759 free AI agent skills in agentskills.io format - compatible with Claude Code, Cursor, Codex, Gemini CLI
Skill Claude CodeCodex
A thin client over the AdMapix read API. It fetches raw structured data and returns it as JSON. It does not analyze, summarize, rank, generate pages, or run autonomous research — the calling agent (e.g. Claude Code, Codex) decides which endpoints to call, composes multi-call workflows from the metadata, and does any…
Skill Claude CodeCodex
A general helper for AI-agent development, covering its functions, use cases, technical topics, and examples. The description does not specify particular operations it performs.
Skill Claude CodeCodex
Multi-agent systems on AWS Bedrock AgentCore with LangGraph orchestration. Source: <.
Skill Claude CodeCodex
Use the local AWS CLI to answer questions about AWS resources. Default to read‑only queries. Only propose or run write/destructive actions after explicit user confirmation.
Skill Claude CodeCodex
Use the local Azure CLI to answer questions about Azure resources. Default to read‑only queries. Only propose or run write/destructive actions after explicit user confirmation.
Skill Claude CodeCodex
A file-management tool for Baidu Netdisk, a cloud storage service, restricted to the /apps/bdpan/ directory.
Skill Claude CodeCodex
A skill for turning long, disorganized, high-risk documents into clearer material for reasoning and decisions. The description is provided in Chinese.
Skill Claude CodeCodex
A local memory system that stores and searches information using LanceDB and JavaScript-based text embeddings. It does not need an external service.
Skill Claude CodeCodex
The ultimate memory system for AI agents. Combines 6 proven approaches into one bulletproof architecture.
Skill Claude CodeCodex
I built this because my agent's MEMORY.md hit 15,000 words and daily logs kept piling up at 2,500 words/day. Needed a way to compress without losing the important stuff.
Skill Claude CodeCodex
Security scanner for Skill平台 agent memory files.
Skill Claude CodeCodex
Skill "memory" from thcjp/hermes-skills, covering memory, how it works, setup, when to use and architecture.
Skill Claude CodeCodex
User faces a tradeoff with multiple options. User asks "should I" or "what do you think about". User is weighing risk vs. reward. User revisits a past decision to evaluate it. User wants to build better decision habits over time. You notice an implicit decision point the user hasn't articulated yet.
Skill Claude CodeCodex
A biologically-inspired memory system that uses spreading activation instead of keyword/vector search. Memories form a neural graph where neurons connect via 20 typed synapses. Frequently co-accessed memories strengthen their connections (Hebbian learning). Stale memories decay naturally. Contradictions are…
Skill Claude CodeCodex
A typed vocabulary + constraint system for representing knowledge as a verifiable graph.
Skill Claude CodeCodex
Use this skill when the user wants a real productivity system, not just one-off motivation. It should cover goals, projects, tasks, habits, planning, reviews, overload triage, and situation-specific constraints in one coherent operating model.
Skill Claude CodeCodex
Guidance for using Redis as a cache, with an expiration time set for every key. Redis is a fast data store often used to temporarily keep frequently needed values.
Skill Claude CodeCodex
A Chinese-language quick reference for improving an agent's behaviour in different situations.
Skill Claude CodeCodex
A self-improvement skill for an agent that updates its working knowledge automatically over time.
Skill Claude CodeCodex
The zero-dependency memory system for AI agents.
Skill Claude CodeCodex
A layered memory and retrieval skill for managing an agent's stored context. RAG means finding relevant saved information when it is needed.
Skill Claude CodeCodex
A development workflow that assigns each task to a new sub-agent and uses two review stages. A sub-agent is a separate coding agent working on part of a larger task.
Skill Claude CodeCodex
A token cost optimization skill that helps you save 50-80% on AI token usage without sacrificing response quality.
Skill Claude CodeCodex
A decentralised memory tool that encrypts stored information end to end and retrieves facts through memory search. Decentralised means the data is not kept in one central place.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: