[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DK6MWKP38GV1P4BK9VSAKH":3,"skill-same:01M6DK6MWKP38GV1P4BK9VSAKH":86},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":68,"ownerHtmlUrl":69,"ownerBlogUrl":70,"ownerDescription":71,"updatedAt":72,"install":73,"resources":85},"01M6DK6MWKP38GV1P4BK9VSAKH","company-research",null,"Research companies, competitors, funding, news, leadership, and market context with Exa Agent and advanced search. Use when researching companies, competitor analysis, market research, or building company lists. Writes findings the caller can fold into brand\u002Fcompetitors.md or brand\u002Flandscape.md. Prefer this over ad-hoc web search for company deep dives. Distinct from competitive-intel (full brand competitive file methodology) - this skill is the Exa research engine those foundation skills should call.","MoizIbnYousaf\u002Fmarketing-cli","MoizIbnYousaf","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F148609638?v=4","01M6DK31T63X0A4VD3HV88V5E4","Abdul Moiz Shahzad","01M6DK31ZWA28MZK3202BZRXAB",35,"MIT","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Fcompany-research\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"company research","research","context","full","deep","leadership","landscape","call","exa","Fold","use","write","read","brand","competitors","web search","Bash","analysis","file","search","2026-11-10 10:12:30",false,"---\nname: company-research\nversion: 0.1.0\ndescription: >\n  Research companies, competitors, funding, news, leadership, and market context\n  with Exa Agent and advanced search. Use when researching companies, competitor\n  analysis, market research, or building company lists. Writes findings the\n  caller can fold into brand\u002Fcompetitors.md or brand\u002Flandscape.md. Prefer this\n  over ad-hoc web search for company deep dives. Distinct from competitive-intel\n  (full brand competitive file methodology) - this skill is the Exa research\n  engine those foundation skills should call.\nallowed-tools:\n  - Bash\n  - Read\n  - Write\n  - Skill\nauthor: Exa Labs (ported by mktg)\nlicense: MIT\nuser-invocable: true\nmetadata:\n  openclaw:\n    emoji: ?\n---\n\n## On Activation\n\n1. Read `brand\u002Fpositioning.md`, `brand\u002Fcompetitors.md`, and `brand\u002Faudience.md` if present. Ground queries in the brand's category and known competitors. All optional.\n2. Confirm Exa MCP Agent tools or `EXA_API_KEY`. If missing, stop with the install hint from Prerequisites \u002F `mktg doctor`.\n3. Default to Exa Agent for deep dives and lists; use advanced search only for quick single lookups.\n4. When `\u002Fcmo` or a research agent owns the brand write, return structured findings + sources - do not silently overwrite `brand\u002Fcompetitors.md` unless the user asked to update brand memory.\n\n# Company Research\n\n\n## mktg runtime note\n\nPrefer **Exa MCP** when available (tools: `web_search_exa`, `web_search_advanced_exa`, `web_fetch_exa`, `agent_run`).\nIf MCP Agent tools use the older create\u002Fwait\u002Fget names (`agent_create_run`, `agent_wait_for_run`, `agent_get_run_output`), use those equivalently.\nWithout MCP, call the HTTP API with `x-api-key: $EXA_API_KEY` (`POST https:\u002F\u002Fapi.exa.ai\u002Fsearch`, `\u002Fcontents`, `\u002Fagent`).\nFirecrawl remains the path for deep scrape of a **known URL** after Exa discovery.\n\n\n## Tool Selection (Critical)\n\nTwo Exa surfaces, two jobs:\n\n- **Exa Agent** (`agent_run`, or legacy `agent_create_run` \u002F `agent_wait_for_run` \u002F `agent_get_run_output`) - the default for company research. Use it for deep dives, competitor analysis, multi-angle research (product + funding + news + people), and building company lists. One Agent run handles query decomposition, multi-step searching, and synthesis internally - do not orchestrate many manual searches for work an Agent run covers.\n- **`web_search_advanced_exa`** - quick, low-latency lookups: a fast `category: \"company\"` discovery pass, a single news check, or finding a homepage.\n\nDo NOT use other Exa tools.\n\n## Deep Dives and Lists: Exa Agent\n\nAgent runs are async: create the run, wait for it, then read the output.\n\n1. `agent_create_run` with a natural-language `query` and, when you want repeatable structure, an `outputSchema` (bound arrays with `maxItems`). Returns an `agent_run_...` ID.\n2. `agent_wait_for_run` until the run is `completed` (call again if still running).