[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M734C88E4N7ARF1519XV8EJ2":3,"skill-same:01M734C88E4N7ARF1519XV8EJ2":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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M734C88E4N7ARF1519XV8EJ2","idea-forge",null,"Expands a raw idea into a structured, research-backed spec in .productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md through interactive brainstorming, web research, business analysis, and multi-advisor debate. Use when the user has a feature idea and wants to explore and structure it before creating a PRD. Do not use for PRD creation, technical specifications, task breakdown, or code implementation.","itseffi\u002Fproductize","itseffi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F15998472?v=4","01M734C5RJ7CKRTPB3FX84VZV7","Effi","01M734C5S6B7FW62ZNWYBZ9GG7",3,"MIT","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: idea-forge\ndescription: Expands a raw idea into a structured, research-backed spec in .productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md through interactive brainstorming, web research, business analysis, and multi-advisor debate. Use when the user has a feature idea and wants to explore and structure it before creating a PRD. Do not use for PRD creation, technical specifications, task breakdown, or code implementation.\nargument-hint: [feature-idea]\n---\n\n# Idea Forge\n\nExpand a raw feature idea into a structured, research-backed spec that serves as the foundation for PRD creation.\n\n\u003CHARD-GATE>\nDo NOT write the idea file until ALL phases are complete and the user has approved the final draft.\nDo NOT skip the research phase — every idea MUST be enriched with market data.\nDo NOT skip user interactions — the user MUST participate in shaping the idea at every decision point.\nThis applies to EVERY idea regardless of perceived simplicity.\n\u003C\u002FHARD-GATE>\n\n## Asking Questions\n\nWhen this skill instructs you to ask the user a question, you MUST use your runtime's dedicated interactive question tool — the tool or function that presents a question to the user and **pauses execution until the user responds**. Do not output questions as plain assistant text and continue generating; always use the mechanism that blocks until the user has answered.\n\nIf your runtime does not provide such a tool, present the question as your complete message and stop generating. Do not answer your own question or proceed without user input.\n\n## Anti-Pattern: \"This Idea Is Too Simple For Full Research\"\n\nEvery idea goes through the full research and debate process. A single button, a minor workflow tweak, a configuration option — all of them. \"Simple\" ideas are where unexamined business assumptions cause the most rework downstream in the PRD. The process can be brief for genuinely simple ideas, but you MUST research and debate before writing.\n\n## Required Inputs\n\n- Feature idea or problem description.\n- Optional: existing `_idea.md` file for update mode.\n\n## Checklist\n\nYou MUST create a task for each phase and complete them in order:\n\n1. **Determine project & directory** — derive slug, create `.productize\u002Ftasks\u002F\u003Cslug>\u002F` and `adrs\u002F`\n2. **Understand the idea** — ask 3-6 targeted questions to refine scope and intent\n3. **Research the market** — web research for competitive intelligence and market data + codebase exploration\n4. **Analyze business viability** — adopt business analyst persona (`references\u002Fbusiness-analyst.md`) for KPIs, personas, and success metrics\n5. **Debate trade-offs** — run advisors session (`references\u002Fadvisors.md`) to challenge assumptions and surface risks\n6. **Scan for opportunities** — adopt product strategist persona (`references\u002Fproduct-strategist.md`) to suggest higher-leverage alternatives before committing to the draft\n7. **Draft the idea** — write using the canonical template from `references\u002Fidea-template.md`\n8. **Review with user** — present the draft, iterate until approved\n9. **Save the file** — write to `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`\n\n## Workflow\n\n1. Determine the project name and working directory.\n   - Derive the slug from the feature idea provided by the user.\n   - Use `.productize\u002Ftasks\u002F\u003Cslug>\u002F` as the target directory.\n   - If `_idea.md` already exists in the target directory, read it and operate in update mode.\n   - Read every existing canonical project knowledge document before shaping the idea:\n     - `.productize\u002Fproject\u002Fcontext.md`\n     - `.productize\u002Fproject\u002Fconventions.md`\n     - `.productize\u002Fproject\u002Farchitecture.md`\n     - `.productize\u002Fproject\u002Fdecisions.md`\n     - `.productize\u002Fproject\u002Fconstraints.md`\n   - Read `.productize\u002Fproject\u002Fmanual.md` when present for human-authored additions that are intentionally kept outside the generated read models.