[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DF0D1ZEJTBJTCPAEXVTFH1":3,"skill-same:01M6DF0D1ZEJTBJTCPAEXVTFH1":204},{"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":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6DF0D1ZEJTBJTCPAEXVTFH1","tiktok-public-research",null,"Use when the user wants to read PUBLIC TikTok data - trending videos, a creator's public posts or likes, a hashtag feed, a single video's metadata or comments, related videos, or a user search - through the self-hosted tiktok MCP server. Covers the read-only tool inventory, the ms_token and residential-proxy reliability knobs, and the hard limits (no own feed, no saved, no DMs, no posting).","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\u002Fskills\u002Ftiktok-public-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],"tiktok public research","research","tiktok","public","read","posting","self","self-hosted","only","ms","reliability","use","MCP","tool","Video","inventory","server","proxy","search","mcp server","2026-11-10 10:12:30",false,"---\nname: tiktok-public-research\ndescription: Use when the user wants to read PUBLIC TikTok data - trending videos, a creator's public posts or likes, a hashtag feed, a single video's metadata or comments, related videos, or a user search - through the self-hosted tiktok MCP server. Covers the read-only tool inventory, the ms_token and residential-proxy reliability knobs, and the hard limits (no own feed, no saved, no DMs, no posting).\n---\n\n# TikTok public-research MCP (`tiktok`)\n\nRead-only access to **public** TikTok data via the self-hosted `tiktok` MCP server\n(`~\u002Fsource\u002Frepos\u002Ftiktok-mcp`, a FastMCP wrapper over `davidteather\u002FTikTok-Api` 7.3.3).\nSame self-hosted ethos as the other social MCPs — but **public-scrape only, no login**.\n\n## Core principle\nThere is **no authentication**. The server logs into nothing and exposes nothing about\nyour account. An optional `ms_token` (an anti-bot cookie copied from a logged-in\n`tiktok.com` session) and an optional residential proxy only make the *scraper* look less\nbot-like — they are **not** credentials and do **not** unlock private data. Everything this\nserver reads is data any logged-out visitor could see.\n\n## Tools (all read-only, public data)\n| Tool | Reads | Notes |\n|---|---|---|\n| `tiktok_trending(count)` | trending feed | works **keyless**; geo-localized to the egress IP\u002Fproxy |\n| `tiktok_user_info(username)` | a creator's public profile + stats | needs `ms_token` (keyless 403s) |\n| `tiktok_user_posts(username, count)` | a creator's public posts | needs `ms_token` |\n| `tiktok_user_liked(username, count)` | a creator's public likes | only if that user made likes public (usually empty) |\n| `tiktok_hashtag(tag, count)` | recent videos for a hashtag | needs `ms_token` |\n| `tiktok_video_details(url_or_id)` | one video's metadata | URL preferred over numeric id |\n| `tiktok_comments(url_or_id, count)` | top-level comments on a video | needs `ms_token` |\n| `tiktok_related_videos(url_or_id, count)` | videos TikTok relates to one video | needs `ms_token` |\n| `tiktok_search_users(query, count)` | public user accounts by name | **user search only** — 7.x has no generic video search |\n\n`count` is clamped to `[1, 50]`. Errors come back structured (`{error, detail, hint}`),\nnever as a crash.\n\n## Reliability — the real constraint (not code, bot-detection)\n- **`tiktok_trending` works with no setup.** Every other tool typically returns\n  `EmptyResponseException` **until an `ms_token` is set** — TikTok bot-walls user\u002Fhashtag\u002F\n  video\u002Fcomment endpoints for an unauthenticated scraper. This is expected, not a bug.\n- **`TIKTOK_MS_TOKEN`** — copy the `msToken` cookie value from a logged-in `tiktok.com`\n  browser session into the gitignored `.env` (or pass via `claude mcp add -e`). Refresh it\n  if calls start returning empty. It is a nonce, not a login — but treat it as private\n  (gitignored, never logged, never committed).\n- **`TIKTOK_PROXY`** (a residential proxy URL) — **required on a datacenter\u002Fcloud egress IP**\n  (TikTok blocks datacenter IPs almost instantly). **Not needed on a home residential IP.**\n  Same rule and same Byteful sticky-RO endpoint used for IG\u002FFB on cloud egress.\n- **`TIKTOK_BROWSER`** — `chromium` (default), `webkit`, or `firefox`. A different engine\n  sometimes evades detection; webkit alone did **not** fix the keyless user\u002Fhashtag block in\n  testing, so reach for `ms_token` first.