[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DAE88FP9G2EHQZHHXRYZ0H":3,"skill-same:01M6DAE88FP9G2EHQZHHXRYZ0H":59},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":58},"01M6DAE88FP9G2EHQZHHXRYZ0H","crosspost",null,"Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Fcrosspost\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32],"content","engine","linkedin","user","use","never","bluesky","patterns","social","cross-platform","across","platform","distribute","distribution","2026-11-10 10:12:30",false,"---\nname: crosspost\ndescription: Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.\norigin: ECC\n---\n\n# Crosspost\n\nDistribute content across multiple social platforms with platform-native adaptation.\n\n## When to Activate\n\n- User wants to post content to multiple platforms\n- Publishing announcements, launches, or updates across social media\n- Repurposing a post from one platform to others\n- User says \"crosspost\", \"post everywhere\", \"share on all platforms\", or \"distribute this\"\n\n## Core Rules\n\n1. **Never post identical content cross-platform.** Each platform gets a native adaptation.\n2. **Primary platform first.** Post to the main platform, then adapt for others.\n3. **Respect platform conventions.** Length limits, formatting, link handling all differ.\n4. **One idea per post.** If the source content has multiple ideas, split across posts.\n5. **Attribution matters.** If crossposting someone else's content, credit the source.\n\n## Platform Specifications\n\n| Platform | Max Length | Link Handling | Hashtags | Media |\n|----------|-----------|---------------|----------|-------|\n| X | 280 chars (4000 for Premium) | Counted in length | Minimal (1-2 max) | Images, video, GIFs |\n| LinkedIn | 3000 chars | Not counted in length | 3-5 relevant | Images, video, docs, carousels |\n| Threads | 500 chars | Separate link attachment | None typical | Images, video |\n| Bluesky | 300 chars | Via facets (rich text) | None (use feeds) | Images |\n\n## Workflow\n\n### Step 1: Create Source Content\n\nStart with the core idea. Use `content-engine` skill for high-quality drafts:\n- Identify the single core message\n- Determine the primary platform (where the audience is biggest)\n- Draft the primary platform version first\n\n### Step 2: Identify Target Platforms\n\nAsk the user or determine from context:\n- Which platforms to target\n- Priority order (primary gets the best version)\n- Any platform-specific requirements (e.g., LinkedIn needs professional tone)\n\n### Step 3: Adapt Per Platform\n\nFor each target platform, transform the content:\n\n**X adaptation:**\n- Open with a hook, not a summary\n- Cut to the core insight fast\n- Keep links out of main body when possible\n- Use thread format for longer content\n\n**LinkedIn adaptation:**\n- Strong first line (visible before \"see more\")\n- Short paragraphs with line breaks\n- Frame around lessons, results, or professional takeaways\n- More explicit context than X (LinkedIn audience needs framing)\n\n**Threads adaptation:**\n- Conversational, casual tone\n- Shorter than LinkedIn, less compressed than X\n- Visual-first if possible\n\n**Bluesky adaptation:**\n- Direct and concise (300 char limit)\n- Community-oriented tone\n- Use feeds\u002Flists for topic targeting instead of hashtags\n\n### Step 4: Post Primary Platform\n\nPost to the primary platform first:\n- Use `x-api` skill for X\n- Use platform-specific APIs or tools for others\n- Capture the post URL for cross-referencing\n\n### Step 5: Post to Secondary Platforms\n\nPost adapted versions to remaining platforms:\n- Stagger timing (not all at once — 30-60 min gaps)\n- Include cross-platform references where appropriate (\"longer thread on X\" etc.)\n\n## Content Adaptation Examples\n\n### Source: Product Launch\n\n**X version:**\n```\nWe just shipped [feature].\n\n[One specific thing it does that's impressive]\n\n[Link]\n```\n\n**LinkedIn version:**\n```\nExcited to share: we just launched [feature] at [Company].