\n3. `agent_get_run_output` - read `output.text` or `output.structured`, plus `output.grounding` citations.\n\nUseful inputs: `systemPrompt` (source preferences, dedup rules), `input.exclusion` (companies to avoid), `previousRunId` (follow-up runs), `effort` (`\"auto\"` default; `\"high\"` for hard research).\n\n### Example: company deep dive\n\n```\nagent_create_run {\n  \"query\": \"Research Anthropic: product lines, funding history and valuation, key executives, main competitors, and notable news from the last 6 months.\",\n  \"effort\": \"auto\",\n  \"outputSchema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"overview\": { \"type\": \"string\" },\n      \"funding\": { \"type\": \"array\", \"maxItems\": 10, \"items\": { \"type\": \"object\", \"properties\": { \"round\": { \"type\": \"string\" }, \"amount\": { \"type\": \"string\" }, \"date\": { \"type\": \"string\" } }, \"required\": [\"round\"] } },\n      \"competitors\": { \"type\": \"array\", \"maxItems\": 10, \"items\": { \"type\": \"string\" } },\n      \"key_people\": { \"type\": \"array\", \"maxItems\": 10, \"items\": { \"type\": \"object\", \"properties\": { \"name\": { \"type\": \"string\" }, \"title\": { \"type\": \"string\" } }, \"required\": [\"name\", \"title\"] } }\n    },\n    \"required\": [\"overview\", \"competitors\"]\n  }\n}\n```\n\n### Example: build a company list\n\n```\nagent_create_run {\n  \"query\": \"Find 25 AI infrastructure startups headquartered in San Francisco. For each, include what they build and their latest funding stage.\",\n  \"effort\": \"auto\",\n  \"outputSchema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"companies\": {\n        \"type\": \"array\",\n        \"maxItems\": 25,\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"name\": { \"type\": \"string\" },\n            \"website\": { \"type\": \"string\", \"format\": \"uri\" },\n            \"description\": { \"type\": \"string\", \"description\": \"in 12 words or less\" },\n            \"funding_stage\": { \"type\": \"string\" }\n          },\n          \"required\": [\"name\", \"website\", \"description\"]\n        }\n      }\n    },\n    \"required\": [\"companies\"]\n  }\n}\n```\n\n## Quick Lookups: Advanced Search\n\nUse `web_search_advanced_exa` when a single fast search answers the question. Tune `numResults` to intent (a few → 10-20; comprehensive → 50-100; specified → match it).\n\n### Categories\n\n- `company` → homepages, rich metadata (headcount, location, funding, revenue)\n- `news` → press coverage, announcements\n- `people` → public professional profiles\n- No category (`type: \"auto\"`) → general web results, broader context\n\nDefault to `type: \"auto\"`. Prefer `highlights` for content extraction; do not stack text + highlights + summary in one call.\n\n### Category-Specific Filter Restrictions\n\nUnsupported category\u002Ffilter combinations return 400 errors:\n\n- `category: \"company\"` does not support published-date or crawl-date filters, `excludeDomains`, or exact-text filters; express constraints like \"founded after 2020\" in the query instead\n- `category: \"people\"` does not support published-date, crawl-date, domain, or exact-text filters; put all filtering in the natural-language query\n- Without a category (or with `news`), domain and date filters work fine\n\n### Examples\n\nDiscovery pass:\n```\nweb_search_advanced_exa {\n  \"query\": \"AI infrastructure startups San Francisco\",\n  \"category\": \"company\",\n  \"numResults\": 20,\n  \"type\": \"auto\"\n}\n```\n\nNews check:\n```\nweb_search_advanced_exa {\n  \"query\": \"Anthropic AI safety\",\n  \"category\": \"news\",\n  \"numResults\": 15,\n  \"startPublishedDate\": \"2025-01-01\"\n}\n```\n\nKey people:\n```\nweb_search_advanced_exa {\n  \"query\": \"VP Engineering AI infrastructure\",\n  \"category\": \"people\",\n  \"numResults\": 20\n}\n```\n\n## Token Isolation\n\nNever dump raw search results into main context. Spawn Task agents for Advanced Search calls; for Agent runs, go straight from `output.structured` to the final answer.\n\n## Browser Fallback\n\nFall back to Claude in Chrome only when content is auth-gated or requires JavaScript rendering.