[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6RW2NZHHPR1N033QZST2W6K":3,"skill-same:01M6RW2NZHHPR1N033QZST2W6K":73},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6RW2NZHHPR1N033QZST2W6K","bmad-advanced-elicitation",null,"Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.","huangjia2019\u002Fsdd-in-action","huangjia2019","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F48795276?v=4","01M6RVB2A5TS40SQTN843K74XF","Jia Huang (黄佳)","01M6RVB2DWAKV004CDR8A4QXCY",175,"MIT","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.claude\u002Fskills\u002Fbmad-advanced-elicitation\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"bmad advanced elicitation","advanced","elicitation","bmad","when","push","critique method","socratic","pre-mortem","for","principles","output","deeper","first principles","use","improve","team","critique","first","red team","2026-11-10 10:12:30",false,"---\nname: bmad-advanced-elicitation\ndescription: 'Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.'\n---\n\n# Advanced Elicitation\n\n**Goal:** Push the LLM to reconsider, refine, and improve its recent output.\n\n---\n\n## CRITICAL LLM INSTRUCTIONS\n\n- **MANDATORY:** Execute ALL steps in the flow section IN EXACT ORDER\n- DO NOT skip steps or change the sequence\n- HALT immediately when halt-conditions are met\n- Each action within a step is a REQUIRED action to complete that step\n- Sections outside flow (validation, output, critical-context) provide essential context - review and apply throughout execution\n- **YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the `communication_language`**\n\n---\n\n## INTEGRATION (When Invoked Indirectly)\n\nWhen invoked from another prompt or process:\n\n1. Receive or review the current section content that was just generated\n2. Apply elicitation methods iteratively to enhance that specific content\n3. Return the enhanced version back when user selects 'x' to proceed and return back\n4. The enhanced content replaces the original section content in the output document\n\n---\n\n## FLOW\n\n### Step 1: Method Registry Loading\n\n**Action:** Load `.\u002Fmethods.csv` for elicitation methods. If party-mode may participate, resolve the agent roster via:\n\n```bash\npython3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_config.py --project-root {project-root} --key agents\n```\n\nThe resolver merges four layers in order: `_bmad\u002Fconfig.toml` (installer base, team-scoped), `_bmad\u002Fconfig.user.toml` (installer base, user-scoped), `_bmad\u002Fcustom\u002Fconfig.toml` (team overrides), and `_bmad\u002Fcustom\u002Fconfig.user.toml` (personal overrides). Each entry under `agents` is keyed by the agent's `code` and carries `name`, `title`, `icon`, `description`, `module`, and `team`.\n\n#### CSV Structure\n\n- **category:** Method grouping (core, structural, risk, etc.)\n- **method_name:** Display name for the method\n- **description:** Rich explanation of what the method does, when to use it, and why it's valuable\n- **output_pattern:** Flexible flow guide using arrows (e.g., \"analysis -> insights -> action\")\n\n#### Context Analysis\n\n- Use conversation history\n- Analyze: content type, complexity, stakeholder needs, risk level, and creative potential\n\n#### Smart Selection\n\n1. Analyze context: Content type, complexity, stakeholder needs, risk level, creative potential\n2. Parse descriptions: Understand each method's purpose from the rich descriptions in CSV\n3. Select 5 methods: Choose methods that best match the context based on their descriptions\n4. Balance approach: Include mix of foundational and specialized techniques as appropriate\n\n---\n\n### Step 2: Present Options and Handle Responses\n\n#### Display Format\n\n```\n**Advanced Elicitation Options**\n_If party mode is active, agents will join in._\nChoose a number (1-5), [r] to Reshuffle, [a] List All, or [x] to Proceed:\n\n1. [Method Name]\n2. [Method Name]\n3. [Method Name]\n4. [Method Name]\n5. [Method Name]\nr. Reshuffle the list with 5 new options\na. List all methods with descriptions\nx. Proceed \u002F No Further Actions\n```\n\n#### Response Handling\n\n**Case 1-5 (User selects a numbered method):**\n\n- Execute the selected method using its description from the CSV\n- Adapt the method's complexity and output format based on the current context\n- Apply the method creatively to the current section content being enhanced\n- Display the enhanced version showing what the method revealed or improved\n- **CRITICAL:** Ask the user if they would like to apply the changes to the doc (y\u002Fn\u002Fother) and HALT to await response.