[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AF29P95SDCCHAE9KGWBAMC":3,"skill-same:01M7AF29P95SDCCHAE9KGWBAMC":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7AF29P95SDCCHAE9KGWBAMC","product-spec-skill",null,"Create feature specifications or PRDs from vague ideas via structured clarifying questions and scope management. Use when defining a new feature, writing a brief for engineering, or turning stakeholder requests into actionable specs. Trigger with \"write a spec for\", \"help me spec this out\", \"PRD for [feature]\".","innFactory-AI\u002Fcompany-ai-stack-skills","innFactory-AI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F165681221?v=4","01M7AEC27VD0D1QX2XBX441MDW","innFactory AI","01M7AEC28G25HQ9H9SN58MNV27",0,"MIT","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fproduct-management\u002Fproduct-spec-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: product-spec-skill\ndescription: Create feature specifications or PRDs from vague ideas via structured clarifying questions and scope management. Use when defining a new feature, writing a brief for engineering, or turning stakeholder requests into actionable specs. Trigger with \"write a spec for\", \"help me spec this out\", \"PRD for [feature]\".\n---\n\n# Product Spec Skill\n\nTurn ambiguous product ideas into clear, engineering-ready specifications. Covers clarification workflows, scope management, requirement structuring, and risk identification so reliable PRDs result. The inputs come from you, a connected MCP source, or companyRAG collections.\n\n## Where the Data Comes From\n\n| Source | What It Adds |\n| --- | --- |\n| **Project tracker via MCP** (e.g. Jira, Linear, Asana, Shortcut) | Existing tickets, epics, or OKRs for context; push finalised stories back |\n| **Design tool via MCP** (e.g. Figma, Miro) | Wireframes, user flows, design-system constraints |\n| **companyRAG collections** | Existing specs, prior research, competitive context, architecture docs |\n| **companyRAG \u002F file upload** | Confluence pages, discovery notes, technical assessments |\n\n> **No connected source?** Provide the data in chat or upload the relevant files — the skill works the same way.\n\n## Specification Workflow\n\nExecute these five phases sequentially. Each phase has a gate — do not advance until the gate condition is met.\n\n### Phase 1: Clarify the Problem\n\nBefore writing a single requirement, establish what problem this feature solves and for whom. Most spec failures trace back to skipping this phase.\n\n**Clarification question sequence** (ask in this order, adapt phrasing to context):\n\n1. Problem statement: \"What problem does this solve, and how do you know it's a real problem?\" — Look for evidence: user research, support tickets, churn data, sales feedback. If the answer is \"stakeholder X wants it,\" probe for the underlying problem.\n2. Affected users: \"Who experiences this problem, and how often?\" — Establish the user segment, frequency, and severity. A problem affecting 5% of users daily may matter more than one affecting 50% annually.\n3. Current workaround: \"How do users solve this today without the feature?\" — Workarounds reveal the true workflow, expectations, and pain intensity. No workaround may indicate low urgency.\n4. Business context: \"Why solve this now? What changes if we don't?\" — Connects to OKRs, revenue targets, competitive pressure, or regulatory deadlines. If the answer is vague, the priority is uncertain.\n5. Prior attempts: \"Has this been tried before? What happened?\" — Prevents re-treading failed approaches and surfaces organisational constraints.\n\n**Gate**: A problem statement exists that names the user, the pain, and the evidence. If the user cannot articulate the problem, help them formulate one before proceeding — do NOT skip to solution design.\n\n### Phase 2: Define Scope\n\nScope creep is the primary cause of spec failure. Use explicit in\u002Fout boundaries and a phasing framework.\n\n**Scope definition steps**:\n\n1. Solution sketch: Ask the user to describe their ideal solution in 2-3 sentences — maximum. This forces prioritisation before detail.