[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-bytedance-claude-to-deerflow-ar":3,"guides-for-bytedance-claude-to-deerflow":242,"similar-k17e05w840mc0qc6pves9w7995866k14":243},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":189,"isFallback":194,"parentExtension":195,"providers":196,"relations":201,"repo":203,"workflow":239},1778053100136.2402,"k17e05w840mc0qc6pves9w7995866k14",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.",{},"Claude to DeerFlow","https://github.com/bytedance/deer-flow/tree/HEAD/skills/public/claude-to-deerflow",[15,16,17,18,19,20],"deerflow","api","http","agent","bash","python",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":178,"workflow":187},1778053169012.8123,"kn7eeh4nyxp3q9gt5px8vftyg1867kep","en",{"checks":26,"evaluatedAt":168,"extensionSummary":169,"promptVersionExtension":170,"promptVersionScoring":171,"rationale":172,"score":173,"summary":174,"tags":175,"targetMarket":176,"tier":177},[27,32,35,38,42,45,49,53,56,59,63,68,71,75,78,81,84,87,90,93,97,101,105,110,114,117,120,123,127,130,133,136,139,142,146,149,152,155,158,161,165],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly states the problem it addresses: interacting with the DeerFlow AI agent platform via its HTTP API for various research, analysis, and management tasks.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","This skill offers significant value beyond a simple API wrapper by providing structured operations, managing threads, handling file uploads, and offering different interaction modes ('flash', 'standard', 'pro', 'ultra'), which would be complex to replicate manually.",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The skill is production-ready, with detailed operational guidance, environment variable configuration, usage examples via a bash script, and clear error handling instructions.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The skill's scope is focused on interacting with the DeerFlow API for its defined operations, not extending into unrelated domains.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The description is concise, readable, and accurately reflects the capabilities described in the SKILL.md file.",{"category":46,"check":47,"severity":30,"summary":48},"Invocation","Scoped tools","The operations are exposed as distinct functionalities (e.g., 'health check', 'list models', 'upload files') rather than a single generalist execution tool.",{"category":50,"check":51,"severity":30,"summary":52},"Documentation","Configuration & parameter reference","Environment variables for API URLs are clearly documented with defaults and descriptions. The different modes and their context implications are also well-explained.",{"category":39,"check":54,"severity":30,"summary":55},"Tool naming","The operations are described clearly in natural language within the SKILL.md, corresponding to API endpoints, which are implicitly well-named.",{"category":39,"check":57,"severity":30,"summary":58},"Minimal I/O surface","The inputs for operations (e.g., thread IDs, message content, file paths) are specific, and the outputs are generally structured or described as streaming events, minimizing extraneous data.",{"category":60,"check":61,"severity":30,"summary":62},"License","License usability","The extension is licensed under the MIT License, which is a permissive open-source license.",{"category":64,"check":65,"severity":66,"summary":67},"Maintenance","Commit recency","not_applicable","The commit date is not available, so recency cannot be evaluated.",{"category":64,"check":69,"severity":66,"summary":70},"Dependency Management","No third-party dependencies are explicitly managed or listed for this skill itself; it relies on the DeerFlow runtime.",{"category":72,"check":73,"severity":66,"summary":74},"Security","Secret Management","This skill does not handle or echo secrets; it relies on the DeerFlow runtime for authentication and authorization.",{"category":72,"check":76,"severity":30,"summary":77},"Injection","The