{
  "markdown": "# Redis Agent Skills\n\nA collection of skills for AI coding agents working with Redis. Skills are packaged instructions and resources that extend agent capabilities.\n\nSkills follow the [Agent Skills](https://agentskills.io/) format.\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| [redis-core](skills/redis-core/) | Data structures, key naming, memory and TTL, atomic primitives, JSON vs Hash, Streams vs Pub/Sub. |\n| [redis-connections](skills/redis-connections/) | Pooling, multiplexing, pipelining, client-side caching, timeouts, slow commands. |\n| [redis-search](skills/redis-search/) | FT.CREATE schema, FT.SEARCH / FT.AGGREGATE / FT.HYBRID, DIALECT 2, vector similarity (HNSW / FLAT), hybrid retrieval, RAG pipelines, zero-downtime index updates. |\n| [redis-semantic-cache](skills/redis-semantic-cache/) | LangCache — cache-aside flow for LLM responses, similarity threshold tuning, per-task cache separation. |\n| [redis-clustering](skills/redis-clustering/) | Hash tags for multi-key operations, avoiding CROSSSLOT, reading from replicas. |\n| [redis-security](skills/redis-security/) | Authentication and TLS, ACL-based least privilege, network bind, firewall, command renaming. |\n| [redis-observability](skills/redis-observability/) | Key metrics (INFO), debugging commands (SLOWLOG, MEMORY DOCTOR, FT.PROFILE), Redis Insight. |\n| [iris-development](skills/iris-development/) | Iris: Redis Agent Memory — provisioning, SDK auth, session events, long-term memory search, async promotion. |\n\n## Installation\n\n### Agent Skills CLI\n\n```bash\nnpx skills add redis/agent-skills\n```\n\n### Claude Code Plugin\n\nYou can also install the skills as a Claude Code plugin:\n\n```\n/plugin marketplace add redis/agent-skills\n/plugin install redis-development@redis\n```\n\n### ChatGPT and Codex Plugin\n\nThe distributable plugin package for ChatGPT and Codex lives at\n[`plugins/redis-development/`](plugins/redis-development/). It includes the\nrequired `.codex-plugin/plugin.json` manifest and real copies of every skill.\nArchive that directory—not the repository root—when preparing a skills-only\nsubmission to the OpenAI plugin submission portal.\n\n### Cursor Plugin\n\nThis repository also includes Cursor plugin packaging. Run this command in chat:\n\n```text\n/add-plugin redis\n```\n\nThe 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](AGENTS.md#where-skills-live).\n\n## Usage\n\nSkills are automatically available once installed. The agent will use them when relevant tasks are detected.\n\n**Examples:**\n```\nHelp me optimize this Redis query\n```\n```\nWhat data structure should I use for a leaderboard?\n```\n```\nReview my Redis connection handling\n```\n\n## Skill Structure\n\nEach skill follows the [agentskills.io specification](https://agentskills.io/specification):\n\n- `SKILL.md` - Instructions for the agent (required)\n- `references/` - Long-form content loaded on demand (optional)\n- `scripts/` - Helper scripts (optional)\n- `assets/` - Static resources (optional)\n\nSee [AGENTS.md](AGENTS.md) for the full layout, conventions, and the \"Adding a New Skill\" walkthrough.\n\n## License\n\nMIT\n",
  "bytes": 3380,
  "sha": "12d8a9cb28fbc0c3a8ea4f33bb28ce2d357e5c6b9996767b06370bd6299de3c6",
  "repo_slug": "redis/agent-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_redis_agent_skills_iris_development_3bae60e0/readme"
}