\n   - Use architecture, decisions, and constraints to assess feasibility and product boundaries without copying implementation detail into the idea artifact.\n   - If the directory does not exist, create it.\n   - Create `.productize\u002Ftasks\u002F\u003Cslug>\u002Fadrs\u002F` directory if it does not exist.\n\n2. Understand the idea through targeted questions.\n   - Follow the question protocol in `references\u002Fquestion-protocol.md`.\n   - Ask 3-6 questions to refine scope, intent, target user, and success criteria.\n   - Ask only one question per message.\n   - Prefer multiple-choice questions when the options can be predetermined.\n   - Include a fallback option (e.g., \"D) Other — describe\") for flexibility.\n   - Complete at least one full clarification round before proceeding to research.\n\n3. Discover context through parallel research.\n   - Seed codebase exploration with all five canonical project knowledge documents listed in step 1, plus `manual.md` when present, and verify relevant facts against the current repository.\n   - Spawn one Agent tool call to explore the codebase for relevant patterns, existing features, and architecture.\n   - Spawn a second Agent tool call to perform 3-7 web searches for market data and competitive intelligence.\n   - Use any available web search tools. If none are available, note the limitation and proceed with codebase exploration only.\n   - Vary query angles across at least 3 searches:\n     1. **Competitive landscape:** `\"{feature category} tools for {domain} 2025 2026\"`\n     2. **Market data:** `\"{problem} market size OR adoption rate OR statistics\"`\n     3. **Technical approach:** `\"{technical solution} architecture OR implementation best practices\"`\n     4. **User expectations:** `\"{feature} UX patterns OR user experience best practices\"` (if relevant)\n     5. **Pricing\u002Fcost:** `\"{service\u002FAPI} pricing OR cost comparison 2025 2026\"` (if relevant)\n   - After both agents complete, merge findings and present a research summary to the user:\n\n     ```\n     **Codebase findings:**\n     - {Relevant existing feature\u002Fpattern}\n     - {Integration point}\n\n     **Market research:**\n     - {Competitor 1}: {what it does}\n     - {Competitor 2}: {what it does}\n     - **Potential differentiator:** {what we can do differently}\n     - **Relevant data:** {statistics found}\n     ```\n\n4. Analyze business viability.\n   - Read `references\u002Fbusiness-analyst.md` and adopt the business analyst persona to evaluate the idea with the refined context from steps 2-3.\n   - Deliver: KPI framework, success metrics, personas, and viability assessment.\n   - Define 3-6 KPIs with measurable targets.\n   - Identify success criteria and risk factors.\n   - Assess viability based on research findings.\n   - Score the feature on these 6 criteria:\n\n     | Criteria            | Question                                            | Score                     |\n     | ------------------- | --------------------------------------------------- | ------------------------- |\n     | **Impact**          | How much more valuable does this make the product?  | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Reach**           | What % of users would this affect?                  | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Frequency**       | How often would users encounter this value?         | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Differentiation** | Does this set us apart or just match competitors?   | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Defensibility**   | Is this easy to copy or does it compound over time? | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Feasibility**     | Can we actually build this?                         | Must do\u002FStrong\u002FMaybe\u002FPass |\n\n   - This evaluation informs the idea's priority and feeds into the advisors debate.\n   - Present the analysis to the user before proceeding.\n\n5. Debate trade-offs through multi-advisor review.\n   - Read `references\u002Fadvisors.md` and run an advisor session in embedded mode to debate:\n     - **Scope:** Is the V1 scope right? Too much? Too little?\n     - **Priority:** Where should this rank vs other planned features?\n     - **Technical approach:** Are there simpler alternatives?\n     - **Risks:** What could go wrong? What are the hidden dependencies?