\n2. In-scope \u002F out-of-scope table: For every capability mentioned, classify explicitly:\n\n| Capability | In Scope (v1) | Future (v2+) | Out of Scope | Rationale |\n| --- | --- | --- | --- | --- |\n| [capability] | ✓ \u002F — | — \u002F ✓ | — \u002F ✓ | [why this classification] |\n\n1. **MoSCoW classification** for in-scope items:   - Must have: Feature is broken without it. Ship-blocking.   - Should have: Significant value, strong expectation, but a workaround exists.   - Could have: Nice-to-have if capacity allows. First to cut.   - Won't have (this time): Explicitly deferred. Documenting \"won't\" prevents scope drift.\n2. **Scope anchoring question**: \"If we could only ship ONE thing from this spec, what would it be?\" — The answer is the non-negotiable core. Everything else is relative priority around it.\n\n**Gate**: An in\u002Fout table exists, MoSCoW classification is applied, and the user has confirmed the scope boundary.\n\n### Phase 3: Write Spec Sections\n\nStructure the PRD using the output template below. For each section, apply these writing principles:\n\n- Requirements over solutions: Describe WHAT and WHY, not HOW. \"Users must be able to filter by date range\" not \"Add a date-picker component.\"\n- Testable acceptance criteria: Every requirement must have a verifiable condition. \"The page loads\" is not testable. \"The page renders the first 20 results within 2 seconds on a 3G connection\" is.\n- Edge cases upfront: For each requirement, ask \"What happens when...?\" — empty states, error conditions, permission boundaries, data limits, concurrent access.\n- One requirement, one statement: Compound requirements (\"the system should X and Y\") hide complexity and create ambiguous acceptance criteria. Split them.\n\n**Requirement decomposition pattern**:\n\n```\nREQUIREMENT: [Clear, single-purpose statement]\n  User story:        As a [role], I want [capability] so that [outcome]\n  Acceptance criteria:\n    GIVEN [context]\n    WHEN  [action]\n    THEN  [observable result]\n  Edge cases:\n    - [What if input is empty\u002Fmalformed\u002Fat limit?]\n    - [What if user lacks permission?]\n    - [What if dependent service is unavailable?]\n  Dependencies:      [Other requirements or systems this depends on]\n  Open questions:    [Unresolved decisions — owner and deadline for resolution]\n```\n\n### Phase 4: Identify Risks\n\nSystematically surface risks before engineering begins. Categorise using:\n\n| Risk Category | What to Look For | Mitigation Pattern |\n| --- | --- | --- |\n| **Technical** | New technology, integration complexity, performance requirements, data migration | Spike\u002Fprototype first, define fallback approach |\n| **Scope** | Ambiguous requirements, undefined edge cases, implicit assumptions | Tighten acceptance criteria, add explicit constraints |\n| **Dependency** | External teams, third-party APIs, platform approvals, shared infrastructure | Identify critical path, establish SLAs or deadlines with owners |\n| **User adoption** | Workflow disruption, learning curve, migration from existing behaviour | Plan rollout strategy, define adoption metrics |\n| **Timeline** | Competing priorities, team availability, sequential dependencies | Identify parallelisable work, flag resource conflicts early |\n\nFor each risk, document: description, likelihood (High\u002FMedium\u002FLow), impact (High\u002FMedium\u002FLow), mitigation plan, and owner.\n\n**Gate**: At least three risks are identified and documented. A spec with zero risks has not been examined critically.\n\n### Phase 5: Set Success Metrics\n\nDefine how the team will know the feature succeeded. Use the metric hierarchy:\n\n1. Primary metric (1 only): The single number that most directly measures whether the problem from Phase 1 is solved. Tied to the problem statement, not the solution.\n2. Leading indicators (2-3): Metrics that move BEFORE the primary metric, providing early signal. Example: if primary is retention, leading might be feature adoption rate or task completion rate.\n3. Guardrail metrics (1-2): Metrics that must NOT degrade. Prevent solving one problem by creating another. Example: page load time must not increase; support ticket volume must not spike.