Skills · category
Research skills and plugins
Public Claude skills and plugins for research, each with Waxell's security verdict and the findings behind it.
- 4,170 reviewed
- 3,045 no issues
- 1,002 to review
- 101 high risk
908 resultsResearch
youtube-transcript-searcharcmiraUse Arcmira to read or summarize a YouTube video from its link, or to search YouTube transcripts across channels: the exact quote and the… Review findingsResearchImages, video & audio35
nblmmagicseekUse this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from… Review findingsResearchData & analytics34
inkassistant-uiBuilds terminal chat UIs with @assistant-ui/react-ink and ANSI markdown with @assistant-ui/react-ink-markdown. Use when scaffolding… Review findingsResearchDesign29
javascript-sdk101-skillsJavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm… Review findingsResearchEngineering28
inference-sh101-skillsAI agent skills for models via inference.sh CLI - generate images with FLUX, create videos with Veo, call LLMs, search the web, and more High riskResearchImages, video & audio28
agent-tools101-skillsRun AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini,… High riskResearchImages, video & audio28
infsh-cli101-skillsRun AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini,… High riskResearchEngineering28
browser-max-automationaktsmmVisible browser automation using available Playwright, CLI, CDP, or computer-use tools with scoped actions and durable verification. Use… High riskResearchDocuments27
powerpoint-automationaktsmmConvert web articles or blog posts into slides through a content.json pipeline, translate or rebuild existing PPTX files onto a template,… High riskResearchDocuments27
x-post-researchaktsmmResearch public X posts from keywords, hashtags, OR queries, domains, or known post URLs, then verify linked primary sources, official… Review findingsResearchData & analytics27
efectopablostanleyEfecto: AI design skills + 46 MCP tools. Create web pages, social media graphics, presentations, and more with AI agents. Review findingsResearchDesign25
jaxtondevrelComposable transformations of Python+NumPy programs. Differentiate, vectorize, JIT-compile to GPU/TPU. Built for high-performance machine… Review findingsResearchEngineering25
pennylanetondevrelCross-platform Python library for differentiable quantum computing. Integrated with machine learning libraries like PyTorch, TensorFlow,… Review findingsResearchEngineering25
plotlytondevrelA high-level interactive graphing library for Python. Ideal for web-based visualizations, 3D plots, and complex interactive dashboards.… Review findingsResearchData & analytics25
pytorchtondevrelLeading deep learning framework. Provides Tensors and Dynamic Computational Graphs with strong GPU acceleration. Widely used for research,… Review findingsResearchEngineering25
qiskittondevrelComprehensive guide for Qiskit - IBM's quantum computing framework. Use for quantum circuit design, quantum algorithms (VQE, QAOA, Grover,… Review findingsResearchDesign25
scikit-biotondevrelLibrary for bioinformatics and community ecology statistics. Provides data structures and algorithms for sequences, alignments,… Review findingsResearchData & analytics25
paper-lookuppracticalswanSearches 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and returns… High riskResearchData & analytics24
tavily-searchpracticalswanSearch the web through Tavily with bounded depth, domains, dates, and result counts. Use when the user needs current information or source… High riskResearchAI & agents24
anti-detect-browserantibrowDrive Chromium from standard Playwright APIs with a real-device fingerprint applied in the kernel, one persistent isolated profile per… Review findingsResearchEngineering21
anti-detect-browser-skillsantibrowDrive a browser that presents one coherent real device: AntiBrow's kernel-level fingerprints, persistent isolated profiles, and… Review findingsResearchEngineering21
multi-account-scrapingantibrowRun the same scrape or task across many accounts at once - each in its own browser profile with its own fingerprint, cookies and exit IP -… Review findingsResearchEngineering21
zhihuacedatacloudSearch Zhihu & the web, get trending topics, and read/publish on Zhihu (知乎), search Zhihu content or the entire web via the official… High riskResearchEngineering17
product-demo-videoiart-aiThis skill should be used when the user asks to "make a product demo video", "create an app demo video", "build a feature announcement… Review findingsResearchImages, video & audio17
momenticmomentic-aiBug bash web and mobile apps with Mo and review findings through Momentic's hosted MCP server. High riskResearchAI & agents17
momenticmomentic-aiBug bash with Mo and write, run and maintain Momentic browser and mobile tests. High riskResearchEngineering17
mo-qamomentic-aiRun and control Mo web and mobile QA with hosted Momentic tools or the qa CLI, including saved environments, mobile builds, private… High riskResearchDocuments17
os-usezrongCross-platform operating system automation and screen control toolkit. Use when users need screenshots, mouse/keyboard control, visual… Review findingsResearchProductivity14
irasutoya-searchmineru98Search and preview Irasutoya illustrations with the installed `irasutoya` command-line tool. Use this skill whenever the user wants to… Review findingsResearchDesign13
irasutoya-searchmineru98Search and preview Irasutoya illustrations with the installed `irasutoya` command-line tool. Use this skill whenever the user wants to… Review findingsResearchDesign13
emblem-ai-agent-walletemblemcompanyConnect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana,… Review findingsResearchProductivity12
emblem-defi-yieldemblemcompanyDeFi yield research and liquid staking via EmblemAI. Discover yield opportunities, compare protocols, check DeFi positions with Nansen,… Review findingsResearchAI & agents12
emblem-market-researchemblemcompanyCrypto market intelligence via EmblemAI. Trending tokens, on-chain analytics, derivatives data, and smart money tracking from CoinGecko,… Review findingsResearchData & analytics12
academic-paper-downloadtiangong-aiFetch and atomically save structurally and identity-verified academic-paper PDFs from legal open-access sources using a DOI or exact… Review findingsResearchAI & agents11
fetch-meta-from-kbtiangong-aiFetch recent `journals` rows directly from PostgreSQL and return a JSON array containing `doi`, `title`, `abstract`, and `date` (filtered… Review findingsResearchDocuments11
notebooklmtiangong-aiNotebookLM CLI wrapper via `python3 {baseDir}/scripts/notebooklm.py` (backed by notebooklm-py). Use for auth, notebooks, chat, sources,… Review findingsResearchEngineering11
coding-agent-docs-optimizationsamberMakes SDK, API or protocol documentation something a coding agent can integrate from unattended - crawler access, machine-readable entry… Review findingsResearchEngineering10
seeker-connectsolana-mobileConnect a web, React Native, or Kotlin dapp to the Seeker device's built-in wallet with Seeker Connect. Use when adding wallet connection,… Review findingsResearchEngineering8
fingerprint-ci-gateliarjsdevGate a build on browser fingerprint regressions with liarjs - save a baseline scan as JSON, diff later runs against it, and fail the job… Review findingsResearchEngineering5
playwright-stealth-verifyliarjsdevCheck whether a Playwright, Puppeteer, Selenium or CDP-driven browser presents a coherent fingerprint, using liarjs as a library against a… Review findingsResearchEngineering5
syncfusion-blazor-smart-rich-text-editorsyncfusionImplements Syncfusion SfSmartRichTextEditor, an AI-enhanced WYSIWYG editor extending SfRichTextEditor in Blazor. Use this when configuring… High riskResearchDesign4
connector-xcaffeinelabsMANDATORY recipe for every Caffeine build that posts to or reads from X (Twitter) from a canister: tweets, replies, reposts, quote posts,… Review findingsResearchEngineering2
extension-inferencecaffeinelabsMANDATORY recipe for every Caffeine build that calls an LLM, chatbot, GPT, or ChatGPT **on Caffeine Inference** (no user-pasted OpenAI… Review findingsResearchEngineering2
agent-pulsejane-o-o-o-oUse Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code, Codex, DeepSeek, OpenClaw, Copilot, Aider, Qwen, OpenCode,… Review findingsResearchEngineering1
See and control which skills your people use
Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.
30 minutes. No commitment.
SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF