[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BX5MPQ2YJCZT6CXG7QPDWK":3,"skill-same:01M7BX5MPQ2YJCZT6CXG7QPDWK":71},{"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":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M7BX5MPQ2YJCZT6CXG7QPDWK","concept-engine",null,"Advanced concept generation from unstructured input — brainstorm notes, meeting transcripts, competitor observations, or a blank-slate strategic exploration. Maps ideas through the Creative Strategy Engine framework (pain x persona x awareness stage) and grounds every concept in Motion performance data. Use when the user has raw input or wants deep strategic mapping. For quick \"give me 3 concepts\" requests without raw material, use create-concepts instead.","CognitionAI\u002Fdevin-marketplace","CognitionAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F163493330?v=4","01M7BVSRD98NC4FG8T3EZS6V5M","Cognition","01M7BVSRDX111C2XPWJ0E6MY26",29,"MIT","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fmotion\u002Fskills\u002Fconcept-engine\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: concept-engine\ndescription: >\n  Advanced concept generation from unstructured input — brainstorm notes, meeting\n  transcripts, competitor observations, or a blank-slate strategic exploration. Maps\n  ideas through the Creative Strategy Engine framework (pain x persona x awareness stage)\n  and grounds every concept in Motion performance data. Use when the user has raw input\n  or wants deep strategic mapping. For quick \"give me 3 concepts\" requests without raw\n  material, use create-concepts instead.\nargument-hint: \"[raw idea or direction] [--count 3] [--focus hook|format|audience]\"\nallowed-tools:\n  - Read\n  - Agent\n  - \"mcp__motion__get_auth_context\"\n  - \"mcp__motion__get_workspace_brand\"\n  - \"mcp__motion__get_creative_insights\"\n  - \"mcp__motion__get_glossary_values\"\n  - \"mcp__motion__get_demographic_breakdown\"\n  - \"mcp__motion__get_workspace_competitors\"\n  - \"mcp__motion__get_inspo_creatives\"\n  - \"mcp__motion__get_inspo_brand_context\"\n  - \"mcp__motion__get_creative_transcript\"\n  - \"mcp__motion__search_brands\"\n  - \"mcp__motion__get_brand_by_domain\"\n  - AskUserQuestion\nmodel: opus\n---\n\n# Concept Engine — Data-Grounded Creative Concept Generator\n\n---\n\n## Phase 0: Orient\n\n1. **Acknowledge**: \"I'll map your input through the creative strategy framework and produce grounded concepts.\"\n2. **Ask for input**: \"What's the raw input — brainstorm notes, meeting transcript, competitor observation, or blank slate?\"\n3. **Connected workflow**: After concepts, you can brief one (`\u002Fbuild-brief`), write hooks for it (`\u002Fwrite-hooks`), or iterate on a specific angle.\n\nIf the user already provided raw input in their message, skip questions and proceed.\n\n---\n\nTransform any input into structured, briefable ad concepts grounded in performance data and the Creative Strategy Engine framework.\n\n---\n\n## Phase 1: Discovery\n\n### 1a. Parse Arguments\n\n- **Raw input** (`$ARGUMENTS`): The source material. Can be anything — a raw idea, meeting transcript, brainstorm notes, competitor observation, a single sentence, or empty.\n- **`--count`**: Number of concepts to generate. Default: 3. Range: 2-5.\n- **`--focus`**: Weight for concept generation:\n  - `hook` — emphasize hook innovation\n  - `format` — emphasize format experimentation\n  - `audience` — emphasize audience expansion\n  - Default: balanced across all dimensions.\n\n### 1b. Load Context\n\n1. Read `${CLAUDE_PLUGIN_ROOT}\u002Fmotion-creative.config.md` for brand guidelines, production constraints, primary KPI, target audience. If the file does not exist, use these defaults and suggest the user run `\u002Fcustomize`:\n   - `primary_kpi`: use goalMetric from first `get_creative_insights` response\n   - `default_date_preset`: LAST_30_DAYS\n   - `default_creative_limit`: 10\n   - `production_capabilities`: all formats\n   - `max_production_difficulty`: High\n   - Brand guidelines: pull from `get_workspace_brand`\n2. Read `${CLAUDE_SKILL_DIR}\u002F..\u002Fcreative-strategist\u002FSKILL.md` for methodology.\n3. Read `${CLAUDE_SKILL_DIR}\u002F..