\n     - **10x Challenge:** Is this truly high-leverage or just incremental? Is there a more ambitious version worth exploring? Could a simpler version deliver disproportionate value?\n   - Follow the advisors session structure from the reference: Opening Statements, Tensions & Debate, Position Evolution, Synthesis.\n   - Use real reusable subagents through `run_agent`. Do NOT simulate the advisors inline. The canonical advisor roster is: `pragmatic-engineer`, `architect-advisor`, `security-advocate`, `product-mind`, `stress-tester`, `the-thinker`.\n   - If `run_agent` is unavailable or the advisors archetypes cannot be resolved, stop with an actionable error that tells the user to run `productize setup`.\n   - Select 3-5 advisors based on dilemma complexity.\n   - Extract: key trade-offs, recommended approach, items for out-of-scope (V1), optional stretch goal for V2+.\n   - After the debate, create an ADR for the scope decision:\n     - Read `references\u002Fadr-template.md`.\n     - Determine the next ADR number by listing existing files in `.productize\u002Ftasks\u002F\u003Cslug>\u002Fadrs\u002F`.\n     - Fill the template: recommended scope as \"Decision\", alternatives as \"Alternatives Considered\", trade-offs as \"Consequences\". Set `kind` to `scope`, `status` to `accepted`, `date` to today, and `supersedes` to a YAML list of ADR references replaced by this decision (for example, `ADR-001`) or `[]`. Keep the Markdown Status and Date sections aligned with that metadata.\n     - When `supersedes` is non-empty, update each replaced ADR's metadata status to `superseded` and its Markdown Status to `Superseded by ADR-NNN`, naming the new ADR.\n     - Write the ADR to `.productize\u002Ftasks\u002F\u003Cslug>\u002Fadrs\u002Fadr-NNN.md` (zero-padded 3-digit number).\n\n6. Scan for opportunities.\n   - Read `references\u002Fproduct-strategist.md` and adopt the product strategist persona.\n   - Using all context gathered so far (research, business analysis, advisors output), evaluate whether the original idea is the highest-leverage move.\n   - Suggest up to 3 alternatives spanning different scales:\n     - One more ambitious version (what if we thought bigger?)\n     - One simpler version (what if we stripped it to the essence?)\n     - One adjacent opportunity (what related problem could we solve instead?)\n   - Score each alternative using the evaluation framework from the reference.\n   - Present the opportunity scan to the user with a clear recommendation:\n     - \"Here is the opportunity scan. I recommend proceeding with [Original \u002F Alternative N \u002F Hybrid]. Which direction do you prefer?\"\n     - A) Proceed with the original idea\n     - B) Adopt alternative N (specify which)\n     - C) Hybrid approach (combine elements)\n     - D) Other — describe\n   - Incorporate the chosen direction into the draft. If the user picks an alternative, update the feature scope accordingly before proceeding.\n\n7. Draft the idea.\n   - Read `references\u002Fidea-template.md` and fill every applicable section with gathered context.\n   - Include an \"Architecture Decision Records\" section listing all ADRs created during this session.\n   - Mandatory sections (ALWAYS include): Overview, Problem (enriched with market data), Core Features, KPIs, Feature Assessment, Advisors Insights, Out of Scope (V1), Architecture Decision Records, Open Questions.\n   - Optional sections (include when relevant): Summary\u002FDifferentiator, Integration with Existing Features, Sub-Features, Cost Estimate.\n   - Prefer active voice, omit needless words, use definite and specific language over vague generalities. Every sentence should earn its place.\n   - Language: **English**. Tone: clear, technical, consistent with existing project artifacts.\n   - Tables: use markdown tables for structured data. Features: minimum 3, maximum 10, ordered by priority. KPIs: minimum 3, maximum 6, with numeric targets. Exclusions: minimum 3 items with justification.\n   - Present the complete draft to the user for review.\n\n8. Review with the user.\n   - Present the draft and ask using the interactive question tool:\n     - \"Here is the idea draft. Please review and let me know:\"\n     - A) Approved — save as is\n     - B) Adjust specific sections (tell me which ones)\n     - C) Rewrite section X (tell me what to change)\n     - D) Discard and start over\n   - If B or C: make the changes and present again.\n   - If D: go back to step 2.\n\n9. Save the idea file.\n   - Generate the slug: kebab-case, 2-5 words, descriptive (e.g., `smart-thumbnail-suggestions`).\n   - Ask the user to confirm the filename using the interactive question tool:\n     - \"Save as `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`? (A) Yes \u002F (B) Different name\"\n   - Write the file to `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`.