\n- **CRITICAL:** ONLY if Yes, apply the changes. IF No, discard your memory of the proposed changes. If any other reply, try best to follow the instructions given by the user.\n- **CRITICAL:** Re-present the same 1-5,r,x prompt to allow additional elicitations\n\n**Case r (Reshuffle):**\n\n- Select 5 random methods from methods.csv, present new list with same prompt format\n- When selecting, try to think and pick a diverse set of methods covering different categories and approaches, with 1 and 2 being potentially the most useful for the document or section being discovered\n\n**Case x (Proceed):**\n\n- Complete elicitation and proceed\n- Return the fully enhanced content back to the invoking skill\n- The enhanced content becomes the final version for that section\n- Signal completion back to the invoking skill to continue with next section\n\n**Case a (List All):**\n\n- List all methods with their descriptions from the CSV in a compact table\n- Allow user to select any method by name or number from the full list\n- After selection, execute the method as described in the Case 1-5 above\n\n**Case: Direct Feedback:**\n\n- Apply changes to current section content and re-present choices\n\n**Case: Multiple Numbers:**\n\n- Execute methods in sequence on the content, then re-offer choices\n\n---\n\n### Step 3: Execution Guidelines\n\n- **Method execution:** Use the description from CSV to understand and apply each method\n- **Output pattern:** Use the pattern as a flexible guide (e.g., \"paths -> evaluation -> selection\")\n- **Dynamic adaptation:** Adjust complexity based on content needs (simple to sophisticated)\n- **Creative application:** Interpret methods flexibly based on context while maintaining pattern consistency\n- Focus on actionable insights\n- **Stay relevant:** Tie elicitation to specific content being analyzed (the current section from the document being created unless user indicates otherwise)\n- **Identify personas:** For single or multi-persona methods, clearly identify viewpoints, and use party members if available in memory already\n- **Critical loop behavior:** Always re-offer the 1-5,r,a,x choices after each method execution\n- Continue until user selects 'x' to proceed with enhanced content, confirm or ask the user what should be accepted from the session\n- Each method application builds upon previous enhancements\n- **Content preservation:** Track all enhancements made during elicitation\n- **Iterative enhancement:** Each selected method (1-5) should:\n  1. Apply to the current enhanced version of the content\n  2. Show the improvements made\n  3. Return to the prompt for additional elicitations or completion\n","# Advanced Elicitation\n\n**Goal:** Push the LLM to reconsider, refine, and improve its recent output.\n\n---\n\n## CRITICAL LLM INSTRUCTIONS\n\n- **MANDATORY:** Execute ALL steps in the flow section IN EXACT ORDER\n- DO NOT skip steps or change the sequence\n- HALT immediately when halt-conditions are met\n- Each action within a step is a REQUIRED action to complete that step\n- Sections outside flow (validation, output, critical-context) provide essential context - review and apply throughout execution\n- **YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the `communication_language`**\n\n---\n\n## INTEGRATION (When Invoked Indirectly)\n\nWhen invoked from another prompt or process:\n\n1. Receive or review the current section content that was just generated\n2. Apply elicitation methods iteratively to enhance that specific content\n3. Return the enhanced version back when user selects 'x' to proceed and return back\n4. The enhanced content replaces the original section content in the output document\n\n---\n\n## FLOW\n\n### Step 1: Method Registry Loading\n\n**Action:** Load `.