add-agent-playbooks — Claude Code skill: features and install
The add-agent-playbooks Claude Code skill connects Redis Iris Agent Playbooks to an existing Python agent. It runs when approved answers or repeatable procedures need to move out of prompts, documents, or a semantic cache.
MIT 110 installs ★ 178 updated 2026-09-08
npx skills add redis/agent-skills --skill add-agent-playbooks -a claude-codeWhat add-agent-playbooks does
The skill guides the connection of a Playbook to an existing Python agent, publication of FAQs and Skills, and a check of the application’s first turn. It preserves the app’s response policy and tool permissions. Integration configures agent context and procedure loading; the check covers a paraphrased question and what happens when no suitable content is found.
Content can be moved from prompts, documents, or retrieved material into versioned files. Review proposals are optional: submitting or accepting one does not publish it. Local defaults require a running stack. Keep application credentials separate from publishing credentials.
What it helps with
- move repeatable procedures from prompts into Skills
- publish approved answers as FAQs
- connect a Playbook to an existing Python agent
- check the agent’s response when matching content is missing
Example prompts for the agent
- Connect Redis Iris Agent Playbooks to my Python agent and test the first application turn.
- Turn approved answers from my documents into published FAQs.
- Move this prompt procedure into a Skill and test it with a paraphrased question.
How to install add-agent-playbooks
1Skills CLI (Vercel)
npx skills add redis/agent-skills --skill add-agent-playbooks -a claude-code2Manually: put the files in place
~/.claude/skills/add-agent-playbooks/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/add-agent-playbooks/
1Skills CLI (Vercel)
npx skills add redis/agent-skills --skill add-agent-playbooks -a codex2Manually: put the files in place
.agents/skills/add-agent-playbooks/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add redis/agent-skills --skill add-agent-playbooks -a cursor2Manually: put the files in place
.cursor/skills/add-agent-playbooks/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install redis/agent-skills skills/add-agent-playbooks2Manually: put the files in place
.github/skills/add-agent-playbooks/SKILL.md1Skills CLI (Vercel)
npx skills add redis/agent-skills --skill add-agent-playbooks -a gemini-cli2Platform CLI
gemini skills install https://github.com/redis/agent-skills --path skills/add-agent-playbooksManually: put the files in place
.devin/skills/add-agent-playbooks/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add redis/agent-skills --skill add-agent-playbooks -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about add-agent-playbooks
How do I install add-agent-playbooks in Claude Code?
Run npx skills add redis/agent-skills --skill add-agent-playbooks -a claude-code. The skill file is at ~/.claude/skills/add-agent-playbooks/SKILL.md.
What does add-agent-playbooks do?
It guides the integration of Redis Iris Agent Playbooks with an existing Python agent, the publication of FAQs and Skills, and a check of the app’s first turn using published content.
What does add-agent-playbooks need to run?
It works with an existing Python agent and Redis Iris Agent Playbooks. Local defaults also require a running stack.
Source text
SKILL.md · MIT
--- name: add-agent-playbooks description: Add Redis Iris Agent Playbooks to an existing agent. Use when approved answers or repeatable procedures live in prompts, document retrieval, or a semantic response cache. Connect or provision a Playbook, publish FAQs and Skills, and verify the first application turn with optional review proposals. license: MIT metadata: author: redis version: "1.0.0" --- # Add Agent Playbooks Bring an existing Python agent to one verified Playbook-backed turn, then finish the requested content migration or integration. FAQs supply published answers; Skills supply procedures loaded separately from discovery previews. The application owns response policy, tool permissions, and approval of actions. ## 1. Orient and choose the behavior Find the model call, tool registration, framework/version, and existing policy or procedure sources. Preserve the graph, business tools, and global response/authorization rules. Infer these decisions from the request and code; ask only about unresolved choices and state defaults used: | Decision | Result | |---|---| | Which repeated tasks need procedures? | One Skill per procedure; skip when none. Move task-specific tool guidance out of prompts. | | Which questions require approved answers? | One FAQ per approved answer; skip when none. | | Which audiences use the content? | One audience: no attribute or filter. Several: matching attributes on content and a trusted runtime audience. | | Should uncovered answers be submitted for review? | Default no. Yes: choose automatic uncovered proposals or an application-owned quality/privacy gate; preserve existing gates. | | Where does the content live today? | Convert relevant prompt text, docs, or retrieved content into versioned files. Retain authoritative sources. | Prefer progressive disclosure when the agent can execute tools; use score-based hooks otherwise. Define clarification, escalation, and outage behavior: approved-only answers need an explicit policy for insufficient content. ## 2. Check prerequisites and connect Follow [provisioning](references/provisioning.md) for the short prerequisite check and new, partial, or existing setup. Reuse usable configuration and published content. Local defaults require a running stack; Cloud and self-managed administration use different paths. Check framework APIs against the installed version before editing. Use an available docs MCP. For the CLI, run `iris agent-playbooks <command> --help`. Inspect installed package source when documentation does not match the installed API. Report unresolved compatibility questions. ## 3. Publish the first relevant content Follow [content authoring](references/content.md) for file formats, quality checks, audience attributes, validation, previews, and publication. Begin with one approved FAQ or procedure relevant to the requested task; use both only when needed. Confirm its serving version before wiring the agent. Complete any broader requested migration after the first turn works. ## 4. Integrate with the application Follow [runtime integration](references/integration.md) for the chosen mode, async variants, and framework placement. Create one configured context object and use it throughout. Build context from the base prompt afresh each turn. Register disclosure tools with both the model and executor. ## 5. Run, inspect, and improve Follow [first success](references/first-success.md): execute the actual application, inspect the content keys/versions and procedure loads, check a paraphrase and missing-content behavior, fix observed gaps, and rerun. Show the user what worked and how to repeat it. Once replacement reads work, remove obsolete runtime prompt/retriever/cache code and its unused embedding pipeline; run affected application checks on the final integration. ## 6. Hand off and maintain Use the handoff in [first success](references/first-success.md#handoff) to distinguish observed results from unverified work and leave an exact repeat command. Walk through the [next approved content update](references/content.md#maintain-the-content), naming the content owner/publisher and any remaining deployment configuration. ## Essential constraints and optional paths - Every `iris` command uses root options `--json --no-input`. The CLI handles administration and content management; the Python SDK runs inside the application. - Keep runtime `.env` credentials separate from `.env.content` publishing credentials and administrative tokens. Grant the agent `read`, adding `propose` only for submissions. Never print secrets or commit env files. - Publication selects serving content. A proposal is a review candidate; submitting or accepting one does not implicitly publish it. - For a semantic response cache, read [cache migration](references/response-cache.md) before replacing its lookup/write path. - For background proposals from Agent Memory, read [Memory extraction](references/memory-extraction.md) before enabling another submission path.
© redis · MIT · redis/agent-skills