\u002Fcreative-strategist\u002Freferences\u002Fconcept-standards.md` for quality bar.\n4. Read `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcreative-strategy-engine.md` for the full strategic framework.\n5. Use `default_date_preset` from settings as the datePreset for all calls unless the user specified a date range. Use `default_creative_limit` from settings as the limit unless the user specified otherwise.\n\n### 1c. Pull Performance Data\n\n**The SPEND call must come first** (it returns goalMetric and spendThreshold). Then dispatch remaining calls in parallel.\n\n1. `get_auth_context()` — resolve workspace\n2. `get_creative_insights(workspaceId, insightType=\"SPEND\", datePreset=\"LAST_30_DAYS\", limit=10, withAggregatedInsights=true)` — spend leaders + account-level aggregates\n\n→ Extract `goalMetric` and `spendThreshold` from the response. If `goalMetric.isCustomConversion` is true, find the matching conversion in the `customConversions` array and include `[\"{id}_cost\", \"{id}_count\"]` in `tableKPIs` on all subsequent calls. Use goalMetric for all efficiency-sorted calls.\n\n3. `get_workspace_brand(workspaceId)` — brand positioning, voice, constraints, creative do's\u002Fdon'ts\n4. `get_creative_insights(workspaceId, insightType=goalMetric, datePreset=\"LAST_30_DAYS\", limit=10)` — efficiency leaders by workspace goal metric\n5. `get_creative_insights(workspaceId, insightType=\"SCALING\", datePreset=\"LAST_30_DAYS\", limit=10)` — what's scaling\n6. For hook rate leaders: filter SPEND results (call #1) to video creatives and sort by `thumbstop_ratio` descending. Do NOT use insightType=\"HOOK\" — it returns the same ranking as SCALING.\n7. `get_glossary_values(workspaceId, includeCreativeIds=true)` — creative taxonomy\n8. `get_demographic_breakdown(workspaceId)` — audience insights\n\nThen pull transcripts from the top 3 performers for hook\u002Fformat reference:\n9. `get_creative_transcript(creativeEntityId, creativeOrigin)`\n\nIf the raw input references competitors or specific brands:\n10. `get_workspace_competitors(workspaceId)` or `search_brands(query, workspaceId)` or `get_brand_by_domain(brandUrl)`\n11. `get_inspo_creatives(brandId, workspaceId, limit=10, sort=\"NEWEST\")` — competitor creative reference\n12. `get_inspo_brand_context(brandId, workspaceId)` — competitor strategy\n\n---\n\n## Phase 2: Analysis\n\n### 2a. Extract Ideas from Raw Input\n\nIf raw input was provided, parse it for:\n- **Explicit creative ideas** — \"we should try...\", \"what about...\", \"I saw this ad that...\"\n- **Implicit opportunities** — pain points mentioned, audience insights, product angles\n- **Strategic directions** — messaging shifts, new audiences, format experiments\n\nIf raw input is empty or minimal, skip to Phase 2b — the performance data becomes the primary source.\n\n### 2b. Map the Strategic Landscape\n\nUsing the Creative Strategy Engine framework:\n\n**Step 1: Identify the Primary Anchor**\n- Is the brand pain-led (solving a functional problem) or desire-led (aspirational)?\n- What are the core pain\u002Fdesire buckets?\n\n**Step 2: Map Personas**\n- For each relevant pain\u002Fdesire, identify 3-5 persona segments\n- Define each by: demographics, psychographics, and how they experience this specific pain\u002Fdesire differently\n\n**Step 3: Define Messaging Angles**\n- For each pain × persona intersection, define the core conversational truth\n- Not marketing copy — real language a real person would say\n- Answer: How does THIS person experience THIS pain? What do they REALLY want? What would they doubt?\n\n**Step 4: Determine Awareness Coverage**\n- Which stages need content? Check existing creative coverage via glossary.\n- Prioritize based on budget signals from the data (high spend = scaling budget, invest in unaware; lower spend = focus on problem\u002Fsolution aware).\n\n### 2c. Ground Each Idea in Performance Data\n\nFor each idea or direction:\n- Does the account data support this direction? Which metrics? Which creatives?\n- Has something similar been tried? Check glossary tags for existing coverage.\n- What audience responds to related approaches? Cross-reference demographics.