\n\n## Hard limits (state them, never imply otherwise)\n- **No own-account data:** your feed, your saved\u002Ffavorites, your following, your likes — none\n  are reachable (there's no session). For your *own* posts\u002Fprofile use the official Display\n  API instead, not this scraper.\n- **No DMs** — no unofficial library exposes the TikTok message inbox; do not imply DM search.\n- **No writes** — no posting, liking, following, commenting. Read-only by construction.\n- **Unofficial-API risk:** heavy scraping from one IP gets that **IP** blocked\n  (`EmptyResponseException`); it does **not** ban a TikTok *account* (nothing is logged in).\n  Keep usage human-paced.\n\n## Setup\nServer: `~\u002Fsource\u002Frepos\u002Ftiktok-mcp` (Python 3.12 `.venv`, `TikTokApi` + `mcp[cli]`, Playwright\nchromium\u002Fwebkit installed). Registered user-scope as `tiktok`:\n```\nclaude mcp add tiktok --scope user -e TIKTOK_MS_TOKEN=\u003CmsToken> -- ^\n  C:\\source\\repos\\tiktok-mcp\\.venv\\Scripts\\python.exe C:\\source\\repos\\tiktok-mcp\\server.py\n```\nTools load on the next Claude Code restart. Per the toolchain's MCP policy, consider adding\n`tiktok` to each project's `disabledMcpServers` and enabling it only where needed (same as the\ndrug MCPs). Full build\u002Fsetup detail: `docs\u002Fsocial\u002FTIKTOK-MCP.md`.\n\nPairs with the broader social MCP reference: [[social-media-toolchain]].\n","# TikTok public-research MCP (`tiktok`)\n\nRead-only access to **public** TikTok data via the self-hosted `tiktok` MCP server\n(`~\u002Fsource\u002Frepos\u002Ftiktok-mcp`, a FastMCP wrapper over `davidteather\u002FTikTok-Api` 7.3.3).\nSame self-hosted ethos as the other social MCPs — but **public-scrape only, no login**.\n\n## Core principle\nThere is **no authentication**. The server logs into nothing and exposes nothing about\nyour account. An optional `ms_token` (an anti-bot cookie copied from a logged-in\n`tiktok.com` session) and an optional residential proxy only make the *scraper* look less\nbot-like — they are **not** credentials and do **not** unlock private data. Everything this\nserver reads is data any logged-out visitor could see.\n\n## Tools (all read-only, public data)\n| Tool | Reads | Notes |\n|---|---|---|\n| `tiktok_trending(count)` | trending feed | works **keyless**; geo-localized to the egress IP\u002Fproxy |\n| `tiktok_user_info(username)` | a creator's public profile + stats | needs `ms_token` (keyless 403s) |\n| `tiktok_user_posts(username, count)` | a creator's public posts | needs `ms_token` |\n| `tiktok_user_liked(username, count)` | a creator's public likes | only if that user made likes public (usually empty) |\n| `tiktok_hashtag(tag, count)` | recent videos for a hashtag | needs `ms_token` |\n| `tiktok_video_details(url_or_id)` | one video's metadata | URL preferred over numeric id |\n| `tiktok_comments(url_or_id, count)` | top-level comments on a video | needs `ms_token` |\n| `tiktok_related_videos(url_or_id, count)` | videos TikTok relates to one video | needs `ms_token` |\n| `tiktok_search_users(query, count)` | public user accounts by name | **user search only** — 7.x has no generic video search |\n\n`count` is clamped to `[1, 50]`. Errors come back structured (`{error, detail, hint}`),\nnever as a crash.\n\n## Reliability — the real constraint (not code, bot-detection)\n- **`tiktok_trending` works with no setup.** Every other tool typically returns\n  `EmptyResponseException` **until an `ms_token` is set** — TikTok bot-walls user\u002Fhashtag\u002F\n  video\u002Fcomment endpoints for an unauthenticated scraper. This is expected, not a bug.\n- **`TIKTOK_MS_TOKEN`** — copy the `msToken` cookie value from a logged-in `tiktok.com`\n  browser session into the gitignored `.env` (or pass via `claude mcp add -e`). Refresh it\n  if calls start returning empty. It is a nonce, not a login — but treat it as private\n  (gitignored, never logged, never committed).\n- **`TIKTOK_PROXY`** (a residential proxy URL) — **required on a datacenter\u002Fcloud egress IP**\n  (TikTok blocks datacenter IPs almost instantly). **Not needed on a home residential IP.**\n  Same rule and same Byteful sticky-RO endpoint used for IG\u002FFB on cloud egress.\n- **`TIKTOK_BROWSER`** — `chromium` (default), `webkit`, or `firefox`. A different engine\n  sometimes evades detection; webkit alone did **not** fix the keyless user\u002Fhashtag block in\n  testing, so reach for `ms_token` first.\n\n## Hard limits (state them, never imply otherwise)\n- **No own-account data:** your feed, your saved\u002Ffavorites, your following, your likes — none\n  are reachable (there's no session). For your *own* posts\u002Fprofile use the official Display\n  API instead, not this scraper.