Skills

from recoupable/skills

Manages Apache Airflow operations via the af CLI (installed via uvx from astro-airflow-mcp), including listing, testing, running, and debugging DAGs, viewing task logs, checking connections and variables, and monitoring system health. Supports multi-instance configuration with auto-discovery of Astro and local deployments.

Go code review checklist skill based on the Go Wiki CodeReviewComments with style standards, formatting, documentation, and community best practices for reviewing Go code

from recoupable/skills

JSON/CSV → LaTeX booktabs tables with bold-best, significance stars, multi-dataset.

A Replicate skill that enables AI agents to search for models, browse curated collections, read model schemas, and pick the right model for building AI-powered applications.

A documentation-only skill that lets AI agents query a locally-running LLM Wiki desktop app via its HTTP API, enabling knowledge retrieval from the user's personal wiki.

from recoupable/skills

Framework for developing, testing, and deploying trading strategies for prediction markets like Polymarket, with signal implementation and backtesting.

An auto-generated agent skill collection from trending security and application security open source projects on GitHub, with installable SKILL.md files for penetration testing and security hardening created by scanning for fast-growing repos every 30 minutes.

Official Appwrite agent skills providing API knowledge for building applications with Appwrite's backend services including authentication, databases, storage, and functions.

A scientific research skill for searching and retrieving clinical trial records, enabling AI agents to explore therapeutic research data from ClinicalTrials.gov.

Part of the Vercel plugin for AI coding agents, providing skills and guidance for Turbopack bundler configuration, optimization, and development workflows within Vercel-deployed applications.

A post-generation design polish skill inspired by Impeccable that audits, critiques, and refines existing HTML/web artifacts—tightening typography, removing AI tells, adding restrained animation, and hardening accessibility.

Mao Zedong thinking framework — a cognitive operating system distilled from the five volumes of Mao's Selected Works for strategic analysis, organizational management, and competitive strategy.

Multi-LLM planning council skill that orchestrates configurable CLI agents (Codex, Claude Code, Gemini, OpenCode) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final bias-resistant plan

Detailed implementation planning skill that creates phased plans with sprints and atomic tasks, covering codebase research, requirements clarification, and structured implementation phases for bugs, features, or tasks

Official Qdrant skill for **deployment options** — guides coding agents through choosing between local development, self-hosted (Docker/Kubernetes), Qdrant Cloud, and hybrid deployment modes, with configuration and trade-off analysis for each approach.

Guides platform abstraction decisions for the Amethyst Kotlin Multiplatform project, including source set placement, expect/actual patterns, and cross-platform code sharing strategies.

A collection of 30 Claude Code skills covering the full academic research paper lifecycle — from literature search and novelty assessment through experiment design, data analysis, writing, and slide generation.

Salesforce skill providing official documentation retrieval guidance for hard-to-fetch online Salesforce docs. Part of the Foundation group alongside sf-metadata, sf-data, and sf-permissions.

A collection of Codex/agent skills for planning, documentation access, frontend development, and browser automation, including parallel task execution, LLM council multi-agent orchestration, Context7 doc fetching, and Gemini Computer Use browser control.

from vinvcn/mattpocock-skills-zh-cn

AgentOps — a toolbox of operational primitives for coding agents that preserves learnings between sessions, supports parallel swarm execution, and builds validation pipelines.

Collection of agent skills for planning, documentation access, frontend development, and browser automation, featuring multi-agent orchestration with planner, parallel tasks, and LLM council capabilities.

Agent skill for running AI models on Replicate, covering prediction creation, polling, webhooks, streaming, file handling, and concurrent execution, part of a collection including model discovery and comparison skills.

A 1-on-1 AI tutor skill based on Bloom's 2-Sigma mastery learning with Socratic questioning, part of the sanyuan-skills code-review-expert collection.

An agent skills monorepo including social media marketing expertise covering strategy, content creation, and community management across Instagram, Facebook, TikTok, and LinkedIn.

Applies Strunk's writing rules to improve clarity, concision, and professionalism in documentation, messages, explanations, and UI text.

Designs and builds scalable AI agent architectures with modular structure, multi-agent coordination, and extensible system patterns