\u002Fmethods.csv` for elicitation methods. If party-mode may participate, resolve the agent roster via:\n\n```bash\npython3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_config.py --project-root {project-root} --key agents\n```\n\nThe resolver merges four layers in order: `_bmad\u002Fconfig.toml` (installer base, team-scoped), `_bmad\u002Fconfig.user.toml` (installer base, user-scoped), `_bmad\u002Fcustom\u002Fconfig.toml` (team overrides), and `_bmad\u002Fcustom\u002Fconfig.user.toml` (personal overrides). Each entry under `agents` is keyed by the agent's `code` and carries `name`, `title`, `icon`, `description`, `module`, and `team`.\n\n#### CSV Structure\n\n- **category:** Method grouping (core, structural, risk, etc.)\n- **method_name:** Display name for the method\n- **description:** Rich explanation of what the method does, when to use it, and why it's valuable\n- **output_pattern:** Flexible flow guide using arrows (e.g., \"analysis -> insights -> action\")\n\n#### Context Analysis\n\n- Use conversation history\n- Analyze: content type, complexity, stakeholder needs, risk level, and creative potential\n\n#### Smart Selection\n\n1. Analyze context: Content type, complexity, stakeholder needs, risk level, creative potential\n2. Parse descriptions: Understand each method's purpose from the rich descriptions in CSV\n3. Select 5 methods: Choose methods that best match the context based on their descriptions\n4. Balance approach: Include mix of foundational and specialized techniques as appropriate\n\n---\n\n### Step 2: Present Options and Handle Responses\n\n#### Display Format\n\n```\n**Advanced Elicitation Options**\n_If party mode is active, agents will join in._\nChoose a number (1-5), [r] to Reshuffle, [a] List All, or [x] to Proceed:\n\n1. [Method Name]\n2. [Method Name]\n3. [Method Name]\n4. [Method Name]\n5. [Method Name]\nr. Reshuffle the list with 5 new options\na. List all methods with descriptions\nx. Proceed \u002F No Further Actions\n```\n\n#### Response Handling\n\n**Case 1-5 (User selects a numbered method):**\n\n- Execute the selected method using its description from the CSV\n- Adapt the method's complexity and output format based on the current context\n- Apply the method creatively to the current section content being enhanced\n- Display the enhanced version showing what the method revealed or improved\n- **CRITICAL:** Ask the user if they would like to apply the changes to the doc (y\u002Fn\u002Fother) and HALT to await response.\n- **CRITICAL:** ONLY if Yes, apply the changes. IF No, discard your memory of the proposed changes. If any other reply, try best to follow the instructions given by the user.\n- **CRITICAL:** Re-present the same 1-5,r,x prompt to allow additional elicitations\n\n**Case r (Reshuffle):**\n\n- Select 5 random methods from methods.csv, present new list with same prompt format\n- When selecting, try to think and pick a diverse set of methods covering different categories and approaches, with 1 and 2 being potentially the most useful for the document or section being discovered\n\n**Case x (Proceed):**\n\n- Complete elicitation and proceed\n- Return the fully enhanced content back to the invoking skill\n- The enhanced content becomes the final version for that section\n- Signal completion back to the invoking skill to continue with next section\n\n**Case a (List All):**\n\n- List all methods with their descriptions from the CSV in a compact table\n- Allow user to select any method by name or number from the full list\n- After selection, execute the method as described in the Case 1-5 above\n\n**Case: Direct Feedback:**\n\n- Apply changes to current section content and re-present choices\n\n**Case: Multiple Numbers:**\n\n- Execute methods in sequence on the content, then re-offer choices\n\n---\n\n### Step 3: Execution Guidelines\n\n- **Method execution:** Use the description from CSV to understand and apply each method\n- **Output pattern:** Use the pattern as a flexible guide (e.g., \"paths -> evaluation -> selection\")\n- **Dynamic adaptation:** Adjust complexity based on content needs (simple to sophisticated)\n- **Creative application:** Interpret methods flexibly based on context while maintaining pattern consistency\n- Focus on actionable insights\n- **Stay relevant:** Tie elicitation to specific content being analyzed (the current section from the document being created unless user indicates otherwise)\n- **Identify personas:** For single or multi-persona methods, clearly identify