\n\nFor each metric:\n\n```\nMETRIC: [name]\n  Type:       Primary \u002F Leading \u002F Guardrail\n  Definition: [Precise calculation — numerator, denominator, time window]\n  Baseline:   [Current value or \"to be established in first 2 weeks\"]\n  Target:     [Specific threshold with timeframe]\n  Source:     [Where the data comes from — analytics tool, database query, survey]\n```\n\n**Gate**: At least one primary metric, one leading indicator, and one guardrail are defined with measurable targets.\n\n## PRD Output Template\n\nUse this structure for the final document. Adapt section depth to feature complexity — a two-week feature needs less detail than a quarter-long initiative.\n\n```\n# [Feature Name] — Product Requirements Document\n\n## 1. Problem Statement\n[From Phase 1 — the problem, who experiences it, evidence it matters]\n\n## 2. Solution Overview\n[2-3 sentence description of the proposed solution approach]\n\n## 3. Goals & Success Metrics\n[From Phase 5 — primary metric, leading indicators, guardrails with targets]\n\n## 4. Scope\n### 4a. In Scope (v1)\n[MoSCoW-classified capabilities for this release]\n\n### 4b. Out of Scope\n[Explicitly deferred items with rationale]\n\n## 5. User Stories & Requirements\n[From Phase 3 — decomposed requirements with acceptance criteria]\n\n### 5a. Must Have\n[Ship-blocking requirements]\n\n### 5b. Should Have\n[High-value requirements with workarounds]\n\n### 5c. Could Have\n[If capacity allows]\n\n## 6. User Flows\n[Key workflows — reference design files if available]\n\n## 7. Edge Cases & Error Handling\n[Consolidated from Phase 3 requirement decomposition]\n\n## 8. Technical Considerations\n[Known constraints, API dependencies, performance requirements, data model changes]\n\n## 9. Risks & Mitigations\n[From Phase 4 — categorised risks with owners]\n\n## 10. Dependencies\n[External teams, services, approvals required]\n\n## 11. Open Questions\n[Unresolved decisions — owner and deadline for each]\n\n## 12. Release Plan\n[Rollout strategy, feature flags, phased launch criteria]\n\n## 13. Appendix\n[Supporting research, competitive context, prior art references]\n```\n\n## Spec Sizing Guide\n\nMatch spec depth to feature scope:\n\n| Feature Scope | Typical Duration | Spec Depth | Key Sections |\n| --- | --- | --- | --- |\n| **Small** (bug fix, copy change, config) | \u003C 1 week | Lightweight — problem + requirements + acceptance criteria | Sections 1, 5, 7 |\n| **Medium** (new feature, workflow change) | 1-6 weeks | Standard — full PRD minus appendix | Sections 1-10 |\n| **Large** (new product area, platform change) | 1+ quarter | Comprehensive — full PRD with appendix, phased scope | All sections, phased release plan |\n\n## Anti-Patterns\n\nRecognise and flag these when they appear:\n\n1. Spec without a problem statement: A solution searching for a problem. If Phase 1 cannot produce a clear problem statement with evidence, the feature is not ready to spec. Redirect to user research or stakeholder alignment.\n2. Unbounded scope: No explicit out-of-scope section, no MoSCoW classification, or every item is \"Must have.\" Challenge with the scope anchoring question and force prioritisation.\n3. Requirements disguised as solutions: \"Add a dropdown\" instead of \"Users must be able to select from predefined options.\" Solution specificity in requirements constrains engineering unnecessarily and conflates the PM and engineering roles.\n4. Acceptance criteria that cannot fail: \"The feature works correctly\" is not testable. Every criterion must have a clear pass\u002Ffail condition.\n5. Zero risks identified: Signals insufficient critical examination. Push back — every feature has risks. The question is whether they are identified and managed.\n6. Metrics without baselines: A target of \"increase retention by 10%\" is meaningless without knowing the current rate. If baselines are unavailable, the first milestone is establishing them.\n7. Orphaned open questions: Questions listed but no owner or deadline for resolution. Every open question must have a name and a date, or it will block engineering.\n\n## Next Steps After Spec Completion\n\nOnce the PRD is reviewed and approved:\n\n1. Engineering review: Schedule a technical review to surface implementation concerns, refine estimates, and identify spikes.\n2. Design handoff: If design work is required, ensure wireframes or prototypes cover all user flows and edge cases in the spec.