[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDVB6ZX4KJDBV0KK5DYFXY":3,"skill-same:01M7FDVB6ZX4KJDBV0KK5DYFXY":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7FDVB6ZX4KJDBV0KK5DYFXY","ask-questions-if-underspecified",null,"Clarify requirements before implementing. Use when serious doubts arise.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fask-questions-if-underspecified\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: ask-questions-if-underspecified\ndescription: Clarify requirements before implementing. Use when serious doubts arise.\nrisk: safe\nsource: community\ndate_added: \"2026-09-04\"\n---\n\n# Ask Questions If Underspecified\n\n## When to Use\nUse this skill when a request has multiple plausible interpretations or key details (objective, scope, constraints, environment, or safety) are unclear.\n\n## When NOT to Use\n\nDo not use this skill when the request is already clear, or when a quick, low-risk discovery read can answer the missing details.\n\n## Goal\n\nAsk the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).\n\n## Workflow\n\n### 1) Decide whether the request is underspecified\n\nTreat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear:\n- Define the objective (what should change vs stay the same)\n- Define \"done\" (acceptance criteria, examples, edge cases)\n- Define scope (which files\u002Fcomponents\u002Fusers are in\u002Fout)\n- Define constraints (compatibility, performance, style, deps, time)\n- Identify environment (language\u002Fruntime versions, OS, build\u002Ftest runner)\n- Clarify safety\u002Freversibility (data migration, rollout\u002Frollback, risk)\n\nIf multiple plausible interpretations exist, assume it is underspecified.\n\n### 2) Ask must-have questions first (keep it small)\n\nAsk 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work.\n\nMake questions easy to answer:\n- Optimize for scannability (short, numbered questions; avoid paragraphs)\n- Offer multiple-choice options when possible\n- Suggest reasonable defaults when appropriate (mark them clearly as the default\u002Frecommended choice; bold the recommended choice in the list, or if you present options in a code block, put a bold \"Recommended\" line immediately above the block and also tag defaults inside the block)\n- Include a fast-path response (e.g., reply `defaults` to accept all recommended\u002Fdefault choices)\n- Include a low-friction \"not sure\" option when helpful (e.g., \"Not sure - use default\")\n- Separate \"Need to know\" from \"Nice to know\" if that reduces friction\n- Structure options so the user can respond with compact decisions (e.g., `1b 2a 3c`); restate the chosen options in plain language to confirm\n\n### 3) Pause before acting\n\nUntil must-have answers arrive:\n- Do not run commands, edit files, or produce a detailed plan that depends on unknowns\n- Do perform a clearly labeled, low-risk discovery step only if it does not commit you to a direction (e.g., inspect repo structure, read relevant config files)\n\nIf the user explicitly asks you to proceed without answers:\n- State your assumptions as a short numbered list\n- Ask for confirmation; proceed only after they confirm or correct them\n\n### 4) Confirm interpretation, then proceed\n\nOnce you have answers, restate the requirements in 1-3 sentences (including key constraints and what success looks like), then start work.\n\n## Question templates\n\n- \"Before I start, I need: (1) ..., (2) ..., (3) .... If you don't care about (2), I will assume ....\"\n- \"Which of these should it be? A) ... B) ... C) ... (pick one)\"\n- \"What would you consider 'done'? For example: ...\"\n- \"Any constraints I must follow (versions, performance, style, deps)? If none, I will target the existing project defaults.\"\n- Use numbered questions with lettered options and a clear reply format\n\n```text\n1) Scope?\na) Minimal change (default)\nb) Refactor while touching the area\nc) Not sure - use default\n2) Compatibility target?\na) Current project defaults (default)\nb) Also support older versions: \u003Cspecify>\nc) Not sure - use default\n\nReply with: defaults (or 1a 2a)\n```\n\n## Anti-patterns\n\n- Don't ask questions you can answer with a quick, low-risk discovery read (e.g., configs, existing patterns, docs).\n- Don't ask open-ended questions if a tight multiple-choice or yes\u002Fno would eliminate ambiguity faster.