\n- What gap does this fill in the taxonomy?\n\n### 2d. Analyze Winning Patterns\n\nFrom performance data + glossary:\n- Which glossary categories correlate with top goalMetric?\n- Which hooks appear in scaling creatives?\n- What messaging patterns do top performers share?\n- What combinations haven't been tried (coverage gaps)?\n\nFrom competitor data (if available):\n- What approaches are competitors running that the account doesn't show?\n- What formats or hooks are converging across the industry?\n- Where are competitors leaving white space?\n\n### 2e. Identify Audience Tensions\n\nFrom brand context and performance patterns, derive 2-3 specific audience tensions:\n- What specific moment does the audience struggle with?\n- What belief does the audience hold that the product challenges?\n- What emotional state is the audience in when most receptive?\n\n---\n\n## Phase 3: Strategy\n\n### 3a. Select Creative Mechanics\n\nFor each concept direction, choose a creative mechanic — the structural mechanism by which the concept delivers the truth to the viewer:\n\n- **Implied Answer** — Visual silently answers a question the hook posed\n- **Social Witness** — Third party's reaction validates the product\n- **Trojan Horse** — Ad looks like content until the product appears\n- **Reframe** — Flips the viewer's existing belief by the end\n- **Contrast Without Comment** — Shows two realities without editorializing\n\nThe mechanic shapes what kind of hook you write and what visual format executes the concept.\n\n### 3b. Map Strategic Positions\n\nFor each concept, define:\n- **Pain\u002FDesire anchor**: What pain or desire does this address?\n- **Persona**: Who specifically is this for?\n- **Messaging angle**: What's the core conversational truth?\n- **Awareness stage**: Where in the funnel does this live?\n- **Creative mechanic**: How does the concept deliver the truth?\n\n---\n\n## Phase 4: Direction\n\n### Concept Card Structure\n\nFor each concept, produce:\n\n**Title** (2-5 words) — Strategic essence, not execution description.\n\n**Format** — Creative format + production style + visual structure. Chosen intentionally — explain why this format serves this concept.\n\n**Messaging Angle** — The consumer motivation being communicated. Specific to this brand.\n\n**Intended Audience** — Specific enough to guide casting, tone, and message. Anchored to a tension from Phase 2e.\n\n**Hook** — The tactic (from hook-tactics library) AND the verbatim opening line.\n- Video: conversational, builds into narrative, reads naturally spoken aloud\n- Static: scannable headline, 5-8 words, complete on its own\n\n**Why It Can Work** — 1-2 sentences connecting to behavioral insight or performance pattern. Must reference specific data.\n\n**Reference Creatives** — 1-2 own top performers and\u002For competitor examples that inform this concept.\n\n**Production Difficulty** — Low \u002F Medium \u002F High.\n\n**Source** — Which part of the raw input inspired this concept (if applicable).\n\n**Data Grounding** — What performance data supports this direction.\n\n**Strategic Position** — Pain × persona × awareness stage from the framework.\n\n### Generation Rules\n\n- Every concept must be grounded in at least one data point from Phase 2\n- At least 2 elements must vary across concepts (audience, angle, format, hook tactic)\n- No concept should replicate an existing ad from the account\n- Each concept must pass the quality bar from concept-standards.md\n- If `--focus` is specified, at least 2 concepts should emphasize that dimension\n- Lead with the strongest or most differentiated concept\n\n### Quality Bar\n\nEvery concept must pass:\n- **Pain point specificity**: Built around a specific lived experience, not a product feature\n- **Strategic coherence**: Audience, message, format, and hook all align\n- **Differentiation**: Couldn't be used by a competitor without modification\n- **Format ambition**: Format chosen intentionally, contributes to persuasion\n- **Persuasive sharpness**: Hook creates tension, viewer feels personally implicated\n- **Testable hypothesis**: \"Why it can work\" is specific enough to succeed or fail clearly\n- **Producible**: Creative team could execute without major clarification\n\n### Handling Thin Context\n\nIf brand context is sparse or performance data is limited:\n- Use direct response fundamentals to fill gaps\n- Lean on category knowledge and proven structures\n- Do not caveat, apologize, or flag missing context\n- Concepts should be indistinguishable in quality from fully-informed outputs\n\n---\n\n## Phase 5: Articulation\n\n### Output Format\n\n**Input Summary** (2-3 sentences)\nWhat the source material contained and what ideas emerged. Skip if no raw input.