\n\n## Output Format\n\nReturn:\n1) Results (structured list; one company per row)\n2) Sources (URLs; 1-line relevance each - use `output.grounding` from Agent runs)\n3) Notes (uncertainty\u002Fconflicts)\n\n## References\n\n- Exa Agent guide: https:\u002F\u002Fdocs.exa.ai\u002Freference\u002Fagent-api-guide\n- Company Search reference: https:\u002F\u002Fdocs.exa.ai\u002Freference\u002Fverticals\u002Fcompany-for-coding-agents\n- Exa MCP setup: https:\u002F\u002Fdocs.exa.ai\u002Freference\u002Fexa-mcp\n- Full docs for LLMs: https:\u002F\u002Fdocs.exa.ai\u002Fllms.txt\n\n## Anti-Patterns\n\n| Anti-pattern | Why it fails | Instead |\n|---|---|---|\n| Using Claude native WebSearch instead of Exa | Misses niche competitors, companies, and cited sources Exa ranks highly. | Use this skill (or Exa MCP) for all open-ended web research. |\n| Calling Exa without `EXA_API_KEY` \u002F MCP auth | Requests 401 and the agent invents results. | Set `EXA_API_KEY` (dashboard.exa.ai) or configure `.mcp.json`; surface the fix via `mktg doctor`. |\n| Dumping raw result JSON into the user chat | Burns context and hides the answer. | Synthesize; cite URLs from grounding \u002F result lists. |\n\n## Attribution\n\nPorted from [exa-labs\u002Fagent-skills](https:\u002F\u002Fgithub.com\u002Fexa-labs\u002Fagent-skills) - adapted for mktg's drop-in contract on 2026-07-18.\n\nUpstream commit: 390ffee2d7e1d0dce2ed8efe4994c2b3c1c0173b\n\nDrift detection: if the upstream skill changes, re-run `mktg-steal https:\u002F\u002Fgithub.com\u002Fexa-labs\u002Fagent-skills` to evaluate the diff.\n","## On Activation\n\n1. Read `brand\u002Fpositioning.md`, `brand\u002Fcompetitors.md`, and `brand\u002Faudience.md` if present. Ground queries in the brand's category and known competitors. All optional.\n2. Confirm Exa MCP Agent tools or `EXA_API_KEY`. If missing, stop with the install hint from Prerequisites \u002F `mktg doctor`.\n3. Default to Exa Agent for deep dives and lists; use advanced search only for quick single lookups.\n4. When `\u002Fcmo` or a research agent owns the brand write, return structured findings + sources - do not silently overwrite `brand\u002Fcompetitors.md` unless the user asked to update brand memory.\n\n# Company Research\n\n\n## mktg runtime note\n\nPrefer **Exa MCP** when available (tools: `web_search_exa`, `web_search_advanced_exa`, `web_fetch_exa`, `agent_run`).\nIf MCP Agent tools use the older create\u002Fwait\u002Fget names (`agent_create_run`, `agent_wait_for_run`, `agent_get_run_output`), use those equivalently.\nWithout MCP, call the HTTP API with `x-api-key: $EXA_API_KEY` (`POST https:\u002F\u002Fapi.exa.ai\u002Fsearch`, `\u002Fcontents`, `\u002Fagent`).\nFirecrawl remains the path for deep scrape of a **known URL** after Exa discovery.\n\n\n## Tool Selection (Critical)\n\nTwo Exa surfaces, two jobs:\n\n- **Exa Agent** (`agent_run`, or legacy `agent_create_run` \u002F `agent_wait_for_run` \u002F `agent_get_run_output`) - the default for company research. Use it for deep dives, competitor analysis, multi-angle research (product + funding + news + people), and building company lists. One Agent run handles query decomposition, multi-step searching, and synthesis internally - do not orchestrate many manual searches for work an Agent run covers.\n- **`web_search_advanced_exa`** - quick, low-latency lookups: a fast `category: \"company\"` discovery pass, a single news check, or finding a homepage.\n\nDo NOT use other Exa tools.\n\n## Deep Dives and Lists: Exa Agent\n\nAgent runs are async: create the run, wait for it, then read the output.\n\n1. `agent_create_run` with a natural-language `query` and, when you want repeatable structure, an `outputSchema` (bound arrays with `maxItems`). Returns an `agent_run_...` ID.\n2. `agent_wait_for_run` until the run is `completed` (call again if still running).\n3. `agent_get_run_output` - read `output.text` or `output.structured`, plus `output.grounding` citations.\n\nUseful inputs: `systemPrompt` (source preferences, dedup rules), `input.exclusion` (companies to avoid), `previousRunId` (follow-up runs), `effort` (`\"auto\"` default; `\"high\"` for hard research).\n\n### Example: company deep dive\n\n```\nagent_create_run {\n  \"query\": \"Research Anthropic: product lines, funding history and valuation, key executives, main competitors, and notable news from the last 6 months.