\n- **No DMs** — no unofficial library exposes the TikTok message inbox; do not imply DM search.\n- **No writes** — no posting, liking, following, commenting. Read-only by construction.\n- **Unofficial-API risk:** heavy scraping from one IP gets that **IP** blocked\n  (`EmptyResponseException`); it does **not** ban a TikTok *account* (nothing is logged in).\n  Keep usage human-paced.\n\n## Setup\nServer: `~\u002Fsource\u002Frepos\u002Ftiktok-mcp` (Python 3.12 `.venv`, `TikTokApi` + `mcp[cli]`, Playwright\nchromium\u002Fwebkit installed). Registered user-scope as `tiktok`:\n```\nclaude mcp add tiktok --scope user -e TIKTOK_MS_TOKEN=\u003CmsToken> -- ^\n  C:\\source\\repos\\tiktok-mcp\\.venv\\Scripts\\python.exe C:\\source\\repos\\tiktok-mcp\\server.py\n```\nTools load on the next Claude Code restart. Per the toolchain's MCP policy, consider adding\n`tiktok` to each project's `disabledMcpServers` and enabling it only where needed (same as the\ndrug MCPs). Full build\u002Fsetup detail: `docs\u002Fsocial\u002FTIKTOK-MCP.md`.\n\nPairs with the broader social MCP reference: [[social-media-toolchain]].\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Ftiktok-public-research","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill tiktok-public-research",{"tool":64,"command":65},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill tiktok-public-research",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill tiktok-public-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Ftiktok-public-research\u002FSKILL.md",true,[72,78,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180,184,188,192,196,200],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},".DS_Store","OTHER","其他",6148,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002F.DS_Store",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"agents\u002Fopenai.yaml","REFERENCE","参考文档",221,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Fagents\u002Fopenai.yaml",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fapp-wiring.md",6637,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fapp-wiring.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fasync-state.md",2833,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fasync-state.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fcomponents-index.md",4303,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fcomponents-index.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fcontrols.md",1682,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fcontrols.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fdeeplinks.md",1703,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fdeeplinks.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Ffocus.md",2390,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Ffocus.md",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fform.md",3062,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fform.md",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Fgrids.md",1851,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fgrids.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Fhaptics.md",2049,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fhaptics.md",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Finput-toolbar.md",1451,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Finput-toolbar.md",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Flightweight-clients.md",2524,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Flightweight-clients.md",{"path":129,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":130,"sourceHtmlUrl":131},"references\u002Flist.md",2732,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Flist.md",{"path":133,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":134,"sourceHtmlUrl":135},"references\u002Floading-placeholders.md",1274,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Floading-placeholders.md",{"path":137,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Fmacos-settings.md",1997,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fmacos-settings.md",{"path":141,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Fmatched-transitions.md",1674,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fmatched-transitions.md",{"path":145,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Fmedia.md",2040,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fmedia.md",{"path":149,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":150,"sourceHtmlUrl":151},"references\u002Fmenu-bar.md",2236,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fmenu-bar.md",{"path":153,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":154,"sourceHtmlUrl":155},"references\u002Fnavigationstack.md",4343,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fnavigationstack.md",{"path":157,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":158,"sourceHtmlUrl":159},"references\u002Foverlay.md",1238,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Foverlay.md",{"path":161,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":162,"sourceHtmlUrl":163},"references\u002Fperformance.md",1990,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fperformance.md",{"path":165,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":166,"sourceHtmlUrl":167},"references\u002Fpreviews.md",1688,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fpreviews.md",{"path":169,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":170,"sourceHtmlUrl":171},"references\u002Fscroll-reveal.md",5299,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fscroll-reveal.md",{"path":173,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":174,"sourceHtmlUrl":175},"references\u002Fscrollview.md",2364,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fscrollview.md",{"path":177,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":178,"sourceHtmlUrl":179},"references\u002Fsearchable.md",1727,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fsearchable.md",{"path":181,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":182,"sourceHtmlUrl":183},"references\u002Fsheets.md",4272,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fsheets.md",{"path":185,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":186,"sourceHtmlUrl":187},"references\u002Fsplit-views.md",2027,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Fsplit-views.md",{"path":189,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":190,"sourceHtmlUrl":191},"references\u002Ftabview.md",3486,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Ftabview.md",{"path":193,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":194,"sourceHtmlUrl":195},"references\u002Ftheming.md",1776,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Ftheming.md",{"path":197,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":198,"sourceHtmlUrl":199},"references\u002Ftitle-menus.md",2115,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Ftitle-menus.md",{"path":201,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":202,"sourceHtmlUrl":203},"references\u002Ftop-bar.md",1359,"https:\u002F\u002Fgithub.com\u002Fagency-black\u002FSkills\u002Fblob\u002Fmain\u002FCopia de swiftui-ui-patterns\u002Freferences\u002Ftop-bar.md",[205,226,251,278,292,308],{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":211,"publishedAt":47},"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",[],[212,213,214,215,216,217,218,219,220,38,221,222,223,224,225],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":233,"publishedAt":47},"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",[232],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[234,235,236,237,238,239,40,240,241,242,243,244,245,246,38,247,248,249,250,39],"openmm md","how","decision","pick","linux","analyze","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do",{"skillNo":252,"name":253,"nameZh":6,"description":254,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":255,"categories":256,"keywords":263,"publishedAt":47},"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",[257,260],{"categoryNo":258,"categoryName":259,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":261,"categoryName":262,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[264,265,266,267,268,269,270,271,272,273,235,274,275,276,277],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":279,"name":280,"nameZh":6,"description":281,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":282,"categories":283,"keywords":284,"publishedAt":47},"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",[],[280,285,286,287,288,289,290,291],"setup","report","project","installation","project setup","issues","state",{"skillNo":293,"name":294,"nameZh":6,"description":295,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":296,"categories":297,"keywords":299,"publishedAt":47},"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",[298],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[294,300,217,301,302,303,38,304,305,306,307],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":309,"name":285,"nameZh":6,"description":310,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":311,"categories":312,"keywords":313,"publishedAt":47},"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",[],[285,287,249,314,289,315],"files","interactive"]