Loading...
Loading...
Found 1,544 Skills
Build and deploy an MCP server from an OpenAPI / Swagger spec using the mcp-use TypeScript SDK. Use this skill whenever the user wants to "turn this OpenAPI spec into an MCP server", "make this API usable from Claude/ChatGPT", "wrap this Swagger doc as MCP tools", "expose this REST API to an LLM", "generate MCP tools from a spec", or pastes/attaches an `openapi.yaml`, `openapi.json`, or `swagger.json` and asks for a Claude-compatible version. Trigger even if the user doesn't say "MCP" — if they describe an existing HTTP API (REST endpoints, an internal service, a third-party API they have a key for) and want an LLM to call it, this is the right skill. Covers spec ingestion (file path, URL, or pasted), operation-to-tool mapping, auth wiring (apiKey, bearer, basic, OAuth bearer), scaffolding with `create-mcp-use-app`, tool generation with proper zod schemas, live testing in the mcp-use inspector, and deploying to Manufact / mcp-use cloud.
Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues. Use when training, evaluating, exporting, or running inference for a TAO Optical Inspection model on AOI / quality-control data. Trigger phrases include "train optical inspection", "AOI defect detection", "Siamese defect classifier", "PCB / manufacturing inspection".
Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export. Use when coordinating multi-stage edge research workflows end-to-end.
For users needing to conduct systematic literature reviews, literature reviews, related work, or literature research: AI automatically generates search terms, performs multi-source retrieval → deduplication → AI reads and scores each paper one by one (1–10 points for semantic relevance and sub-topic grouping) → selects papers based on high-score priority ratio → automatically generates word budget for the review (70% cited sections + 30% non-cited sections, average of three samplings) → free writing in the style of senior domain experts (fixed sections: abstract, introduction, sub-topics, discussion, future outlook, conclusion), with strict verification of main text word count and number of references, and mandatory export to PDF and Word. Supports multilingual translation and intelligent compilation (en/zh/ja/de/fr/es).
Search TypeScript SYMBOLS (functions, types, classes) - NOT text. Use Glob to find files, Grep for text search, LSP for symbol search. Provides type-aware results that understand imports, exports, and relationships.
Google Vault: Manage eDiscovery holds and exports.
Test web applications for XML injection vulnerabilities including XXE, XPath injection, and XML entity attacks to identify data exposure and server-side request forgery risks.
Bubble.io plugin development rules, API reference, and coding standards. Use when working on any task in this repo: writing, reviewing, refactoring, or creating initialize.js, update.js, preview.js, header.html, element actions, client-side actions, server-side actions (SSA), Plugin API v4 async/await code, JSDoc, setup files, README, CHANGELOG, marketplace descriptions, or field tooltips. Also use for security audits, code review, debugging, and publishing plugins. Covers instance/properties/context objects, BubbleThing/BubbleList interfaces, data loading suspension, DOM/canvas rules, element vs shared headers, exposed states, event handling, ESLint standards, and Bubble hard limits.
Comprehensive automation for Letterly transcriptions. This skill exports the latest CSV from Letterly, processes "magic" notes into Obsidian markdown with custom metadata, semantically links them using a vector database, and moves them to the final Transcriptions directory. Use when the user asks to "process new letterly transcriptions", "sync letterly", or "import magic notes from letterly".
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model to TAO Toolkit", "wire a HuggingFace ViT/DETR/ SegFormer into tao-pytorch", "build a TAO trainer + deploy pipeline for an HF CV model", or pastes a HuggingFace model URL/ID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy/latency tuning. Supports classification, object detection, semantic / instance / panoptic segmentation, zero-shot detection, and depth estimation.
Shadow platform help — bot-free AI meeting assistant capturing audio + screen on macOS, on-device transcription, autopilot meeting detection, AI summaries/action items/follow-up emails, Skills system for custom post-meeting tasks. Use when setting up Shadow for the first time, Shadow not detecting meetings automatically, Shadow using too much CPU or memory on Mac, Shadow speaker attribution is wrong, Shadow screen capture not working, Shadow free tier ran out of AI meetings, choosing between Shadow and Granola or Jamie or Bluedot for bot-free recording, or exporting Shadow notes to Markdown or Zapier. Do NOT use for choosing between all AI note-takers (use /sales-note-taker) or reviewing a call for coaching (use /sales-call-review).
Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text prompts. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Mask-Grounding-DINO model. Trigger phrases include "train Mask Grounding DINO", "open-vocabulary segmentation", "text-prompted instance segmentation", "grounded mask DETR".