skill primarily makes HTTP calls to a configured API and uses bash scripts for client-side operations, with no indication of loading untrusted external code or data as instructions.",{"category":72,"check":79,"severity":30,"summary":80},"Transitive Supply-Chain Grenades","The skill's scripts are contained within the repository and do not fetch remote code or data at runtime for execution. HTTP calls are to the DeerFlow API.",{"category":72,"check":82,"severity":30,"summary":83},"Sandbox Isolation","The skill itself doesn't directly interact with the file system or execute commands in a way that would violate sandbox isolation; it relies on the DeerFlow runtime's sandbox mechanisms.",{"category":72,"check":85,"severity":30,"summary":86},"Sandbox escape primitives","No detached process spawns or deny-retry loops are present in the bundled scripts.",{"category":72,"check":88,"severity":30,"summary":89},"Data Exfiltration","The skill makes outbound calls only to the DeerFlow API endpoints, which are expected and documented. No evidence of confidential data exfiltration.",{"category":72,"check":91,"severity":30,"summary":92},"Hidden Text Tricks","The bundled files do not contain any hidden text tricks, invisible characters, or obfuscation patterns designed to steer the model without curator visibility.",{"category":94,"check":95,"severity":30,"summary":96},"Hooks","Opaque code execution","The bundled scripts are plain bash and Python, with no signs of obfuscation, base64 payloads, or runtime code fetching.",{"category":98,"check":99,"severity":30,"summary":100},"Portability","Structural Assumption","The skill uses environment variables and relative paths for scripts within its own bundle, avoiding assumptions about user project structure.",{"category":102,"check":103,"severity":66,"summary":104},"Trust","Issues Attention","No GitHub issues data is available for this repository.",{"category":106,"check":107,"severity":108,"summary":109},"Versioning","Release Management","warning","There is no manifest version declared in SKILL.md, package.json, or other standard locations, and no GitHub releases or CHANGELOG are present. Install instructions reference HEAD.",{"category":111,"check":112,"severity":30,"summary":113},"Code Execution","Validation","The bash script uses Python for JSON parsing and argument escaping, and the SSE parsing logic in the Python script includes robust JSON parsing, suggesting validation of inputs and outputs.",{"category":72,"check":115,"severity":30,"summary":116},"Unguarded Destructive Operations","The skill's operations are primarily API interactions and status checks, not destructive operations. File uploads are handled by the DeerFlow API.",{"category":111,"check":118,"severity":30,"summary":119},"Error Handling","The bash script includes robust error handling for health checks and thread creation, and the Python SSE parser explicitly checks for 'error' events. The SKILL.md also provides error handling guidance.",{"category":111,"check":121,"severity":30,"summary":122},"Logging","The bash script uses `>&2` for informational messages, and the Python parsing script prints errors to stderr, providing a form of logging for the execution process. The SKILL.md implies logging via thread history.",{"category":124,"check":125,"severity":66,"summary":126},"Compliance","GDPR","The skill interacts with the DeerFlow API and does not appear to handle personal data directly, nor does it submit data to third parties.",{"category":124,"check":128,"severity":30,"summary":129},"Target market","The extension's functionality is general-purpose and does not appear to be geographically or jurisdictionally restricted, thus targeting a global market.",{"category":98,"check":131,"severity":30,"summary":132},"Runtime stability","The skill relies on standard bash and Python scripts and makes HTTP requests, making it portable across POSIX-compliant environments. It explicitly uses `curl` and `python3`.",{"category":46,"check":134,"severity":30,"summary":135},"Precise Purpose","The description and SKILL.md clearly define the purpose (interact with DeerFlow API) and provide specific triggers and boundaries (e.g., research, analysis, thread management).",{"category":46,"check":137,"severity":30,"summary":138},"Concise Frontmatter","The frontmatter in SKILL.md is concise and clearly states the skill's name and core purpose, followed by trigger phrases.",{"category":50,"check":140,"severity":30,"summary":141},"Concise Body","The SKILL.md is well-structured, uses progressive disclosure for details like architecture and environment variables, and the core operations are presented concisely.",{"category":143,"check":144,"severity":30,"summary":145},"Context","Progressive Disclosure","Details like architecture, environment variables, and API operations are presented clearly within SKILL.md, with bash script examples demonstrating usage.",{"category":143,"check":147,"severity":66,"summary":148},"Forked exploration","This skill is an API client and does not perform deep exploration or code review that would necessitate a forked context.",{"category":28,"check":150,"severity":30,"summary":151},"Usage examples","The SKILL.md provides clear bash script examples for key operations like sending messages and collecting responses, along with a detailed explanation of the SSE output parsing.",{"category":28,"check":153,"severity":30,"summary":154},"Edge cases","The SKILL.md documentation addresses potential issues like DeerFlow not running, stream errors, and common problems like port conflicts, providing guidance on recovery.",{"category":111,"check":156,"severity":66,"summary":157},"Tool Fallback","This skill uses standard tools like `curl` and `python3`. It does not rely on external MCP servers or custom toolkits that would require a fallback.",{"category":98,"check":159,"severity":30,"summary":160},"Stack assumptions","The scripts explicitly use `#!/usr/bin/env bash` and `python3`, and `curl` is a standard utility, indicating clear stack assumptions.",{"category":162,"check":163,"severity":30,"summary":164},"Safety","Halt on unexpected state","The health check in the bash script halts execution if DeerFlow is unreachable, and the Python SSE parser checks for 'error' events, indicating it halts on unexpected states.",{"category":98,"check":166,"severity":66,"summary":167},"Cross-skill coupling","This skill is self-contained and interacts with the DeerFlow API; it does not implicitly rely on or cross-link to other skills.",1778053116070,"This skill provides a direct interface to the DeerFlow AI agent platform's HTTP API. It enables users to send messages, manage conversations and threads, upload files, and query DeerFlow's status, models, and agents through clearly defined operations and a helper bash script.","2.0.0","3.4.0","The 'claude-to-deerflow' skill is exceptionally well-documented and robust. It adheres to all best practices for scope, security, and usability. The only minor point is the lack of a formal versioning signal, which is a common omission for individual skills.",96,"A high-quality skill for interacting with the DeerFlow AI agent platform via its HTTP API.",[15,16,17,18,19,20],"global","verified",{"codeQuality":179,"collectedAt":180,"documentation":181,"maintenance":183,"security":184,"testCoverage":186},{},1778053103954,{"descriptionLength":182,"readmeSize":8},500,{},{"hasNpmPackage":185,"smitheryVerified":185},false,{"hasCi":185,"hasTests":185},{"updatedAt":188},1778053169012,{"githubOwner":190,"githubRepo":191,"locale":24,"slug":192,"type":193},"bytedance","deer-flow","claude-to-deerflow","skill",true,null,{"extract":197,"llm":200},{"commitSha":198,"license":199},"1336872b15c25d45ebcb7c1cf72369c2bdd53187","MIT",{"promptVersionExtension":170,"promptVersionScoring":171,"score":173,"targetMarket":176,"tier":177},{"repoId":202},"kd789sm7egx1h0t1jag6zzhcq98656wv",{"_creationTime":204,"_id":202,"identity":205,"providers":207,"workflow":236},1777995558409.9045