\n3. Spec as living document: Specs evolve during implementation. Establish a change-log section and a lightweight change-approval process (who can approve scope changes mid-build).\n\n## Guardrails\n\n- NEVER fabricate user research, metrics, or data. When data is not provided, state \"Data needed — [specify what]\" and leave the field for the user to fill.\n- NEVER assume technical constraints. Flag as [Requires engineering input] unless the user or a companyRAG collection provides specifics.\n- NEVER generate competitor features or market data. Reference the competitive-analysis skill or ask the user.\n- Source-label every element as [From user input], [Spec framework], or [AI suggestion — verify].\n\n> **Tip:** Ask for Markdown or DOCX output via companyFILES to get a formatted document ready for distribution.\n","# Product Spec Skill\n\nTurn ambiguous product ideas into clear, engineering-ready specifications. Covers clarification workflows, scope management, requirement structuring, and risk identification so reliable PRDs result. The inputs come from you, a connected MCP source, or companyRAG collections.\n\n## Where the Data Comes From\n\n| Source | What It Adds |\n| --- | --- |\n| **Project tracker via MCP** (e.g. Jira, Linear, Asana, Shortcut) | Existing tickets, epics, or OKRs for context; push finalised stories back |\n| **Design tool via MCP** (e.g. Figma, Miro) | Wireframes, user flows, design-system constraints |\n| **companyRAG collections** | Existing specs, prior research, competitive context, architecture docs |\n| **companyRAG \u002F file upload** | Confluence pages, discovery notes, technical assessments |\n\n> **No connected source?** Provide the data in chat or upload the relevant files — the skill works the same way.\n\n## Specification Workflow\n\nExecute these five phases sequentially. Each phase has a gate — do not advance until the gate condition is met.\n\n### Phase 1: Clarify the Problem\n\nBefore writing a single requirement, establish what problem this feature solves and for whom. Most spec failures trace back to skipping this phase.\n\n**Clarification question sequence** (ask in this order, adapt phrasing to context):\n\n1. Problem statement: \"What problem does this solve, and how do you know it's a real problem?\" — Look for evidence: user research, support tickets, churn data, sales feedback. If the answer is \"stakeholder X wants it,\" probe for the underlying problem.\n2. Affected users: \"Who experiences this problem, and how often?\" — Establish the user segment, frequency, and severity. A problem affecting 5% of users daily may matter more than one affecting 50% annually.\n3. Current workaround: \"How do users solve this today without the feature?\" — Workarounds reveal the true workflow, expectations, and pain intensity. No workaround may indicate low urgency.\n4. Business context: \"Why solve this now? What changes if we don't?\" — Connects to OKRs, revenue targets, competitive pressure, or regulatory deadlines. If the answer is vague, the priority is uncertain.\n5. Prior attempts: \"Has this been tried before? What happened?\" — Prevents re-treading failed approaches and surfaces organisational constraints.\n\n**Gate**: A problem statement exists that names the user, the pain, and the evidence. If the user cannot articulate the problem, help them formulate one before proceeding — do NOT skip to solution design.\n\n### Phase 2: Define Scope\n\nScope creep is the primary cause of spec failure. Use explicit in\u002Fout boundaries and a phasing framework.\n\n**Scope definition steps**:\n\n1. Solution sketch: Ask the user to describe their ideal solution in 2-3 sentences — maximum. This forces prioritisation before detail.\n2. In-scope \u002F out-of-scope table: For every capability mentioned, classify explicitly:\n\n| Capability | In Scope (v1) | Future (v2+) | Out of Scope | Rationale |\n| --- | --- | --- | --- | --- |\n| [capability] | ✓ \u002F — | — \u002F ✓ | — \u002F ✓ | [why this classification] |\n\n1. **MoSCoW classification** for in-scope items:   - Must have: Feature is broken without it. Ship-blocking.   - Should have: Significant value, strong expectation, but a workaround exists.   - Could have: Nice-to-have if capacity allows. First to cut.   - Won't have (this time): Explicitly deferred. Documenting \"won't\" prevents scope drift.\n2. **Scope anchoring question**: \"If we could only ship ONE thing from this spec, what would it be?\" — The answer is the non-negotiable core. Everything else is relative priority around it.\n\n**Gate**: An in\u002Fout table exists, MoSCoW classification is applied, and the user has confirmed the scope boundary.\n\n### Phase 3: Write Spec Sections\n\nStructure the PRD using the output template below. For each section, apply these writing principles:\n\n- Requirements over solutions: Describe WHAT and WHY, not HOW. \"Users must be able to filter by date range\" not \"Add a date-picker component.\"\n- Testable acceptance criteria: Every requirement must have a verifiable condition. \"The page loads\" is not testable. \"The page renders the first 20 results within 2 seconds on a 3G connection\" is.\n- Edge cases upfront: For each requirement, ask \"What happens when...?\" — empty states, error conditions, permission boundaries, data limits, concurrent access.\n- One requirement, one statement: Compound requirements (\"the system should X and Y\") hide complexity and create ambiguous acceptance criteria. Split them.\n\n**Requirement decomposition pattern**:\n\n```\nREQUIREMENT: [Clear, single-purpose statement]\n  User story:        As a [role], I want [capability] so that [outcome]\n  Acceptance criteria:\n    GIVEN [context]\n    WHEN  [action]\n    THEN  [observable result]\n  Edge cases:\n    - [What if input is empty\u002Fmalformed\u002Fat limit?]\n    - [What if user lacks permission?]\n    - [What if dependent service is unavailable?]\n  Dependencies:      [Other requirements or systems this depends on]\n  Open questions:    [Unresolved decisions — owner and deadline for resolution]\n```\n\n### Phase 4: Identify Risks\n\nSystematically surface risks before engineering begins. Categorise using:\n\n| Risk Category | What to Look For | Mitigation Pattern |\n| --- | --- | --- |\n| **Technical** | New technology, integration complexity, performance requirements, data migration | Spike\u002Fprototype first, define fallback approach |\n| **Scope** | Ambiguous requirements, undefined edge cases, implicit assumptions | Tighten acceptance criteria, add explicit constraints |\n| **Dependency** | External teams, third-party APIs, platform approvals, shared infrastructure | Identify critical path, establish SLAs or deadlines with owners |\n| **User adoption** | Workflow disruption, learning curve, migration from existing behaviour | Plan rollout strategy, define adoption metrics |\n| **Timeline** | Competing priorities, team availability, sequential dependencies | Identify parallelisable work, flag resource conflicts early |\n\nFor each risk, document: description, likelihood (High\u002FMedium\u002FLow), impact (High\u002FMedium\u002FLow), mitigation plan, and owner.\n\n**Gate**: At least three risks are identified and documented. A spec with zero risks has not been examined critically.\n\n### Phase 5: Set Success Metrics\n\nDefine how the team will know the feature succeeded. Use the metric hierarchy:\n\n1. Primary metric (1 only): The single number that most directly measures whether the problem from Phase 1 is solved. Tied to the problem statement, not the solution.\n2. Leading indicators (2-3): Metrics that move BEFORE the primary metric, providing early signal. Example: if primary is retention, leading might be feature adoption rate or task completion rate.\n3. Guardrail metrics (1-2): Metrics that must NOT degrade. Prevent solving one problem by creating another. Example: page load time must not increase; support ticket volume must not spike.\n\nFor each metric:\n\n```\nMETRIC: [name]\n  Type:       Primary \u002F Leading \u002F Guardrail\n  Definition: [Precise calculation — numerator, denominator, time window]\n  Baseline:   [Current value or \"to be established in first 2 weeks\"]\n  Target:     [Specific threshold with timeframe]\n  Source:     [Where the data comes from — analytics tool, database query, survey]\n```\n\n**Gate**: At least one primary metric, one leading indicator, and one guardrail are defined with measurable targets.\n\n## PRD Output Template\n\nUse this structure for the final document. Adapt section depth to feature complexity — a two-week feature needs less detail than a quarter-long initiative.