\n\nHere's why it matters:\n\n[2-3 short paragraphs with context]\n\n[Takeaway for the audience]\n\n[Link]\n```\n\n**Threads version:**\n```\njust shipped something cool — [feature]\n\n[casual explanation of what it does]\n\nlink in bio\n```\n\n### Source: Technical Insight\n\n**X version:**\n```\nTIL: [specific technical insight]\n\n[Why it matters in one sentence]\n```\n\n**LinkedIn version:**\n```\nA pattern I've been using that's made a real difference:\n\n[Technical insight with professional framing]\n\n[How it applies to teams\u002Forgs]\n\n#relevantHashtag\n```\n\n## API Integration\n\n### Batch Crossposting Service (Example Pattern)\nIf using a crossposting service (e.g., Postbridge, Buffer, or a custom API), the pattern looks like:\n\n```python\nimport os\nimport requests\n\nresp = requests.post(\n    \"https:\u002F\u002Fyour-crosspost-service.example\u002Fapi\u002Fposts\",\n    headers={\"Authorization\": f\"Bearer {os.environ['POSTBRIDGE_API_KEY']}\"},\n    json={\n        \"platforms\": [\"twitter\", \"linkedin\", \"threads\"],\n        \"content\": {\n            \"twitter\": {\"text\": x_version},\n            \"linkedin\": {\"text\": linkedin_version},\n            \"threads\": {\"text\": threads_version}\n        }\n    },\n    timeout=30,\n)\nresp.raise_for_status()\n```\n\n### Manual Posting\nWithout Postbridge, post to each platform using its native API:\n- X: Use `x-api` skill patterns\n- LinkedIn: LinkedIn API v2 with OAuth 2.0\n- Threads: Threads API (Meta)\n- Bluesky: AT Protocol API\n\n## Quality Gate\n\nBefore posting:\n- [ ] Each platform version reads naturally for that platform\n- [ ] No identical content across platforms\n- [ ] Length limits respected\n- [ ] Links work and are placed appropriately\n- [ ] Tone matches platform conventions\n- [ ] Media is sized correctly for each platform\n\n## Related Skills\n\n- `content-engine` — Generate platform-native content\n- `x-api` — X\u002FTwitter API integration\n","# Crosspost\n\nDistribute content across multiple social platforms with platform-native adaptation.\n\n## When to Activate\n\n- User wants to post content to multiple platforms\n- Publishing announcements, launches, or updates across social media\n- Repurposing a post from one platform to others\n- User says \"crosspost\", \"post everywhere\", \"share on all platforms\", or \"distribute this\"\n\n## Core Rules\n\n1. **Never post identical content cross-platform.** Each platform gets a native adaptation.\n2. **Primary platform first.** Post to the main platform, then adapt for others.\n3. **Respect platform conventions.** Length limits, formatting, link handling all differ.\n4. **One idea per post.** If the source content has multiple ideas, split across posts.\n5. **Attribution matters.** If crossposting someone else's content, credit the source.\n\n## Platform Specifications\n\n| Platform | Max Length | Link Handling | Hashtags | Media |\n|----------|-----------|---------------|----------|-------|\n| X | 280 chars (4000 for Premium) | Counted in length | Minimal (1-2 max) | Images, video, GIFs |\n| LinkedIn | 3000 chars | Not counted in length | 3-5 relevant | Images, video, docs, carousels |\n| Threads | 500 chars | Separate link attachment | None typical | Images, video |\n| Bluesky | 300 chars | Via facets (rich text) | None (use feeds) | Images |\n\n## Workflow\n\n### Step 1: Create Source Content\n\nStart with the core idea. Use `content-engine` skill for high-quality drafts:\n- Identify the single core message\n- Determine the primary platform (where the audience is biggest)\n- Draft the primary platform version first\n\n### Step 2: Identify Target Platforms\n\nAsk the user or determine from context:\n- Which platforms to target\n- Priority order (primary gets the best version)\n- Any platform-specific requirements (e.g., LinkedIn needs professional tone)\n\n### Step 3: Adapt Per Platform\n\nFor each target platform, transform the content:\n\n**X adaptation:**\n- Open with a hook, not a summary\n- Cut to the core insight fast\n- Keep links out of main body when possible\n- Use thread format for longer content\n\n**LinkedIn adaptation:**\n- Strong first line (visible before \"see more\")\n- Short paragraphs with line breaks\n- Frame around lessons, results, or professional takeaways\n- More explicit context than X (LinkedIn audience needs framing)\n\n**Threads adaptation:**\n- Conversational, casual tone\n- Shorter than LinkedIn, less compressed than X\n- Visual-first if possible\n\n**Bluesky adaptation:**\n- Direct and concise (300 char limit)\n- Community-oriented tone\n- Use feeds\u002Flists for topic targeting instead of hashtags\n\n### Step 4: Post Primary Platform\n\nPost to the primary platform first:\n- Use `x-api` skill for X\n- Use platform-specific APIs or tools for others\n- Capture the post URL for cross-referencing\n\n### Step 5: Post to Secondary Platforms\n\nPost adapted versions to remaining platforms:\n- Stagger timing (not all at once — 30-60 min gaps)\n- Include cross-platform references where appropriate (\"longer thread on X\" etc.)