Loading...
Loading...
Found 2,503 Skills
Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
ConvexFS (convex-fs) — path-based file storage and serving component for Convex powered by bunny.net CDN. Covers installation, setup, file upload/download flows, path management, blob lifecycle, atomic transactions (move/copy/delete), compare-and-swap, signed URLs, file expiration, garbage collection, auth for uploads/downloads, multiple filesystems, React integration, and production best practices. Use when working with ConvexFS, uploading files in Convex, serving files via CDN, managing file paths, building file storage features, or configuring bunny.net with Convex. Triggers on: convex-fs, ConvexFS, bunny.net, file upload, file storage convex, blob, commitFiles, registerRoutes, buildDownloadUrl, fs.stat, fs.list, fs.transact, fs.move, fs.copy, fs.delete, fs.writeFile, fs.getDownloadUrl, "how do I upload files in Convex", "serve files from Convex", "ConvexFS setup".
Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore lists.
Extract structured data from Office documents (DOCX, PPTX, XLSX, HWP, HWPX) using the Polaris AI DataInsight Doc Extract API. Use when the user wants to parse, analyze, or extract text, tables, charts, images, or shapes from document files. Invoke this skill whenever the user mentions extracting content from Word, PowerPoint, Excel, HWP, or HWPX files, wants to parse document structure, needs to convert document data for RAG pipelines, or asks about reading tables, charts, or text from Office-format documents — even if they don't explicitly mention "DataInsight" or "Polaris".
Build world-class kanban board drag-and-drop with @dnd-kit. Linear-quality UX with proper collision detection, smooth animations, and visual feedback
Expert guidance for LangChain and LangGraph development with Python, covering chain composition, agents, memory, and RAG implementations.
JaCoCo Java code coverage tool USE WHEN: user mentions "JaCoCo", "Java coverage", "code coverage", asks about "coverage threshold", "jacoco-maven-plugin", "coverage report", "LINE coverage", "BRANCH coverage" DO NOT USE FOR: JavaScript/TypeScript coverage - use Vitest skill, SonarQube analysis - use `sonarqube` skill, test execution - use testing skills
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.
Use when cognee is a Python AI memory engine that transforms documents into knowledge graphs with vector and graph storage for semantic search and reasoning. Use this skill when writing code that calls cognee's Python API (add, cognify, search, memify, config, datasets, prune, session) or integrating cognee-mcp. Covers the full public API, SearchType modes, DataPoint custom models, pipeline tasks, and configuration for LLM/embedding/vector/graph providers. Do NOT use for general knowledge graph theory or unrelated Python libraries.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for browser cookies, localStorage, sessionStorage, IndexedDB, Cache Storage, service workers, offline caches, and client-side session persistence. Use when the user asks to inspect browser state, replay cached auth or session behavior, explain why a page behaves differently after load, or trace how stored client state changes requests, rendering, or access. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
Dense vector embeddings, semantic search, RAG pipelines, and reranking via Together AI. Generate embeddings with open-source models and rerank results behind dedicated endpoints. Reach for it whenever the user needs vector representations or retrieval quality improvements rather than direct text generation.
Master philosophy of language - meaning, reference, truth, speech acts. Use for: semantics, pragmatics, meaning theory, reference. Triggers: 'meaning', 'reference', 'Frege', 'sense', 'Kripke', 'speech act', 'semantics', 'pragmatics', 'truth conditions', 'propositions', 'names', 'descriptions', 'rigid designator', 'natural kind', 'context', 'indexical'.