\",\n  \"effort\": \"auto\",\n  \"outputSchema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"overview\": { \"type\": \"string\" },\n      \"funding\": { \"type\": \"array\", \"maxItems\": 10, \"items\": { \"type\": \"object\", \"properties\": { \"round\": { \"type\": \"string\" }, \"amount\": { \"type\": \"string\" }, \"date\": { \"type\": \"string\" } }, \"required\": [\"round\"] } },\n      \"competitors\": { \"type\": \"array\", \"maxItems\": 10, \"items\": { \"type\": \"string\" } },\n      \"key_people\": { \"type\": \"array\", \"maxItems\": 10, \"items\": { \"type\": \"object\", \"properties\": { \"name\": { \"type\": \"string\" }, \"title\": { \"type\": \"string\" } }, \"required\": [\"name\", \"title\"] } }\n    },\n    \"required\": [\"overview\", \"competitors\"]\n  }\n}\n```\n\n### Example: build a company list\n\n```\nagent_create_run {\n  \"query\": \"Find 25 AI infrastructure startups headquartered in San Francisco. For each, include what they build and their latest funding stage.\",\n  \"effort\": \"auto\",\n  \"outputSchema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"companies\": {\n        \"type\": \"array\",\n        \"maxItems\": 25,\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"name\": { \"type\": \"string\" },\n            \"website\": { \"type\": \"string\", \"format\": \"uri\" },\n            \"description\": { \"type\": \"string\", \"description\": \"in 12 words or less\" },\n            \"funding_stage\": { \"type\": \"string\" }\n          },\n          \"required\": [\"name\", \"website\", \"description\"]\n        }\n      }\n    },\n    \"required\": [\"companies\"]\n  }\n}\n```\n\n## Quick Lookups: Advanced Search\n\nUse `web_search_advanced_exa` when a single fast search answers the question. Tune `numResults` to intent (a few → 10-20; comprehensive → 50-100; specified → match it).\n\n### Categories\n\n- `company` → homepages, rich metadata (headcount, location, funding, revenue)\n- `news` → press coverage, announcements\n- `people` → public professional profiles\n- No category (`type: \"auto\"`) → general web results, broader context\n\nDefault to `type: \"auto\"`. Prefer `highlights` for content extraction; do not stack text + highlights + summary in one call.\n\n### Category-Specific Filter Restrictions\n\nUnsupported category\u002Ffilter combinations return 400 errors:\n\n- `category: \"company\"` does not support published-date or crawl-date filters, `excludeDomains`, or exact-text filters; express constraints like \"founded after 2020\" in the query instead\n- `category: \"people\"` does not support published-date, crawl-date, domain, or exact-text filters; put all filtering in the natural-language query\n- Without a category (or with `news`), domain and date filters work fine\n\n### Examples\n\nDiscovery pass:\n```\nweb_search_advanced_exa {\n  \"query\": \"AI infrastructure startups San Francisco\",\n  \"category\": \"company\",\n  \"numResults\": 20,\n  \"type\": \"auto\"\n}\n```\n\nNews check:\n```\nweb_search_advanced_exa {\n  \"query\": \"Anthropic AI safety\",\n  \"category\": \"news\",\n  \"numResults\": 15,\n  \"startPublishedDate\": \"2025-01-01\"\n}\n```\n\nKey people:\n```\nweb_search_advanced_exa {\n  \"query\": \"VP Engineering AI infrastructure\",\n  \"category\": \"people\",\n  \"numResults\": 20\n}\n```\n\n## Token Isolation\n\nNever dump raw search results into main context. Spawn Task agents for Advanced Search calls; for Agent runs, go straight from `output.structured` to the final answer.\n\n## Browser Fallback\n\nFall back to Claude in Chrome only when content is auth-gated or requires JavaScript rendering.\n\n## Output Format\n\nReturn:\n1) Results (structured list; one company per row)\n2) Sources (URLs; 1-line relevance each - use `output.grounding` from Agent runs)\n3) Notes (uncertainty\u002Fconflicts)\n\n## References\n\n- Exa Agent guide: https:\u002F\u002Fdocs.exa.ai\u002Freference\u002Fagent-api-guide\n- Company Search reference: https:\u002F\u002Fdocs.exa.ai\u002Freference\u002Fverticals\u002Fcompany-for-coding-agents\n- Exa MCP setup: https:\u002F\u002Fdocs.exa.ai\u002Freference\u002Fexa-mcp\n- Full docs for LLMs: https:\u002F\u002Fdocs.exa.ai\u002Fllms.txt\n\n## Anti-Patterns\n\n| Anti-pattern | Why it fails | Instead |\n|---|---|---|\n| Using Claude native WebSearch instead of Exa | Misses niche competitors, companies, and cited sources Exa ranks highly. | Use this skill (or Exa MCP) for all open-ended web research. |\n| Calling Exa without `EXA_API_KEY` \u002F MCP auth | Requests 401 and the agent invents results. | Set `EXA_API_KEY` (dashboard.exa.ai) or configure `.mcp.json`; surface the fix via `mktg doctor`. |\n| Dumping raw result JSON into the user chat | Burns context and hides the answer. | Synthesize; cite URLs from grounding \u002F result lists. |\n\n## Attribution\n\nPorted from [exa-labs\u002Fagent-skills](https:\u002F\u002Fgithub.com\u002Fexa-labs\u002Fagent-skills) - adapted for mktg's drop-in contract on 2026-07-18.