,{"githubOwner":190,"githubRepo":191,"sourceUrl":206},"https://github.com/bytedance/deer-flow",{"discover":208,"github":211},{"sources":209},[210],"skills-sh",{"closedIssues90d":212,"forks":213,"homepage":214,"license":199,"openIssues90d":215,"pushedAt":216,"readmeSize":217,"stars":218,"topics":219},389,8629,"https://deerflow.tech",356,1778052455000,38642,65247,[18,220,221,222,223,224,225,226,227,228,229,230,231,20,232,233,234,235],"agentic","agentic-framework","agentic-workflow","ai","ai-agents","deep-research","langchain","langgraph","llm","multi-agent","nodejs","podcast","langmanus","typescript","harness","superagent",{"discoverAt":237,"extractAt":238,"githubAt":238,"updatedAt":238},1777995558409,1778053102364,{"anyEnrichmentAt":240,"extractAt":241,"githubAt":240,"llmAt":188,"updatedAt":188},1778053101076,1778053100136,[],[244,272,300,322,350,381],{"_creationTime":245,"_id":246,"community":247,"display":248,"identity":257,"providers":261,"relations":266,"workflow":268},1778054711476.0596,"k17ed9jy1nygmcqva51bkzyyyd866r6h",{"reviewCount":8},{"description":249,"installMethods":250,"name":251,"sourceUrl":252,"tags":253},"Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify application — including defining routes, implementing plugins, setting up JSON Schema validation, handling errors, optimising performance, managing authentication, configuring CORS and security headers, integrating databases, working with WebSockets, and deploying to production. Covers the full Fastify request lifecycle (hooks, serialization, logging with Pino) and TypeScript integration via strip types. Trigger terms: Fastify, Node.js server, REST API, API routes, backend framework, fastify.config, server.ts, app.ts.",{},"Fastify Best Practices","https://github.com/mcollina/skills/tree/HEAD/skills/fastify",[254,230,233,255,16,256,17],"fastify","backend","server",{"githubOwner":258,"githubRepo":259,"locale":24,"slug":260,"type":193},"mcollina","skills","fastify-best-practices",{"extract":262,"llm":264},{"commitSha":263,"license":199},"5b2a81354b6d10325da0db9decc9ce5ecc714138",{"promptVersionExtension":170,"promptVersionScoring":171,"score":265,"targetMarket":176,"tier":177},98,{"repoId":267},"kd7a9jywzfe3c5g5r1a62htmrn865rt1",{"anyEnrichmentAt":269,"extractAt":270,"githubAt":269,"llmAt":271,"updatedAt":271},1778054711844,1778054711476,1778054745098,{"_creationTime":273,"_id":274,"community":275,"display":276,"identity":285,"providers":288,"relations":293,"workflow":295},1777995614337.9856,"k177fpj38ebtn9tkr8x4kx39xd864dvz",{"reviewCount":8},{"description":277,"name":278,"sourceUrl":279,"tags":280},"TypeScript client for the Tandem autonomous agent engine HTTP + SSE API","Tandem TypeScript Client","https://github.com/frumu-ai/tandem/tree/HEAD/packages/tandem-client-ts",[233,281,16,282,18,283,284],"client","tandem","sdk","node-js",{"githubOwner":286,"githubRepo":282,"locale":24,"slug":287,"type":193},"frumu-ai","frumu-tandem-client",{"extract":289,"llm":291,"smithery":292},{"commitSha":290,"license":199},"25c8ae7c2f8b20d576a2b8d44946ac2e0ff9408d",{"promptVersionExtension":170,"promptVersionScoring":171,"score":265,"targetMarket":176,"tier":177},{"qualityScore":8,"totalActivations":8,"uniqueUsers":8,"useCount":8,"verified":185},{"repoId":294},"kd72pd305er4m7vecv9p6mnd4s865kea",{"anyEnrichmentAt":296,"extractAt":297,"githubAt":298,"llmAt":299,"smitheryAt":296,"updatedAt":299},1777995723550,1777995614338,1777995614791,1777995897177,{"_creationTime":301,"_id":302,"community":303,"display":304,"identity":314,"providers":316,"relations":320,"workflow":321},1778053100136.2437,"k177cymqjd5pwcqq4tk0kek34d867am8",{"reviewCount":8},{"description":305,"installMethods":306,"name":307,"sourceUrl":308,"tags":309},"Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.",{},"GitHub Deep Research