\n\n**Concept Cards** (count × cards)\nEach following the format above.\n\n**Recommendation**\n\"I'd brief **[Concept X]** and **[Concept Y]** first — [data-grounded rationale for each].\"\n\n**Strategic Map**\nShow where these concepts fit in the pain × persona × awareness stage matrix. Identify remaining gaps for future ideation.\n\n### Close\n\n\"Want to turn any of these into a production brief? Run `\u002Fbuild-brief` with the concept, or I can develop it further.\"\n\n---\n\n## Error Handling\n\nRead `${CLAUDE_SKILL_DIR}\u002F..\u002Fcreative-strategist\u002Freferences\u002Ferror-handling.md` for degraded mode and error handling guidance.\n","# Concept Engine — Data-Grounded Creative Concept Generator\n\n---\n\n## Phase 0: Orient\n\n1. **Acknowledge**: \"I'll map your input through the creative strategy framework and produce grounded concepts.\"\n2. **Ask for input**: \"What's the raw input — brainstorm notes, meeting transcript, competitor observation, or blank slate?\"\n3. **Connected workflow**: After concepts, you can brief one (`\u002Fbuild-brief`), write hooks for it (`\u002Fwrite-hooks`), or iterate on a specific angle.\n\nIf the user already provided raw input in their message, skip questions and proceed.\n\n---\n\nTransform any input into structured, briefable ad concepts grounded in performance data and the Creative Strategy Engine framework.\n\n---\n\n## Phase 1: Discovery\n\n### 1a. Parse Arguments\n\n- **Raw input** (`$ARGUMENTS`): The source material. Can be anything — a raw idea, meeting transcript, brainstorm notes, competitor observation, a single sentence, or empty.\n- **`--count`**: Number of concepts to generate. Default: 3. Range: 2-5.\n- **`--focus`**: Weight for concept generation:\n  - `hook` — emphasize hook innovation\n  - `format` — emphasize format experimentation\n  - `audience` — emphasize audience expansion\n  - Default: balanced across all dimensions.\n\n### 1b. Load Context\n\n1. Read `${CLAUDE_PLUGIN_ROOT}\u002Fmotion-creative.config.md` for brand guidelines, production constraints, primary KPI, target audience. If the file does not exist, use these defaults and suggest the user run `\u002Fcustomize`:\n   - `primary_kpi`: use goalMetric from first `get_creative_insights` response\n   - `default_date_preset`: LAST_30_DAYS\n   - `default_creative_limit`: 10\n   - `production_capabilities`: all formats\n   - `max_production_difficulty`: High\n   - Brand guidelines: pull from `get_workspace_brand`\n2. Read `${CLAUDE_SKILL_DIR}\u002F..\u002Fcreative-strategist\u002FSKILL.md` for methodology.\n3. Read `${CLAUDE_SKILL_DIR}\u002F..\u002Fcreative-strategist\u002Freferences\u002Fconcept-standards.md` for quality bar.\n4. Read `${CLAUDE_SKILL_DIR}\u002Freferences\u002Fcreative-strategy-engine.md` for the full strategic framework.\n5. Use `default_date_preset` from settings as the datePreset for all calls unless the user specified a date range. Use `default_creative_limit` from settings as the limit unless the user specified otherwise.\n\n### 1c. Pull Performance Data\n\n**The SPEND call must come first** (it returns goalMetric and spendThreshold). Then dispatch remaining calls in parallel.\n\n1. `get_auth_context()` — resolve workspace\n2. `get_creative_insights(workspaceId, insightType=\"SPEND\", datePreset=\"LAST_30_DAYS\", limit=10, withAggregatedInsights=true)` — spend leaders + account-level aggregates\n\n→ Extract `goalMetric` and `spendThreshold` from the response. If `goalMetric.isCustomConversion` is true, find the matching conversion in the `customConversions` array and include `[\"{id}_cost\", \"{id}_count\"]` in `tableKPIs` on all subsequent calls. Use goalMetric for all efficiency-sorted calls.