\n\n```\n# [Feature Name] — Product Requirements Document\n\n## 1. Problem Statement\n[From Phase 1 — the problem, who experiences it, evidence it matters]\n\n## 2. Solution Overview\n[2-3 sentence description of the proposed solution approach]\n\n## 3. Goals & Success Metrics\n[From Phase 5 — primary metric, leading indicators, guardrails with targets]\n\n## 4. Scope\n### 4a. In Scope (v1)\n[MoSCoW-classified capabilities for this release]\n\n### 4b. Out of Scope\n[Explicitly deferred items with rationale]\n\n## 5. User Stories & Requirements\n[From Phase 3 — decomposed requirements with acceptance criteria]\n\n### 5a. Must Have\n[Ship-blocking requirements]\n\n### 5b. Should Have\n[High-value requirements with workarounds]\n\n### 5c. Could Have\n[If capacity allows]\n\n## 6. User Flows\n[Key workflows — reference design files if available]\n\n## 7. Edge Cases & Error Handling\n[Consolidated from Phase 3 requirement decomposition]\n\n## 8. Technical Considerations\n[Known constraints, API dependencies, performance requirements, data model changes]\n\n## 9. Risks & Mitigations\n[From Phase 4 — categorised risks with owners]\n\n## 10. Dependencies\n[External teams, services, approvals required]\n\n## 11. Open Questions\n[Unresolved decisions — owner and deadline for each]\n\n## 12. Release Plan\n[Rollout strategy, feature flags, phased launch criteria]\n\n## 13. Appendix\n[Supporting research, competitive context, prior art references]\n```\n\n## Spec Sizing Guide\n\nMatch spec depth to feature scope:\n\n| Feature Scope | Typical Duration | Spec Depth | Key Sections |\n| --- | --- | --- | --- |\n| **Small** (bug fix, copy change, config) | \u003C 1 week | Lightweight — problem + requirements + acceptance criteria | Sections 1, 5, 7 |\n| **Medium** (new feature, workflow change) | 1-6 weeks | Standard — full PRD minus appendix | Sections 1-10 |\n| **Large** (new product area, platform change) | 1+ quarter | Comprehensive — full PRD with appendix, phased scope | All sections, phased release plan |\n\n## Anti-Patterns\n\nRecognise and flag these when they appear:\n\n1. Spec without a problem statement: A solution searching for a problem. If Phase 1 cannot produce a clear problem statement with evidence, the feature is not ready to spec. Redirect to user research or stakeholder alignment.\n2. Unbounded scope: No explicit out-of-scope section, no MoSCoW classification, or every item is \"Must have.\" Challenge with the scope anchoring question and force prioritisation.\n3. Requirements disguised as solutions: \"Add a dropdown\" instead of \"Users must be able to select from predefined options.\" Solution specificity in requirements constrains engineering unnecessarily and conflates the PM and engineering roles.\n4. Acceptance criteria that cannot fail: \"The feature works correctly\" is not testable. Every criterion must have a clear pass\u002Ffail condition.\n5. Zero risks identified: Signals insufficient critical examination. Push back — every feature has risks. The question is whether they are identified and managed.\n6. Metrics without baselines: A target of \"increase retention by 10%\" is meaningless without knowing the current rate. If baselines are unavailable, the first milestone is establishing them.\n7. Orphaned open questions: Questions listed but no owner or deadline for resolution. Every open question must have a name and a date, or it will block engineering.\n\n## Next Steps After Spec Completion\n\nOnce the PRD is reviewed and approved:\n\n1. Engineering review: Schedule a technical review to surface implementation concerns, refine estimates, and identify spikes.\n2. Design handoff: If design work is required, ensure wireframes or prototypes cover all user flows and edge cases in the spec.\n3. Spec as living document: Specs evolve during implementation. Establish a change-log section and a lightweight change-approval process (who can approve scope changes mid-build).\n\n## Guardrails\n\n- NEVER fabricate user research, metrics, or data. When data is not provided, state \"Data needed — [specify what]\" and leave the field for the user to fill.\n- NEVER assume technical constraints. Flag as [Requires engineering input] unless the user or a companyRAG collection provides specifics.