\n\nUpstream commit: 390ffee2d7e1d0dce2ed8efe4994c2b3c1c0173b\n\nDrift detection: if the upstream skill changes, re-run `mktg-steal https:\u002F\u002Fgithub.com\u002Fexa-labs\u002Fagent-skills` to evaluate the diff.\n",{"name":5,"author":52,"license":15,"version":53,"metadata":54,"description":57,"allowed-tools":58,"user-invocable":62},"Exa Labs (ported by mktg)","0.1.0",{"openclaw":55},{"emoji":56},"?","Research companies, competitors, funding, news, leadership, and market context with Exa Agent and advanced search. Use when researching companies, competitor analysis, market research, or building company lists. Writes findings the caller can fold into brand\u002Fcompetitors.md or brand\u002Flandscape.md. Prefer this over ad-hoc web search for company deep dives. Distinct from competitive-intel (full brand competitive file methodology) - this skill is the Exa research engine those foundation skills should call.\n",[43,59,60,61],"Read","Write","Skill",true,"main","65a0c0d1e5a6f4ac9fb5281a72c91cbf7e9257aa","skills\u002Fcompany-research",5,"https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli","https:\u002F\u002Fwww.marketing-cli.com\u002F","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf","https:\u002F\u002Fmoiz.ai","AI Engineer\r\n","2026-10-20 15:05:36",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":62},[75,78,81],{"tool":76,"command":77},"npx","npx skills add MoizIbnYousaf\u002Fmarketing-cli --skill company-research",{"tool":79,"command":80},"bunx","bunx skills add MoizIbnYousaf\u002Fmarketing-cli --skill company-research",{"tool":82,"command":83},"pnpm","pnpm dlx skills add MoizIbnYousaf\u002Fmarketing-cli --skill company-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Fcompany-research\u002FSKILL.md",[],[87,107,133,167,199,225],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":47},"01M6DKQDNVS30J8TB3YYM13PJ2","cmo-studio-integration","When mktg-studio is running on this machine, \u002Fcmo proactively narrates work into the dashboard via Bash + curl against the localhost HTTP API. Detect via \u002Fapi\u002Fhealth, then log every meaningful action — the user sees what \u002Fcmo is doing in real time.","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fstudio\u002Fskills\u002Fcmo-studio-integration\u002FSKILL.md",[],[94,95,96,97,98,99,100,101,43,102,103,104,105,106],"integration","cmo","cmo studio integration","real time","dashboard","http","api","health","work","curl","user","log","time",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":119,"publishedAt":47},"01M6DKQ8KH8EZ27YY7PEDSZGMT","voice-extraction","Reverse-engineer any person's writing voice from their content. Paste in posts, articles, tweets, or essays and this skill launches 10 parallel Sonnet subagents to analyze every dimension of the voice, then synthesizes into a voice file. Use when someone says 'match this voice,' 'analyze this writing,' 'extract their voice,' 'make me sound like this,' 'study this person's writing,' or pastes in content they want to learn from.","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Fvoice-extraction\u002FSKILL.md",[113,114],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[120,121,122,123,124,125,45,126,127,128,129,37,130,131,132],"extraction","voice","voice extraction","writing","learn","content","analyze","parallel","extract","subagents","engineer","study","me",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":148,"publishedAt":47},"01M6DKPZAQ4NTERXENEFKFACZZ","visual-style","Build a persistent visual brand identity for image generation. Defines how the brand looks visually — aesthetic, lighting, composition, mood — and writes it to brand\u002Fcreative-kit.md so \u002Fimage-gen and other creative skills produce consistent on-brand visuals. Three modes: Extract (from website\u002FURL), Build (interview), Reference (mood board\u002Fexamples). Use when starting any project that needs images, when the user says \"visual style\", \"brand aesthetic\", \"image style\", \"visual identity\", \"how should our images look\", \"build visual brand\", \"define our look\", or when \u002Fimage-gen outputs feel generic