\n\n3. `get_workspace_brand(workspaceId)` — brand positioning, voice, constraints, creative do's\u002Fdon'ts\n4. `get_creative_insights(workspaceId, insightType=goalMetric, datePreset=\"LAST_30_DAYS\", limit=10)` — efficiency leaders by workspace goal metric\n5. `get_creative_insights(workspaceId, insightType=\"SCALING\", datePreset=\"LAST_30_DAYS\", limit=10)` — what's scaling\n6. For hook rate leaders: filter SPEND results (call #1) to video creatives and sort by `thumbstop_ratio` descending. Do NOT use insightType=\"HOOK\" — it returns the same ranking as SCALING.\n7. `get_glossary_values(workspaceId, includeCreativeIds=true)` — creative taxonomy\n8. `get_demographic_breakdown(workspaceId)` — audience insights\n\nThen pull transcripts from the top 3 performers for hook\u002Fformat reference:\n9. `get_creative_transcript(creativeEntityId, creativeOrigin)`\n\nIf the raw input references competitors or specific brands:\n10. `get_workspace_competitors(workspaceId)` or `search_brands(query, workspaceId)` or `get_brand_by_domain(brandUrl)`\n11. `get_inspo_creatives(brandId, workspaceId, limit=10, sort=\"NEWEST\")` — competitor creative reference\n12. `get_inspo_brand_context(brandId, workspaceId)` — competitor strategy\n\n---\n\n## Phase 2: Analysis\n\n### 2a. Extract Ideas from Raw Input\n\nIf raw input was provided, parse it for:\n- **Explicit creative ideas** — \"we should try...\", \"what about...\", \"I saw this ad that...\"\n- **Implicit opportunities** — pain points mentioned, audience insights, product angles\n- **Strategic directions** — messaging shifts, new audiences, format experiments\n\nIf raw input is empty or minimal, skip to Phase 2b — the performance data becomes the primary source.\n\n### 2b. Map the Strategic Landscape\n\nUsing the Creative Strategy Engine framework:\n\n**Step 1: Identify the Primary Anchor**\n- Is the brand pain-led (solving a functional problem) or desire-led (aspirational)?\n- What are the core pain\u002Fdesire buckets?\n\n**Step 2: Map Personas**\n- For each relevant pain\u002Fdesire, identify 3-5 persona segments\n- Define each by: demographics, psychographics, and how they experience this specific pain\u002Fdesire differently\n\n**Step 3: Define Messaging Angles**\n- For each pain × persona intersection, define the core conversational truth\n- Not marketing copy — real language a real person would say\n- Answer: How does THIS person experience THIS pain? What do they REALLY want? What would they doubt?\n\n**Step 4: Determine Awareness Coverage**\n- Which stages need content? Check existing creative coverage via glossary.\n- Prioritize based on budget signals from the data (high spend = scaling budget, invest in unaware; lower spend = focus on problem\u002Fsolution aware).\n\n### 2c. Ground Each Idea in Performance Data\n\nFor each idea or direction:\n- Does the account data support this direction? Which metrics? Which creatives?\n- Has something similar been tried? Check glossary tags for existing coverage.\n- What audience responds to related approaches? Cross-reference demographics.\n- What gap does this fill in the taxonomy?\n\n### 2d. Analyze Winning Patterns\n\nFrom performance data + glossary:\n- Which glossary categories correlate with top goalMetric?\n- Which hooks appear in scaling creatives?\n- What messaging patterns do top performers share?\n- What combinations haven't been tried (coverage gaps)?\n\nFrom competitor data (if available):\n- What approaches are competitors running that the account doesn't show?\n- What formats or hooks are converging across the industry?\n- Where are competitors leaving white space?\n\n### 2e. Identify Audience Tensions\n\nFrom brand context and performance patterns, derive 2-3 specific audience tensions:\n- What specific moment does the audience struggle with?\n- What belief does the audience hold that the product challenges?\n- What emotional state is the audience in when most receptive?