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Ask Questions If Underspecified\n\n## When to Use\nUse this skill when a request has multiple plausible interpretations or key details (objective, scope, constraints, environment, or safety) are unclear.\n\n## When NOT to Use\n\nDo not use this skill when the request is already clear, or when a quick, low-risk discovery read can answer the missing details.\n\n## Goal\n\nAsk the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).\n\n## Workflow\n\n### 1) Decide whether the request is underspecified\n\nTreat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear:\n- Define the objective (what should change vs stay the same)\n- Define \"done\" (acceptance criteria, examples, edge cases)\n- Define scope (which files\u002Fcomponents\u002Fusers are in\u002Fout)\n- Define constraints (compatibility, performance, style, deps, time)\n- Identify environment (language\u002Fruntime versions, OS, build\u002Ftest runner)\n- Clarify safety\u002Freversibility (data migration, rollout\u002Frollback, risk)\n\nIf multiple plausible interpretations exist, assume it is underspecified.\n\n### 2) Ask must-have questions first (keep it small)\n\nAsk 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work.\n\nMake questions easy to answer:\n- Optimize for scannability (short, numbered questions; avoid paragraphs)\n- Offer multiple-choice options when possible\n- Suggest reasonable defaults when appropriate (mark them clearly as the default\u002Frecommended choice; bold the recommended choice in the list, or if you present options in a code block, put a bold \"Recommended\" line immediately above the block and also tag defaults inside the block)\n- Include a fast-path response (e.g., reply `defaults` to accept all recommended\u002Fdefault choices)\n- Include a low-friction \"not sure\" option when helpful (e.g., \"Not sure - use default\")\n- Separate \"Need to know\" from \"Nice to know\" if that reduces friction\n- Structure options so the user can respond with compact decisions (e.g., `1b 2a 3c`); restate the chosen options in plain language to confirm\n\n### 3) Pause before acting\n\nUntil must-have answers arrive:\n- Do not run commands, edit files, or produce a detailed plan that depends on unknowns\n- Do perform a clearly labeled, low-risk discovery step only if it does not commit you to a direction (e.g., inspect repo structure, read relevant config files)\n\nIf the user explicitly asks you to proceed without answers:\n- State your assumptions as a short numbered list\n- Ask for confirmation; proceed only after they confirm or correct them\n\n### 4) Confirm interpretation, then proceed\n\nOnce you have answers, restate the requirements in 1-3 sentences (including key constraints and what success looks like), then start work.\n\n## Question templates\n\n- \"Before I start, I need: (1) ..., (2) ..., (3) .... If you don't care about (2), I will assume ....\"\n- \"Which of these should it be? A) ... B) ... C) ... (pick one)\"\n- \"What would you consider 'done'? For example: ...\"\n- \"Any constraints I must follow (versions, performance, style, deps)? If none, I will target the existing project defaults.\"\n- Use numbered questions with lettered options and a clear reply format\n\n```text\n1) Scope?\na) Minimal change (default)\nb) Refactor while touching the area\nc) Not sure - use default\n2) Compatibility target?\na) Current project defaults (default)\nb) Also support older versions: \u003Cspecify>\nc) Not sure - use default\n\nReply with: defaults (or 1a 2a)\n```\n\n## Anti-patterns\n\n- Don't ask questions you can answer with a quick, low-risk discovery read (e.g., configs, existing patterns, docs).\n- Don't ask open-ended questions if a tight multiple-choice or yes\u002Fno would eliminate ambiguity faster.\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"safe","community","2026-09-04","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","07-后端与架构\u002Fask-questions-if-underspecified",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill ask-questions-if-underspecified",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill ask-questions-if-underspecified",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill ask-questions-if-underspecified","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fask-questions-if-underspecified\u002FSKILL.md",true,[],[50,57,62,69,76,83],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":58,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]