\n   - Confirm the file path to the user.\n   - Remind the user that the next step is to create a PRD using `create-prd` from this idea.\n\n## Process Flow\n\n```dot\ndigraph idea_forge {\n    \"Determine project & directory\" [shape=box];\n    \"Ask 3-6 targeted questions (one at a time)\" [shape=box];\n    \"Discover context (codebase + web)\" [shape=box];\n    \"Analyze business viability\" [shape=box];\n    \"Debate trade-offs (advisors)\" [shape=box];\n    \"Create ADR for scope decision\" [shape=box];\n    \"Opportunity scan (product strategist)\" [shape=box];\n    \"User picks direction?\" [shape=diamond];\n    \"Draft idea (canonical template)\" [shape=box];\n    \"User approves draft?\" [shape=diamond];\n    \"Save _idea.md\" [shape=doublecircle];\n\n    \"Determine project & directory\" -> \"Ask 3-6 targeted questions (one at a time)\";\n    \"Ask 3-6 targeted questions (one at a time)\" -> \"Discover context (codebase + web)\";\n    \"Discover context (codebase + web)\" -> \"Analyze business viability\";\n    \"Analyze business viability\" -> \"Debate trade-offs (advisors)\";\n    \"Debate trade-offs (advisors)\" -> \"Create ADR for scope decision\";\n    \"Create ADR for scope decision\" -> \"Opportunity scan (product strategist)\";\n    \"Opportunity scan (product strategist)\" -> \"User picks direction?\";\n    \"User picks direction?\" -> \"Draft idea (canonical template)\" [label=\"confirmed\"];\n    \"Draft idea (canonical template)\" -> \"User approves draft?\";\n    \"User approves draft?\" -> \"Draft idea (canonical template)\" [label=\"no, revise\"];\n    \"User approves draft?\" -> \"Save _idea.md\" [label=\"approved\"];\n}\n```\n\n## Error Handling\n\n- If the user provides insufficient context to complete a section, note it in the Open Questions section rather than guessing.\n- If web research tools (Exa MCP, web search) are unavailable, proceed with codebase exploration only and note the limitation.\n- If the reference files for business analyst or advisors are missing, perform the analysis and debate inline using the guidelines described in phases 4 and 5.\n- If the target directory cannot be created, stop and report the filesystem error.\n- If operating in update mode, preserve sections the user has not asked to change.\n\n## Key Principles\n\n- **One question at a time** — Do not overwhelm with multiple questions in a single message\n- **Multiple choice preferred** — Always offer options before open-ended questions\n- **Research before writing** — Never write an idea without market data\n- **Incremental validation** — Present analysis and draft for approval before saving\n- **Business focus only** — Never ask about implementation; that belongs in TechSpec\n- **Scope discipline** — Aggressively trim scope to a viable V1\n- **Pipeline awareness** — The idea feeds into `create-prd`; focus on WHAT and WHY, not HOW\n- **Template compliance** — Every idea MUST follow the canonical template\n- **Language consistency** — Write all idea content in English\n","# Idea Forge\n\nExpand a raw feature idea into a structured, research-backed spec that serves as the foundation for PRD creation.\n\n\u003CHARD-GATE>\nDo NOT write the idea file until ALL phases are complete and the user has approved the final draft.\nDo NOT skip the research phase — every idea MUST be enriched with market data.\nDo NOT skip user interactions — the user MUST participate in shaping the idea at every decision point.\nThis applies to EVERY idea regardless of perceived simplicity.\n\u003C\u002FHARD-GATE>\n\n## Asking Questions\n\nWhen this skill instructs you to ask the user a question, you MUST use your runtime's dedicated interactive question tool — the tool or function that presents a question to the user and **pauses execution until the user responds**. Do not output questions as plain assistant text and continue generating; always use the mechanism that blocks until the user has answered.\n\nIf your runtime does not provide such a tool, present the question as your complete message and stop generating. Do not answer your own question or proceed without user input.\n\n## Anti-Pattern: \"This Idea Is Too Simple For Full Research\"\n\nEvery idea goes through the full research and debate process. A single button, a minor workflow tweak, a configuration option — all of them. \"Simple\" ideas are where unexamined business assumptions cause the most rework downstream in the PRD. The process can be brief for genuinely simple ideas, but you MUST research and debate before writing.\n\n## Required Inputs\n\n- Feature idea or problem description.\n- Optional: existing `_idea.md` file for update mode.