SKILL.md files package domain expertise into something any AI agent can use. Drop one into your project and your agent learns how to process PDFs, design interfaces, write tests, or whatever the skill teaches.
1381 skills
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog skills: Then install individual plugins: Or browse available plugins: Copy any skill directory to .claude/skills/ in your project: Any directory under skills/ that contains a .claude-plugin/plugin.json is automatically discovered and added to the market
- MCP Server: code-to-tree - Using code-to-tree - Configure MCP Clients - Building (Windows) - Building (macOS) The code-to-tree server's goals are: 1. Give LLMs the capability of accurately converting source code into AST(Abstract Syntax Tree), regardless of language. 2. One standalone binary should be everything the MCP client needs. These goals imply: 1. The underlying syntax parser should be v
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
A Model Context Protocol (MCP) server for YouTube integration. Retrieve video transcripts, details, and metadata using YouTube's Data API. Get instant access to YouTube with our managed infrastructure - no setup required: 🔗 Get Free API Key → API Key Setup: Get your YouTube Data API key from the Google Cloud Console and enable the YouTube Data API v3. - Video Transcripts: Retrieve full video tran
Use when working with code refactoring context restore
Practitioner-focused workflows for running, validating, and packaging reproducible open AI governance studies. This repository contains execution pipelines, source artifacts, and validation gates for reproducible governance reports. Every headline finding is expected to map to: - a versioned artifact - a deterministic query in the claims ledger - a reproducible execution path in pipelines/ Use thi
Use when working with context management context save
A comprehensive async Python SDK for TickTick with MCP (Model Context Protocol) server support. Includes full support for Dida365 (滴答清单) as well. Use TickTick programmatically from Python, or let AI assistants manage your tasks. - Why This Library? - Installation - MCP Server Setup & Usage - Step 1: Register Your App - Step 2: Get OAuth2 Access Token - Step 3: Configure Your AI Assistant - CLI Ref
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence.
Windows 11 system management
Automate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search tools first for current schemas.
Scrape, crawl, search, and extract web data. Converts any website to LLM-ready markdown. Local-first with smart escalation (HTTP → browser → stealth). No API key needed.
Expert patterns for Azure Functions development including isolated worker model, Durable Functions orchestration, cold start optimization, and production patterns. Covers .NET, Python, and Node.js programming models. Use when: azure function, azure functions, durable functions, azure serverless, function app.
Automate Pipedrive CRM operations including deals, contacts, organizations, activities, notes, and pipeline management via Rube MCP (Composio). Always search tools first for current schemas.
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
DBOS TypeScript SDK for building reliable, fault-tolerant applications with durable workflows. Use this skill when writing TypeScript code with DBOS, creating workflows and steps, using queues, using DBOSClient from external applications, or building applications that need to be resilient to failures.
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
For the best experience, use Pipedream's hosted MCP server which provides: - 2,800+ APIs and 10,000+ tools through a single server - Built-in authentication: no manual token management required - Multiple tool modes: sub-agent and full configuration - Automatic app discovery - Enterprise-grade reliability and security 🚀 Get started: Pipedream MCP Documentation This reference implementation shows
Multi-agent orchestration platform for enterprise AI development. Run 12+ AI agents concurrently with full governance, Gemini-powered code review, and enforced quality gates. Solves coordination, verification, and metrics challenges that stall enterprise AI adoption.
Validates Conductor project artifacts for completeness,
Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users enter the experiment, and the disambiguation when a percentage like "roll out to 25%" could mean either. Use when the user mentions a rollout percentage, variant split, or traffic distribution; gives a ratio like 60/40, 70/30, or 80/20; asks "who sees the test variant?
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.