because no visual style exists yet.","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-style\u002FSKILL.md",[139,142,145],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":143,"categoryName":144,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":146,"categoryName":147,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000032","设计师",[149,150,151,152,153,154,155,156,157,158,40,159,37,160,161,162,163,164,165,166],"visual","style","visual style","image","identity","visuals","produce","website","Composition","how","interview","images","aesthetic","three","lighting","positioning","project","define",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":182,"publishedAt":47},"01M6DKPR2K3YJ1MAJG8XT815VP","video-content","Three-tier video pipeline: ffmpeg Quick (5s, instant) → ffmpeg Enhanced with Ken Burns (15s, polished) → Remotion Animated (60-90s, production-grade). Takes static slides from Paper MCP or any PNGs and assembles them into platform-ready video. Make sure to use this skill whenever the user has slides, images, or PNGs and wants to turn them into video — even if they just say 'make a video from these', 'animate my slides', 'I have images and need a TikTok', or 'stitch these together'. Also use when they mention ffmpeg video assembly, Remotion-animated slide assembly, Ken Burns effects, or any slides-to-video pipeline. Owns the slides→MP4 assembly pipeline; for writing, debugging, or running `remotion render` on Remotion code itself, see \u002Fremotion-best-practices; for screen-recorded product demos, see \u002Fmarketing-demo. Works with any PNG source — Paper exports, Canva, screenshots, anything.","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-content\u002FSKILL.md",[173,174,177,178,181],{"categoryNo":143,"categoryName":144,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":175,"categoryName":176,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":179,"categoryName":180,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000035","市场营销",{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},[125,183,184,185,123,186,187,188,189,190,191,43,192,193,194,195,160,196,197,198],"Video","video content","MCP","status","debugging","code","product","pipeline","Remotion","marketing","instant","assemble","ready","stitch","tiktok","screen",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":210,"publishedAt":47},"01M6DKPKDPTV6JFSW4SK3CKQCH","typefully","Create, schedule, and manage social media posts via Typefully. ALWAYS use this skill when asked to draft, schedule, post, or check tweets, posts, threads, or social media content for Twitter\u002FX, LinkedIn, Threads, Bluesky, or Mastodon.","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Ftypefully\u002FSKILL.md",[205,206,207,208,209],{"categoryNo":140,"categoryName":141,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":175,"categoryName":176,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":146,"categoryName":147,"taxonomyType":117,"taxonomyTypeDesc":118},{"categoryNo":179,"categoryName":180,"taxonomyType":117,"taxonomyTypeDesc":118},[201,211,212,213,43,192,121,40,214,215,216,217,218,37,219,220,221,222,223,224],"create","SET","Media","schedule","twitter","linkedin","social media","check","manage","bluesky","social","draft","distribution","scripts",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":229,"categories":230,"keywords":235,"publishedAt":47},"01M6DKP7X0YHAK9QZ1ZRKFQ596","tiktok-slideshow","Orchestrator skill that chains \u002Fslideshow-script → \u002Fpaper-marketing → \u002Fvideo-content for end-to-end TikTok slideshow production. Each phase is an independent Lego block — this orchestrator is just one recipe that combines them. Produces 5 publishable TikTok videos from a single positioning angle. Triggers on \"TikTok slideshow\", \"TikTok video\", \"make TikTok\", \"slideshow video\", \"TikTok content\".","https:\u002F\u002Fgithub.com\u002FMoizIbnYousaf\u002Fmarketing-cli\u002Fblob\u002Fmain\u002Fskills\u002Ftiktok-slideshow\u002FSKILL.md",[231,232,233,234],{"categoryNo":143,"categoryName":144,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":175,"categoryName":176,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":179,"categoryName":180,"taxonomyType":117,"taxonomyTypeDesc":118},[197,236,186,125,237,183,191,43,192,238,239,240,164,241,242,243,244],"tiktok slideshow","Production","just","orchestrator","bun","end","triggers","ffmpeg","paper"]