viewpoints, and use party members if available in memory already\n- **Critical loop behavior:** Always re-offer the 1-5,r,a,x choices after each method execution\n- Continue until user selects 'x' to proceed with enhanced content, confirm or ask the user what should be accepted from the session\n- Each method application builds upon previous enhancements\n- **Content preservation:** Track all enhancements made during elicitation\n- **Iterative enhancement:** Each selected method (1-5) should:\n  1. Apply to the current enhanced version of the content\n  2. Show the improvements made\n  3. Return to the prompt for additional elicitations or completion\n",{"name":5,"description":7},"master","7ccc24b38f7cae09897ace41ebae14780250ac86","week3\u002Fcode\u002F.claude\u002Fskills\u002Fbmad-advanced-elicitation",60,"https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action","https:\u002F\u002Fgithub.com\u002Fhuangjia2019","https:\u002F\u002Fkage-ai.com","AI researcher at A*STAR | Author of Designing AI Agents (Manning) | Co-founder of ADPS","2026-08-25 16:05:09",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add huangjia2019\u002Fsdd-in-action --skill bmad-advanced-elicitation",{"tool":59,"command":60},"bunx","bunx skills add huangjia2019\u002Fsdd-in-action --skill bmad-advanced-elicitation",{"tool":62,"command":63},"pnpm","pnpm dlx skills add huangjia2019\u002Fsdd-in-action --skill bmad-advanced-elicitation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.claude\u002Fskills\u002Fbmad-advanced-elicitation\u002FSKILL.md",true,[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"methods.csv","ASSET","资产文件",9911,"https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.claude\u002Fskills\u002Fbmad-advanced-elicitation\u002Fmethods.csv",[74,95,110,126,141,156],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":39},"01M6WZBHKBA02YT2SHSACNJR91","openspec-verify-change","Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.opencode\u002Fskills\u002Fopenspec-verify-change\u002FSKILL.md",[],[81,82,83,84,85,23,86,87,88,89,90,33,91,92,93,94],"change","openspec verify change","verify","verify change","openspec","validate","complete","verify implementation","coherent","implementation","user","correct","artifacts","cli",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":39},"01M6WZBEQRPC45MDYVPMG17X89","openspec-sync-specs","Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.opencode\u002Fskills\u002Fopenspec-sync-specs\u002FSKILL.md",[],[102,103,85,81,104,94,105,23,106,107,108,109,33,91],"openspec sync specs","sync","spec","update","changes","with","main","delta",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":39},"01M6WZBA2QKBW10Z1ZYA4K2AV9","openspec-propose","Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.opencode\u002Fskills\u002Fopenspec-propose\u002FSKILL.md",[],[117,85,23,90,118,87,119,28,120,107,121,122,123,91,93,124,81,94,125,33],"openspec propose","build","describe","ready","get","proposal","generated","tasks","design",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":39},"01M6WZB3J0FJQJ0WSW9EK6447P","openspec-onboard","Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.opencode\u002Fskills\u002Fopenspec-onboard\u002FSKILL.md",[],[133,134,85,107,135,28,87,136,137,138,139,140,94],"openspec onboard","onboard","codebase","cycle","narration","work","onboarding","workflow",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":39},"01M6WZAZX6QSAV79619M68K8N1","openspec-new-change","Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.opencode\u002Fskills\u002Fopenspec-new-change\u002FSKILL.md",[],[81,85,148,149,150,33,151,152,91,153,154,140,94,155,23,107],"openspec new change","structured","artifact","new feature","fix","start","create","feature",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":39},"01M6WZAX8300NEPY3T1J8FRS3C","openspec-ff-change","Fast-forward through OpenSpec artifact creation. Use when the user wants to quickly create all artifacts needed for implementation without stepping through each one individually.","https:\u002F\u002Fgithub.com\u002Fhuangjia2019\u002Fsdd-in-action\u002Fblob\u002Fmaster\u002Fweek3\u002Fcode\u002F.opencode\u002Fskills\u002Fopenspec-ff-change\u002FSKILL.md",[],[81,163,85,94,23,28,164,150,90,33,91,165,93,154],"openspec ff change","creation","fast"]