\n\n## Checklist\n\nYou MUST create a task for each phase and complete them in order:\n\n1. **Determine project & directory** — derive slug, create `.productize\u002Ftasks\u002F\u003Cslug>\u002F` and `adrs\u002F`\n2. **Understand the idea** — ask 3-6 targeted questions to refine scope and intent\n3. **Research the market** — web research for competitive intelligence and market data + codebase exploration\n4. **Analyze business viability** — adopt business analyst persona (`references\u002Fbusiness-analyst.md`) for KPIs, personas, and success metrics\n5. **Debate trade-offs** — run advisors session (`references\u002Fadvisors.md`) to challenge assumptions and surface risks\n6. **Scan for opportunities** — adopt product strategist persona (`references\u002Fproduct-strategist.md`) to suggest higher-leverage alternatives before committing to the draft\n7. **Draft the idea** — write using the canonical template from `references\u002Fidea-template.md`\n8. **Review with user** — present the draft, iterate until approved\n9. **Save the file** — write to `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`\n\n## Workflow\n\n1. Determine the project name and working directory.\n   - Derive the slug from the feature idea provided by the user.\n   - Use `.productize\u002Ftasks\u002F\u003Cslug>\u002F` as the target directory.\n   - If `_idea.md` already exists in the target directory, read it and operate in update mode.\n   - Read every existing canonical project knowledge document before shaping the idea:\n     - `.productize\u002Fproject\u002Fcontext.md`\n     - `.productize\u002Fproject\u002Fconventions.md`\n     - `.productize\u002Fproject\u002Farchitecture.md`\n     - `.productize\u002Fproject\u002Fdecisions.md`\n     - `.productize\u002Fproject\u002Fconstraints.md`\n   - Read `.productize\u002Fproject\u002Fmanual.md` when present for human-authored additions that are intentionally kept outside the generated read models.\n   - Use architecture, decisions, and constraints to assess feasibility and product boundaries without copying implementation detail into the idea artifact.\n   - If the directory does not exist, create it.\n   - Create `.productize\u002Ftasks\u002F\u003Cslug>\u002Fadrs\u002F` directory if it does not exist.\n\n2. Understand the idea through targeted questions.\n   - Follow the question protocol in `references\u002Fquestion-protocol.md`.\n   - Ask 3-6 questions to refine scope, intent, target user, and success criteria.\n   - Ask only one question per message.\n   - Prefer multiple-choice questions when the options can be predetermined.\n   - Include a fallback option (e.g., \"D) Other — describe\") for flexibility.\n   - Complete at least one full clarification round before proceeding to research.\n\n3. Discover context through parallel research.\n   - Seed codebase exploration with all five canonical project knowledge documents listed in step 1, plus `manual.md` when present, and verify relevant facts against the current repository.\n   - Spawn one Agent tool call to explore the codebase for relevant patterns, existing features, and architecture.\n   - Spawn a second Agent tool call to perform 3-7 web searches for market data and competitive intelligence.\n   - Use any available web search tools. If none are available, note the limitation and proceed with codebase exploration only.\n   - Vary query angles across at least 3 searches:\n     1. **Competitive landscape:** `\"{feature category} tools for {domain} 2025 2026\"`\n     2. **Market data:** `\"{problem} market size OR adoption rate OR statistics\"`\n     3. **Technical approach:** `\"{technical solution} architecture OR implementation best practices\"`\n     4. **User expectations:** `\"{feature} UX patterns OR user experience best practices\"` (if relevant)\n     5. **Pricing\u002Fcost:** `\"{service\u002FAPI} pricing OR cost comparison 2025 2026\"` (if relevant)\n   - After both agents complete, merge findings and present a research summary to the user:\n\n     ```\n     **Codebase findings:**\n     - {Relevant existing feature\u002Fpattern}\n     - {Integration point}\n\n     **Market research:**\n     - {Competitor 1}: {what it does}\n     - {Competitor 2}: {what it does}\n     - **Potential differentiator:** {what we can do differently}\n     - **Relevant data:** {statistics found}\n     ```\n\n4. Analyze business viability.\n   - Read `references\u002Fbusiness-analyst.md` and adopt the business analyst persona to evaluate the idea with the refined context from steps 2-3.\n   - Deliver: KPI framework, success metrics, personas, and viability assessment.\n   - Define 3-6 KPIs with measurable targets.\n   - Identify success criteria and risk factors.\n   - Assess viability based on research findings.\n   - Score the feature on these 6 criteria:\n\n     | Criteria            | Question                                            | Score                     |\n     | ------------------- | --------------------------------------------------- | ------------------------- |\n     | **Impact**          | How much more valuable does this make the product?  | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Reach**           | What % of users would this affect?                  | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Frequency**       | How often would users encounter this value?         | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Differentiation** | Does this set us apart or just match competitors?   | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Defensibility**   | Is this easy to copy or does it compound over time? | Must do\u002FStrong\u002FMaybe\u002FPass |\n     | **Feasibility**     | Can we actually build this?                         | Must do\u002FStrong\u002FMaybe\u002FPass |\n\n   - This evaluation informs the idea's priority and feeds into the advisors debate.\n   - Present the analysis to the user before proceeding.\n\n5. Debate trade-offs through multi-advisor review.\n   - Read `references\u002Fadvisors.md` and run an advisor session in embedded mode to debate:\n     - **Scope:** Is the V1 scope right? Too much? Too little?\n     - **Priority:** Where should this rank vs other planned features?\n     - **Technical approach:** Are there simpler alternatives?\n     - **Risks:** What could go wrong? What are the hidden dependencies?\n     - **10x Challenge:** Is this truly high-leverage or just incremental? Is there a more ambitious version worth exploring? Could a simpler version deliver disproportionate value?\n   - Follow the advisors session structure from the reference: Opening Statements, Tensions & Debate, Position Evolution, Synthesis.\n   - Use real reusable subagents through `run_agent`. Do NOT simulate the advisors inline. The canonical advisor roster is: `pragmatic-engineer`, `architect-advisor`, `security-advocate`, `product-mind`, `stress-tester`, `the-thinker`.\n   - If `run_agent` is unavailable or the advisors archetypes cannot be resolved, stop with an actionable error that tells the user to run `productize setup`.\n   - Select 3-5 advisors based on dilemma complexity.\n   - Extract: key trade-offs, recommended approach, items for out-of-scope (V1), optional stretch goal for V2+.\n   - After the debate, create an ADR for the scope decision:\n     - Read `references\u002Fadr-template.md`.\n     - Determine the next ADR number by listing existing files in `.productize\u002Ftasks\u002F\u003Cslug>\u002Fadrs\u002F`.\n     - Fill the template: recommended scope as \"Decision\", alternatives as \"Alternatives Considered\", trade-offs as \"Consequences\". Set `kind` to `scope`, `status` to `accepted`, `date` to today, and `supersedes` to a YAML list of ADR references replaced by this decision (for example, `ADR-001`) or `[]`. Keep the Markdown Status and Date sections aligned with that metadata.\n     - When `supersedes` is non-empty, update each replaced ADR's metadata status to `superseded` and its Markdown Status to `Superseded by ADR-NNN`, naming the new ADR.\n     - Write the ADR to `.productize\u002Ftasks\u002F\u003Cslug>\u002Fadrs\u002Fadr-NNN.md` (zero-padded 3-digit number).\n\n6. Scan for opportunities.\n   - Read `references\u002Fproduct-strategist.md` and adopt the product strategist persona.\n   - Using all context gathered so far (research, business analysis, advisors output), evaluate whether the original idea is the highest-leverage move.\n   - Suggest up to 3 alternatives spanning different scales:\n     - One more ambitious version (what if we thought bigger?)\n     - One simpler version (what if we stripped it to the essence?)\n     - One adjacent opportunity (what related problem could we solve instead?)\n   - Score each alternative using the evaluation framework from the reference.\n   - Present the opportunity scan to the user with a clear recommendation:\n     - \"Here is the opportunity scan. I recommend proceeding with [Original \u002F Alternative N \u002F Hybrid]. Which direction do you prefer?\"\n     - A) Proceed with the original idea\n     - B) Adopt alternative N (specify which)\n     - C) Hybrid approach (combine elements)\n     - D) Other — describe\n   - Incorporate the chosen direction into the draft. If the user picks an alternative, update the feature scope accordingly before proceeding.\n\n7. Draft the idea.\n   - Read `references\u002Fidea-template.md` and fill every applicable section with gathered context.\n   - Include an \"Architecture Decision Records\" section listing all ADRs created during this session.