt_data_generator:\n      number_of_examples: 2\n      chunk_size: 1000\n      model_name: gpt-4\n      output_path: generated_examples.pkl\n      input_function:\n        name: headline_generation\n        description: Generate a landing page headline for a tech startup business.\n        parameters:\n          tech_startup_business: str\nvariations:\n  - name: task\n    generator_name: openai_prompt_based_variation_generator\n    generator_config:\n      number_of_variations: 2\n      model_name: gpt-4\n      output_path: generated_prompts.pkl\n      variables:\n        - tech_startup_business\n      prompt:\n        - role: system\n          content: Write concise prompts for GPT-4.\n    variations:\n      - value_type: str\n        value: Generate landing page headline for {tech_startup_business}\n        instantiated_value: Generate landing page headline for {tech_startup_business}\n        variation_id: null\n```\n\nThe custom function should use `StringWrapper(name=\"task\", variables={\"tech_startup_business\": tech_startup_business}, state=state)` so generated\u002Fmanual prompt values are applied.\n\n## Workflow guidance\n\n1. Start with a tiny run: one or two generated examples and one or two variations.\n2. Always set `output_path` for provider-backed generators so reruns load cached pickles instead of paying\u002Fcalling again.\n3. Keep `variables` explicit for prompt variation generation; generated prompt outputs must contain `{variable}` placeholders when configured.\n4. For document generation, start with `source: text` before file or Google Drive sources.\n5. Route generated outputs into [evaluation-optimization](..\u002Fevaluation-optimization\u002FSKILL.md) for evaluator, selector, and enhancer design.\n\n## Safety and cost boundaries\n\n- OpenAI generators call network services and can bill. Confirm credentials and budget before running.\n- Document file\u002Fdrive sources can invoke loaders, OCR, Google APIs, and local file reads. Use only approved documents.\n- Retrieval demos that use embeddings\u002FFAISS\u002FOpenAI are reference patterns, not default runtime paths.\n- If the user only needs a static prompt list, use manual `variations` instead of provider-backed generation.\n","# YiVal prompt automation\n\nUse this sub-skill when the task involves generating input examples, generating prompt variations, caching generated prompts\u002Fdata, using `yival gen`\u002F`yival task`, or wiring OpenAI\u002Fdocument\u002Fchain-of-density\u002Fself-exemplar generators into a YiVal config.\n\n## Read first\n\n- [Generators reference](references\u002Fgenerators-reference.md): built-in data and variation generators, config fields, and registry ids.\n- [Prompt workflows](references\u002Fprompt-workflows.md): common auto-prompt experiment patterns.\n- [Provider and cache notes](references\u002Fprovider-cache-notes.md): credentials, output paths, rate limits, and offline alternatives.\n- [Prompt automation troubleshooting](references\u002Ftroubleshooting.md): generation-specific failures.\n\nUseful helper:\n\n- `python sub-skills\u002Fprompt-automation\u002Fscripts\u002Finspect_prompt_components.py` prints built-in generator ids and default configs after importing their modules.\n\n## Built-in generator map\n\n| Need | YAML location | Registry id |\n| --- | --- | --- |\n| Generate synthetic input examples from a function\u002Ftask description | `dataset.data_generators` | `openai_prompt_data_generator` |\n| Generate questions from text\u002Ffile\u002FGoogle Drive document content | `dataset.data_generators` | `document_data_generator` |\n| Generate optimized prompt strings with OpenAI | `variations[].generator_name` | `openai_prompt_based_variation_generator` |\n| Use the fixed chain-of-density summarization prompt | `variations[].generator_name` | `chain_of_density_prompt_generator` |\n| Use a self-exemplar prompt template | `variations[].generator_name` | `self_exemplar` |\n\n## Minimal auto-prompt shape\n\n```yaml\ndescription: Auto prompt experiment\ncustom_function: my_task.headline\ndataset:\n  source_type: machine_generated\n  data_generators:\n    openai_prompt_data_generator:\n      number_of_examples: 2\n      chunk_size: 1000\n      model_name: gpt-4\n      output_path: generated_examples.pkl\n      input_function:\n        name: headline_generation\n        description: Generate a landing page headline for a tech startup business.\n        parameters:\n          tech_startup_business: str\nvariations:\n  - name: task\n    generator_name: openai_prompt_based_variation_generator\n    generator_config:\n      number_of_variations: 2\n      model_name: gpt-4\n      output_path: generated_prompts.pkl\n      variables:\n        - tech_startup_business\n      prompt:\n        - role: system\n          content: Write concise prompts for GPT-4.\n    variations:\n      - value_type: str\n        value: Generate landing page headline for {tech_startup_business}\n        instantiated_value: Generate landing page headline for {tech_startup_business}\n        variation_id: null\n```\n\nThe custom function should use `StringWrapper(name=\"task\", variables={\"tech_startup_business\": tech_startup_business}, state=state)` so generated\u002Fmanual prompt values are applied.\n\n## Workflow guidance\n\n1. Start with a tiny run: one or two generated examples and one or two variations.\n2. Always set `output_path` for provider-backed generators so reruns load cached pickles instead of paying\u002Fcalling again.\n3. Keep `variables` explicit for prompt variation generation; generated prompt outputs must contain `{variable}` placeholders when configured.\n4. For document generation, start with `source: text` before file or Google Drive sources.\n5. Route generated outputs into [evaluation-optimization](..\u002Fevaluation-optimization\u002FSKILL.md) for evaluator, selector, and enhancer design.\n\n## Safety and cost boundaries\n\n- OpenAI generators call network services and can bill. Confirm credentials and budget before running.\n- Document file\u002Fdrive sources can invoke loaders, OCR, Google APIs, and local file reads. Use only approved documents.\n- Retrieval demos that use embeddings\u002FFAISS\u002FOpenAI are reference patterns, not default runtime paths.\n- If the user only needs a static prompt list, use manual `variations` instead of provider-backed generation.\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\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation",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-automation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill prompt-automation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill prompt-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fgenerators-reference.md","REFERENCE","参考文档",3553,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002Freferences\u002Fgenerators-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fprompt-workflows.md",2685,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002Freferences\u002Fprompt-workflows.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fprovider-cache-notes.md",1759,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002Freferences\u002Fprovider-cache-notes.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",1876,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Finspect_prompt_components.py","SCRIPT","脚本",1838,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fyi-val\u002Fsub-skills\u002Fprompt-automation\u002Fscripts\u002Finspect_prompt_components.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]