\n\n## Content Adaptation Examples\n\n### Source: Product Launch\n\n**X version:**\n```\nWe just shipped [feature].\n\n[One specific thing it does that's impressive]\n\n[Link]\n```\n\n**LinkedIn version:**\n```\nExcited to share: we just launched [feature] at [Company].\n\nHere's why it matters:\n\n[2-3 short paragraphs with context]\n\n[Takeaway for the audience]\n\n[Link]\n```\n\n**Threads version:**\n```\njust shipped something cool — [feature]\n\n[casual explanation of what it does]\n\nlink in bio\n```\n\n### Source: Technical Insight\n\n**X version:**\n```\nTIL: [specific technical insight]\n\n[Why it matters in one sentence]\n```\n\n**LinkedIn version:**\n```\nA pattern I've been using that's made a real difference:\n\n[Technical insight with professional framing]\n\n[How it applies to teams\u002Forgs]\n\n#relevantHashtag\n```\n\n## API Integration\n\n### Batch Crossposting Service (Example Pattern)\nIf using a crossposting service (e.g., Postbridge, Buffer, or a custom API), the pattern looks like:\n\n```python\nimport os\nimport requests\n\nresp = requests.post(\n    \"https:\u002F\u002Fyour-crosspost-service.example\u002Fapi\u002Fposts\",\n    headers={\"Authorization\": f\"Bearer {os.environ['POSTBRIDGE_API_KEY']}\"},\n    json={\n        \"platforms\": [\"twitter\", \"linkedin\", \"threads\"],\n        \"content\": {\n            \"twitter\": {\"text\": x_version},\n            \"linkedin\": {\"text\": linkedin_version},\n            \"threads\": {\"text\": threads_version}\n        }\n    },\n    timeout=30,\n)\nresp.raise_for_status()\n```\n\n### Manual Posting\nWithout Postbridge, post to each platform using its native API:\n- X: Use `x-api` skill patterns\n- LinkedIn: LinkedIn API v2 with OAuth 2.0\n- Threads: Threads API (Meta)\n- Bluesky: AT Protocol API\n\n## Quality Gate\n\nBefore posting:\n- [ ] Each platform version reads naturally for that platform\n- [ ] No identical content across platforms\n- [ ] Length limits respected\n- [ ] Links work and are placed appropriately\n- [ ] Tone matches platform conventions\n- [ ] Media is sized correctly for each platform\n\n## Related Skills\n\n- `content-engine` — Generate platform-native content\n- `x-api` — X\u002FTwitter API integration\n",{"name":5,"origin":38,"description":7},"ECC","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Flibrary\u002Fskills\u002Fcrosspost","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill crosspost",{"tool":51,"command":52},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill crosspost",{"tool":54,"command":55},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill crosspost","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Flibrary\u002Fskills\u002Fcrosspost\u002FSKILL.md",true,[],[60,81,112,139,153,168],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":33},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[67,68,69,70,71,72,73,74,75,23,76,77,78,79,80],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":92,"publishedAt":33},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[93,94,95,96,97,98,99,100,101,102,103,104,105,106,23,107,108,109,110,111],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":124,"publishedAt":33},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[118,121],{"categoryNo":119,"categoryName":120,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":122,"categoryName":123,"taxonomyType":90,"taxonomyTypeDesc":91},"01JBSEEDCAT000000000000008","测试与质量",[125,126,127,128,129,130,131,132,133,134,94,135,136,137,138],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":145,"publishedAt":33},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[141,146,147,148,149,150,151,152],"setup","report","project","installation","project setup","issues","state",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":33},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[159],{"categoryNo":88,"categoryName":89,"taxonomyType":90,"taxonomyTypeDesc":91},[155,161,72,162,163,164,23,22,165,166,167],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":169,"name":146,"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":173,"publishedAt":33},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[146,148,109,174,150,175],"files","interactive"]