\n   - Mandatory sections (ALWAYS include): Overview, Problem (enriched with market data), Core Features, KPIs, Feature Assessment, Advisors Insights, Out of Scope (V1), Architecture Decision Records, Open Questions.\n   - Optional sections (include when relevant): Summary\u002FDifferentiator, Integration with Existing Features, Sub-Features, Cost Estimate.\n   - Prefer active voice, omit needless words, use definite and specific language over vague generalities. Every sentence should earn its place.\n   - Language: **English**. Tone: clear, technical, consistent with existing project artifacts.\n   - Tables: use markdown tables for structured data. Features: minimum 3, maximum 10, ordered by priority. KPIs: minimum 3, maximum 6, with numeric targets. Exclusions: minimum 3 items with justification.\n   - Present the complete draft to the user for review.\n\n8. Review with the user.\n   - Present the draft and ask using the interactive question tool:\n     - \"Here is the idea draft. Please review and let me know:\"\n     - A) Approved — save as is\n     - B) Adjust specific sections (tell me which ones)\n     - C) Rewrite section X (tell me what to change)\n     - D) Discard and start over\n   - If B or C: make the changes and present again.\n   - If D: go back to step 2.\n\n9. Save the idea file.\n   - Generate the slug: kebab-case, 2-5 words, descriptive (e.g., `smart-thumbnail-suggestions`).\n   - Ask the user to confirm the filename using the interactive question tool:\n     - \"Save as `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`? (A) Yes \u002F (B) Different name\"\n   - Write the file to `.productize\u002Ftasks\u002F\u003Cslug>\u002F_idea.md`.\n   - Confirm the file path to the user.\n   - Remind the user that the next step is to create a PRD using `create-prd` from this idea.\n\n## Process Flow\n\n```dot\ndigraph idea_forge {\n    \"Determine project & directory\" [shape=box];\n    \"Ask 3-6 targeted questions (one at a time)\" [shape=box];\n    \"Discover context (codebase + web)\" [shape=box];\n    \"Analyze business viability\" [shape=box];\n    \"Debate trade-offs (advisors)\" [shape=box];\n    \"Create ADR for scope decision\" [shape=box];\n    \"Opportunity scan (product strategist)\" [shape=box];\n    \"User picks direction?\" [shape=diamond];\n    \"Draft idea (canonical template)\" [shape=box];\n    \"User approves draft?\" [shape=diamond];\n    \"Save _idea.md\" [shape=doublecircle];\n\n    \"Determine project & directory\" -> \"Ask 3-6 targeted questions (one at a time)\";\n    \"Ask 3-6 targeted questions (one at a time)\" -> \"Discover context (codebase + web)\";\n    \"Discover context (codebase + web)\" -> \"Analyze business viability\";\n    \"Analyze business viability\" -> \"Debate trade-offs (advisors)\";\n    \"Debate trade-offs (advisors)\" -> \"Create ADR for scope decision\";\n    \"Create ADR for scope decision\" -> \"Opportunity scan (product strategist)\";\n    \"Opportunity scan (product strategist)\" -> \"User picks direction?\";\n    \"User picks direction?\" -> \"Draft idea (canonical template)\" [label=\"confirmed\"];\n    \"Draft idea (canonical template)\" -> \"User approves draft?\";\n    \"User approves draft?\" -> \"Draft idea (canonical template)\" [label=\"no, revise\"];\n    \"User approves draft?\" -> \"Save _idea.md\" [label=\"approved\"];\n}\n```\n\n## Error Handling\n\n- If the user provides insufficient context to complete a section, note it in the Open Questions section rather than guessing.\n- If web research tools (Exa MCP, web search) are unavailable, proceed with codebase exploration only and note the limitation.\n- If the reference files for business analyst or advisors are missing, perform the analysis and debate inline using the guidelines described in phases 4 and 5.\n- If the target directory cannot be created, stop and report the filesystem error.\n- If operating in update mode, preserve sections the user has not asked to change.\n\n## Key Principles\n\n- **One question at a time** — Do not overwhelm with multiple questions in a single message\n- **Multiple choice preferred** — Always offer options before open-ended questions\n- **Research before writing** — Never write an idea without market data\n- **Incremental validation** — Present analysis and draft for approval before saving\n- **Business focus only** — Never ask about implementation; that belongs in TechSpec\n- **Scope discipline** — Aggressively trim scope to a viable V1\n- **Pipeline awareness** — The idea feeds into `create-prd`; focus on WHAT and WHY, not HOW\n- **Template compliance** — Every idea MUST follow the canonical template\n- **Language consistency** — Write