Sandbox
@redis/agent-skills

Redis skills pack for agent coding assistants

This repo packages Redis-specific skills that AI coding agents can use when they are asked to work on Redis. Each skill pairs instructions with supporting references, so the agent can apply the right Redis patterns for queries, connections, search, security, observability, clustering, and memory.

146 stars29 forksTypeScriptUpdated 9d ago
Who it's for

Builders who want their coding agent to follow Redis-specific practices for app work, ops, and debugging.

What it delivers

You can get Redis-aware help without re-explaining the same patterns every time.

What it does

Redis skill set

Includes separate skills for core data structures, connections, search, semantic cache, clustering, security, observability, and Iris development.

Agent-specific packaging

Provides installable plugin bundles for Claude Code, Codex, and Cursor in addition to the raw skills directory.

Validation and sync scripts

Includes scripts to sync generated plugin copies and validate plugin and skill structure.

Skill references and assets

Each skill can include `references/`, `scripts/`, and `assets/` alongside its `SKILL.md` instructions.

How to get it

  1. 1Run
    npx skills add redis/agent-skills
  2. 2You can also install the skills as a Claude Code plugin
    /plugin install redis-development@claude-plugins-official
  3. 3This repository also includes Cursor plugin packaging. Run this command in chat
    /add-plugin redis
  4. 4Examples
    Help me optimize this Redis query
  5. 5Run
    What data structure should I use for a leaderboard?
  6. 6Run
    Review my Redis connection handling

README

Redis Agent Skills

A collection of skills for AI coding agents working with Redis. Skills are packaged instructions and resources that extend agent capabilities.

Skills follow the Agent Skills format.

Available Skills

SkillDescription
redis-coreData structures, key naming, memory and TTL, atomic primitives, JSON vs Hash, Streams vs Pub/Sub.
redis-connectionsPooling, multiplexing, pipelining, client-side caching, timeouts, slow commands.
redis-searchFT.CREATE schema, FT.SEARCH / FT.AGGREGATE / FT.HYBRID, DIALECT 2, vector similarity (HNSW / FLAT), hybrid retrieval, RAG pipelines, zero-downtime index updates.
redis-semantic-cacheLangCache — cache-aside flow for LLM responses, similarity threshold tuning, per-task cache separation.
redis-clusteringHash tags for multi-key operations, avoiding CROSSSLOT, reading from replicas.
redis-securityAuthentication and TLS, ACL-based least privilege, network bind, firewall, command renaming.
redis-observabilityKey metrics (INFO), debugging commands (SLOWLOG, MEMORY DOCTOR, FT.PROFILE), Redis Insight.
iris-developmentIris: Redis Agent Memory — provisioning, SDK auth, session events, long-term memory search, async promotion.

Installation

Agent Skills CLI

npx skills add redis/agent-skills

Claude Code Plugin

You can also install the skills as a Claude Code plugin:

/plugin install redis-development@claude-plugins-official

ChatGPT and Codex Plugin

The distributable plugin package for ChatGPT and Codex lives at plugins/redis-development/. It includes the required .codex-plugin/plugin.json manifest and real copies of every skill. Archive that directory—not the repository root—when preparing a skills-only submission to the OpenAI plugin submission portal.

Cursor Plugin

This repository also includes Cursor plugin packaging. Run this command in chat:

/add-plugin redis

The top-level skills/ directory remains the source of truth. plugins/redis-development/skills/ holds generated real copies used by the ChatGPT, Codex, and Claude Code plugin package (not symlinks, which plugin installation flows may drop); npm run sync:plugins regenerates them and the pre-commit hook keeps them current. See AGENTS.md.

Usage

Skills are automatically available once installed. The agent will use them when relevant tasks are detected.

Examples:

Help me optimize this Redis query
What data structure should I use for a leaderboard?
Review my Redis connection handling

Skill Structure

Each skill follows the agentskills.io specification:

  • SKILL.md - Instructions for the agent (required)
  • references/ - Long-form content loaded on demand (optional)
  • scripts/ - Helper scripts (optional)
  • assets/ - Static resources (optional)

See AGENTS.md for the full layout, conventions, and the "Adding a New Skill" walkthrough.

License

MIT

Files in the repo

Repository payload18 top-level entries
  • .claude-plugin
  • .cursor-plugin
  • .github
  • .husky
  • assets
  • evals
  • packages
  • plugins
  • scripts
  • skills
  • .gitignore
  • AGENTS.md
  • CLAUDE.md
  • CONTRIBUTING.md
  • LICENSE
  • package-lock.json
  • package.json
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More collections

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

52k

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

34k