\n\n---\n\n## Phase 3: Strategy\n\n### 3a. Select Creative Mechanics\n\nFor each concept direction, choose a creative mechanic — the structural mechanism by which the concept delivers the truth to the viewer:\n\n- **Implied Answer** — Visual silently answers a question the hook posed\n- **Social Witness** — Third party's reaction validates the product\n- **Trojan Horse** — Ad looks like content until the product appears\n- **Reframe** — Flips the viewer's existing belief by the end\n- **Contrast Without Comment** — Shows two realities without editorializing\n\nThe mechanic shapes what kind of hook you write and what visual format executes the concept.\n\n### 3b. Map Strategic Positions\n\nFor each concept, define:\n- **Pain\u002FDesire anchor**: What pain or desire does this address?\n- **Persona**: Who specifically is this for?\n- **Messaging angle**: What's the core conversational truth?\n- **Awareness stage**: Where in the funnel does this live?\n- **Creative mechanic**: How does the concept deliver the truth?\n\n---\n\n## Phase 4: Direction\n\n### Concept Card Structure\n\nFor each concept, produce:\n\n**Title** (2-5 words) — Strategic essence, not execution description.\n\n**Format** — Creative format + production style + visual structure. Chosen intentionally — explain why this format serves this concept.\n\n**Messaging Angle** — The consumer motivation being communicated. Specific to this brand.\n\n**Intended Audience** — Specific enough to guide casting, tone, and message. Anchored to a tension from Phase 2e.\n\n**Hook** — The tactic (from hook-tactics library) AND the verbatim opening line.\n- Video: conversational, builds into narrative, reads naturally spoken aloud\n- Static: scannable headline, 5-8 words, complete on its own\n\n**Why It Can Work** — 1-2 sentences connecting to behavioral insight or performance pattern. Must reference specific data.\n\n**Reference Creatives** — 1-2 own top performers and\u002For competitor examples that inform this concept.\n\n**Production Difficulty** — Low \u002F Medium \u002F High.\n\n**Source** — Which part of the raw input inspired this concept (if applicable).\n\n**Data Grounding** — What performance data supports this direction.\n\n**Strategic Position** — Pain × persona × awareness stage from the framework.\n\n### Generation Rules\n\n- Every concept must be grounded in at least one data point from Phase 2\n- At least 2 elements must vary across concepts (audience, angle, format, hook tactic)\n- No concept should replicate an existing ad from the account\n- Each concept must pass the quality bar from concept-standards.md\n- If `--focus` is specified, at least 2 concepts should emphasize that dimension\n- Lead with the strongest or most differentiated concept\n\n### Quality Bar\n\nEvery concept must pass:\n- **Pain point specificity**: Built around a specific lived experience, not a product feature\n- **Strategic coherence**: Audience, message, format, and hook all align\n- **Differentiation**: Couldn't be used by a competitor without modification\n- **Format ambition**: Format chosen intentionally, contributes to persuasion\n- **Persuasive sharpness**: Hook creates tension, viewer feels personally implicated\n- **Testable hypothesis**: \"Why it can work\" is specific enough to succeed or fail clearly\n- **Producible**: Creative team could execute without major clarification\n\n### Handling Thin Context\n\nIf brand context is sparse or performance data is limited:\n- Use direct response fundamentals to fill gaps\n- Lean on category knowledge and proven structures\n- Do not caveat, apologize, or flag missing context\n- Concepts should be indistinguishable in quality from fully-informed outputs\n\n---\n\n## Phase 5: Articulation\n\n### Output Format\n\n**Input Summary** (2-3 sentences)\nWhat the source material contained and what ideas emerged. Skip if no raw input.\n\n**Concept Cards** (count × cards)\nEach following the format above.\n\n**Recommendation**\n\"I'd brief **[Concept X]** and **[Concept Y]** first — [data-grounded rationale for each].\"\n\n**Strategic Map**\nShow where these concepts fit in the pain × persona × awareness stage matrix. Identify remaining gaps for future ideation.\n\n### Close\n\n\"Want to turn any of these into a production brief? Run `\u002Fbuild-brief` with the concept, or I can develop it further.