all idea content in English\n",{"name":5,"description":7,"argument-hint":24},[25],"feature-idea","main","f177680a573a242a81bd0a776f9681f620e6d74c","extensions\u002Fidea-forge\u002Fskills\u002Fidea-forge",0,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize","https:\u002F\u002Fgithub.com\u002Fitseffi","2026-08-07 20:07:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add itseffi\u002Fproductize --skill idea-forge",{"tool":39,"command":40},"bunx","bunx skills add itseffi\u002Fproductize --skill idea-forge",{"tool":42,"command":43},"pnpm","pnpm dlx skills add itseffi\u002Fproductize --skill idea-forge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002FSKILL.md",true,[47,53,57,61,65,69],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fadr-template.md","REFERENCE","参考文档",1305,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002Freferences\u002Fadr-template.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fadvisors.md",5312,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002Freferences\u002Fadvisors.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fbusiness-analyst.md",4053,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002Freferences\u002Fbusiness-analyst.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fidea-template.md",4592,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002Freferences\u002Fidea-template.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fproduct-strategist.md",5516,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002Freferences\u002Fproduct-strategist.md",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fquestion-protocol.md",3612,"https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fextensions\u002Fidea-forge\u002Fskills\u002Fidea-forge\u002Freferences\u002Fquestion-protocol.md",[74,81,88,95,102,109],{"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":19},"01M7357QB5M87V95F82E73V2TF","workflow-memory","Maintains workflow-scoped task memory for Productize runs using .productize\u002Ftasks\u002F\u003Cname>\u002Fmemory\u002F files. Use when a task prompt provides workflow memory paths and requires the agent to read, update, compact, and promote durable context across PRD task executions. Do not use for PR review remediation, global user preferences, or programmatic event-log summarization.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-memory\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7357K97HSYEHAQTW5ZKM4CE","review-round","Performs a comprehensive code review of a PRD implementation and generates a review round directory with issue files compatible with fix-reviews. Use when reviewing implemented PRD tasks, creating a manual review round without an external provider, or performing a quality audit of code changes. Do not use for fetching reviews from external providers, fixing existing review issues, executing PRD tasks, or editing source code.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Freview-round\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7357F2NZE5NSYM2SJXEGBFZ","productize","Productize root skill for building, shipping, operating, and growing AI products inside a coding harness. Routes work across thesis framing, discovery, research, positioning, finance, decision making, requirements, design, metrics, AI-builder execution, code implementation, verification, stakeholder narratives, growth, launch, operation, and learning workflows. Use when the user wants to build a product from zero, improve an existing product, or needs product work that spans multiple lifecycle stages before code, launch, operation, or growth execution.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize\u002FSKILL.md",[],[],{"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":19},"01M7357B48F8MK86EQF135FJQ6","productize-wwas","Why-What-Acceptance. Use when writing backlog items in Why-What-Acceptance format, breaking features into independent valuable work, or adding strategic context to delivery items.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-wwas\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M735783CDA9MQ0SPR9X6QZSE","productize-writing-plans","Create comprehensive implementation plans with bite-sized tasks. Use when you have requirements before touching code.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-writing-plans\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M735750V5Q6WRBX1ZFGNRMEB","productize-write-spec","Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea into a structured document, scoping goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into phases.","https:\u002F\u002Fgithub.com\u002Fitseffi\u002Fproductize\u002Fblob\u002Fmain\u002Fskills\u002Fproductize-write-spec\u002FSKILL.md",[],[]]