\n- NEVER generate competitor features or market data. Reference the competitive-analysis skill or ask the user.\n- Source-label every element as [From user input], [Spec framework], or [AI suggestion — verify].\n\n> **Tip:** Ask for Markdown or DOCX output via companyFILES to get a formatted document ready for distribution.\n",{"name":5,"description":7},"main","39e0752000720de2d20917bd46c1c5149c4a0221","en\u002Fskills\u002Fproduct-management\u002Fproduct-spec-skill","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills","https:\u002F\u002Fgithub.com\u002FinnFactory-AI","https:\u002F\u002Finnfactory.ai","Engineering AI. Enabling Tomorrow.","2026-11-13 19:54:47",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add innFactory-AI\u002Fcompany-ai-stack-skills --skill product-spec-skill",{"tool":38,"command":39},"bunx","bunx skills add innFactory-AI\u002Fcompany-ai-stack-skills --skill product-spec-skill",{"tool":41,"command":42},"pnpm","pnpm dlx skills add innFactory-AI\u002Fcompany-ai-stack-skills --skill product-spec-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fproduct-management\u002Fproduct-spec-skill\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7AF4HHK5B987T44HW7BZFVZ","sales-asset-skill","Produce tailored one-pagers, landing pages, case study drafts, and demo narratives personalised to a specific deal and buyer persona. Use when preparing collateral for a specific deal, building leave-behind materials, or customising standard assets for a prospect. Trigger with \"create a one-pager for\", \"sales deck for [deal]\", \"customise this asset for\".","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fsales\u002Fsales-asset-skill\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7AF4D32V0FJE0QGCBZSQ7BW","pipeline-review-skill","Analyse deal health, surface stale or at-risk opportunities, and produce a prioritised weekly action plan. Use when preparing for a pipeline review meeting, assessing forecast accuracy, or identifying stuck deals. Trigger with \"review my pipeline\", \"pipeline health check\", \"deal risk analysis\".","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fsales\u002Fpipeline-review-skill\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7AF48W7G8DMAHRAM125B192","outreach-skill","Research a prospect then draft personalised outreach with research-backed hooks, subject-line variants, and follow-up sequences. Use when cold-emailing a prospect, writing LinkedIn outreach, or building a multi-touch sequence. Trigger with \"draft outreach to [person\u002Fcompany]\", \"write cold email to\", \"outreach sequence for\".","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fsales\u002Foutreach-skill\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AF43VKNPQ7G1NTQ4MRH40J","forecast-skill","Build a weighted revenue forecast with risk flags, commit recommendations, and gap-to-quota analysis. Use when preparing for a forecast call, evaluating end-of-quarter projections, or assessing pipeline coverage. Trigger with \"build forecast\", \"forecast for this quarter\", \"where do I stand against quota\".","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fsales\u002Fforecast-skill\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AF3Z5N61VYSEJRYWXR4JP1","deal-strategy-skill","Map stakeholder power dynamics, surface deal risks, and recommend a step-by-step engagement strategy. Use when entering a complex deal, preparing for an executive sponsor meeting, or diagnosing a stuck opportunity. Trigger with \"plan deal strategy for\", \"stakeholder map\", \"how do I advance this deal\".","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fsales\u002Fdeal-strategy-skill\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AF3VGG29AX0T2X9WQ5MWDN","call-summary-skill","Extract action items, key topics, and objections from call notes or transcripts and draft a customer-facing follow-up email. Use after a sales call, demo, or discovery session. Trigger with \"summarise this call\", \"call notes from\", \"write follow-up for this meeting\".","https:\u002F\u002Fgithub.com\u002FinnFactory-AI\u002Fcompany-ai-stack-skills\u002Fblob\u002Fmain\u002Fen\u002Fskills\u002Fsales\u002Fcall-summary-skill\u002FSKILL.md",[],[]]