\"\n\n---\n\n## Error Handling\n\nRead `${CLAUDE_SKILL_DIR}\u002F..\u002Fcreative-strategist\u002Freferences\u002Ferror-handling.md` for degraded mode and error handling guidance.\n",{"name":5,"model":24,"description":25,"allowed-tools":26,"argument-hint":41},"opus","Advanced concept generation from unstructured input — brainstorm notes, meeting transcripts, competitor observations, or a blank-slate strategic exploration. Maps ideas through the Creative Strategy Engine framework (pain x persona x awareness stage) and grounds every concept in Motion performance data. Use when the user has raw input or wants deep strategic mapping. For quick \"give me 3 concepts\" requests without raw material, use create-concepts instead.\n",[27,28,29,30,31,32,33,34,35,36,37,38,39,40],"Read","Agent","mcp__motion__get_auth_context","mcp__motion__get_workspace_brand","mcp__motion__get_creative_insights","mcp__motion__get_glossary_values","mcp__motion__get_demographic_breakdown","mcp__motion__get_workspace_competitors","mcp__motion__get_inspo_creatives","mcp__motion__get_inspo_brand_context","mcp__motion__get_creative_transcript","mcp__motion__search_brands","mcp__motion__get_brand_by_domain","AskUserQuestion","[raw idea or direction] [--count 3] [--focus hook|format|audience]","main","9836d94e88404aabb682086405c2aa9cba7657ac","plugins\u002Fmotion\u002Fskills\u002Fconcept-engine",156,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace","https:\u002F\u002Fgithub.com\u002FCognitionAI","https:\u002F\u002Fcognition.ai\u002F","Makers of Devin, the AI software engineer.","2026-11-13 07:08:23",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add CognitionAI\u002Fdevin-marketplace --skill concept-engine",{"tool":57,"command":58},"bunx","bunx skills add CognitionAI\u002Fdevin-marketplace --skill concept-engine",{"tool":60,"command":61},"pnpm","pnpm dlx skills add CognitionAI\u002Fdevin-marketplace --skill concept-engine","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fmotion\u002Fskills\u002Fconcept-engine\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fcreative-strategy-engine.md","REFERENCE","参考文档",34254,"https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fmotion\u002Fskills\u002Fconcept-engine\u002Freferences\u002Fcreative-strategy-engine.md",[72,78,85,91,98,105],{"skillNo":73,"name":74,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7BYC4AJGM98P2G9JH7QS24Z","business-data","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fwindsor-ai\u002Fskills\u002Fbusiness-data\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7BYBZ0CD4CBCPZHRZ551BNK","workflow","Creates durable, resumable workflows using Vercel's Workflow SDK. Use when building workflows that need to survive restarts, pause for external events, retry on failure, or coordinate multi-step operations over time. Triggers on mentions of \"workflow\", \"durable functions\", \"resumable\", \"workflow sdk\", \"queue\", \"event\", \"push\", \"subscribe\", or step-based orchestration.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002Fupstream\u002FSKILL.md",[],[],{"skillNo":86,"name":80,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7BYB1XSZHKHD8JZTQJ62JN0","Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause\u002Fresume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7BYASGMK935J33E21N5WTW0","verification","Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fverification\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7BY9WJERKSKEH9HK6E71GW2","vercel-storage","Vercel storage expert guidance — Blob, Global Config (formerly Edge Config), and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-storage\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7BY9N034894YV2J9DCRZHYS","vercel-services","Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. Use when composing a polyglot or multi-service application on one Vercel deployment; defining the `services` key, service-targeted rewrites, or service bindings in `vercel.json`; or running all services with `vercel dev`.","https:\u002F\u002Fgithub.com\u002FCognitionAI\u002Fdevin-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fvercel\u002Fskills\u002Fvercel-services\u002FSKILL.md",[],[]]