Skill","https://github.com/bytedance/deer-flow/tree/HEAD/skills/public/github-deep-research",[310,311,312,16,313,20],"github","research","analysis","report-generation",{"githubOwner":190,"githubRepo":191,"locale":24,"slug":315,"type":193},"github-deep-research",{"extract":317,"llm":318},{"commitSha":198,"license":199},{"promptVersionExtension":170,"promptVersionScoring":171,"score":319,"targetMarket":176,"tier":177},97,{"repoId":202},{"anyEnrichmentAt":240,"extractAt":241,"githubAt":240,"llmAt":188,"updatedAt":188},{"_creationTime":323,"_id":324,"community":325,"display":326,"identity":337,"providers":339,"relations":344,"workflow":346},1778053689272.9238,"k17a5hw81fhwybk1wxavs6mvjs8676ca",{"reviewCount":8},{"description":327,"installMethods":328,"name":329,"sourceUrl":330,"tags":331},"Set up a new Prisma Postgres database and connect it to a local project using the Management API. Use when asked to \"set up a database\", \"create a Prisma Postgres project\", \"get a connection string\", \"connect my app to Prisma Postgres\", or \"provision a database\".",{},"Prisma Postgres Setup","https://github.com/prisma/skills/tree/HEAD/prisma-postgres-setup",[332,333,334,335,336,16,233,284],"prisma","postgres","database","setup","connection",{"githubOwner":332,"githubRepo":259,"locale":24,"slug":338,"type":193},"prisma-postgres-setup",{"extract":340,"llm":342},{"commitSha":341,"license":199},"741a74fdafc1bf61fa208c2f73878be688cba263",{"promptVersionExtension":170,"promptVersionScoring":171,"score":343,"targetMarket":176,"tier":177},99,{"repoId":345},"kd76h7swxyhk8405svecsqq7gh864y5s",{"anyEnrichmentAt":347,"extractAt":348,"githubAt":347,"llmAt":349,"updatedAt":349},1778053689723,1778053689272,1778053716548,{"_creationTime":351,"_id":352,"community":353,"display":354,"identity":367,"providers":370,"relations":375,"workflow":377},1778054070894.8628,"k17antgkdftwdz7cf6tkh5kq65867wht",{"reviewCount":8},{"description":355,"installMethods":356,"name":357,"sourceUrl":358,"tags":359},"Autonomous AI pentester for web apps and APIs. Run white-box security assessments with Shannon — analyzes source code, identifies attack vectors, and executes real exploits to prove vulnerabilities. Triggered by 'shannon', 'pentest', 'security audit', 'vuln scan'.",{},"Shannon Skill","https://github.com/unicodeveloper/shannon",[360,361,362,16,363,364,365,366],"security","pentesting","automation","web","exploit","owasp","docker",{"githubOwner":368,"githubRepo":369,"locale":24,"slug":369,"type":193},"unicodeveloper","shannon",{"extract":371,"llm":374},{"commitSha":372,"license":373},"6a97124bee816c7cc76c6e17bb2b0fe8c0eae032","AGPL-3.0",{"promptVersionExtension":170,"promptVersionScoring":171,"score":265,"targetMarket":176,"tier":177},{"repoId":376},"kd7dk33pc652m4w5wrxaga9qn5865x26",{"anyEnrichmentAt":378,"extractAt":379,"githubAt":378,"llmAt":380,"updatedAt":380},1778054071281,1778054070894,1778054087802,{"_creationTime":382,"_id":383,"community":384,"display":385,"identity":393,"providers":397,"relations":401,"workflow":403},1778053622473.6575,"k179xp8x1d5vrwv3r4m931ed458660q4",{"reviewCount":8},{"description":386,"installMethods":387,"name":388,"sourceUrl":389,"tags":390},"Search the web using Brave Search API for fast, privacy-respecting results with localization, freshness filtering, and extra snippets. Use when you need web search results with country/language targeting or time-based filtering. Requires BRAVE_API_KEY. Keywords: brave, web search, localized search, privacy search, freshness filtering.",{},"Web Search (Brave Search API)","https://github.com/jwynia/agent-skills/tree/HEAD/skills/general/research/tools/web-search-brave",[391,392,311,16],"web-search","brave-search",{"githubOwner":394,"githubRepo":395,"locale":24,"slug":396,"type":193},"jwynia","agent-skills","web-search-brave",{"extract":398,"llm":400},{"commitSha":399,"license":199},"e02ec7e226a6e4f8419fd3b88a1d8e472d421b32",{"promptVersionExtension":170,"promptVersionScoring":171,"score":265,"targetMarket":176,"tier":177},{"repoId":402},"kd7efn3mprpa8rd8vm5hw5ebzx864fph",{"anyEnrichmentAt":404,"extractAt":405,"githubAt":404,"llmAt":406,"updatedAt":406},1778053625386,1778053622473,1778054012696]