/docs
Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations).
$ npx -y skills add Chorus-AIDLC/Chorus --skill docs --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/docs
Context preview
The summary Claude sees to decide when to auto-load this skill.
Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations).
SKILL.md
docs.SKILL.mdname: docs
description: Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations).
license: AGPL-3.0
metadata:
author: chorus
version: "0.16.0"
category: project-management
mcp_server: chorus
Docs Skill
This skill is a **thin router to the live Chorus documentation site** (`https://doc.chorus-ai.dev`). Use it to answer questions about **how to use, configure, deploy, or operate Chorus** — grounding the answer in the current published docs instead of memory.
It is **not** a workflow skill: it does not drive the AI-DLC pipeline. For that, use `/skill:idea`, `/skill:proposal`, `/skill:develop`, `/skill:review`, or `/skill:yolo`.
---
When to Use
Use this skill whenever the user asks a **product-usage** question about Chorus, such as:
- **UI workflow** — how the Idea → Proposal → Task → Verify pipeline works in the web app, what a control does, how statuses flow.
- **Agent setup** — creating an API key, permissions and role presets, connecting an agent.
- **Plugin setup** — installing/configuring the Claude Code / Codex / OpenClaw / Kiro / Pi plugin.
- **API / MCP** — the REST API, the MCP tool surface, authentication, real-time events.
- **Deployment** — self-hosting, the CDK stack, environment configuration.
- **Operations / troubleshooting** — running Chorus, diagnosing connection or setup problems.
Do **NOT** use it to *drive* the pipeline (claiming ideas, writing proposals, executing tasks) — that is what the stage skills above are for. This skill answers "how does the product work / how do I set it up"; the stage skills *do* the work.
---
Access Convention
The docs site is agent-friendly. Follow this three-step convention every time. **Do NOT** answer from memory, and **do NOT** hardcode a page list — the index is the source of truth and pages change over time.
1. **Fetch the index.** Get `https://doc.chorus-ai.dev/llms.txt` — a machine-readable index that lists every documentation page with a one-line summary and its `.md` URL. **The index is a single, unlocalized file that lives ONLY at the root `/llms.txt`. Never prefix it with a locale — `https://doc.chorus-ai.dev/zh/llms.txt` (and `/ja/`, `/ko/`) does NOT exist and returns 404.** 2. **Fetch the relevant page(s) as raw Markdown.** Pick the page(s) that match the question from the index, then fetch the raw Markdown by **appending `.md`** to the page URL (e.g. `https://doc.chorus-ai.dev/guides/getting-started` → `https://doc.chorus-ai.dev/guides/getting-started.md`). 3. **Ground the answer and link the human page.** Base your answer on the fetched Markdown, and link the human-facing page (the `.md` URL **without** the `.md` suffix) so the user can open it in a browser.
Use whatever web-fetch capability your environment provides (your built-in fetch tool, `curl`, etc.) — this skill states the convention, not a specific tool binding.
---
Locale
The `/llms.txt` index itself is **not** localized — there is exactly one, at the root. Localization applies to **pages**, not the index:
- The index always lives at `https://doc.chorus-ai.dev/llms.txt` and lists the root (`en`) page URLs. **Do not look for `/zh/llms.txt` — it does not exist.**
- `en` is the root (unprefixed): `https://doc.chorus-ai.dev/...`
- `zh`, `ja`, `ko` are **path-prefixed pages**: take a page path from the index and prepend the locale — `https://doc.chorus-ai.dev/zh/...`, `/ja/...`, `/ko/...`
- Appending `.md` works on the prefixed pages too (e.g. `https://doc.chorus-ai.dev/zh/guides/getting-started.md`).
- **Match the user's language** when the docs exist in it; fall back to `en` otherwise.
---
Relationship to the Workflow Skills
This skill **complements** the AI-DLC workflow skills — it does not replace them:
| The user wants to… | Use | |--------------------|-----| | Learn how to use / configure / deploy / operate Chorus | **this skill** (`/skill:docs`) | | Drive an idea / write a proposal / execute or verify a task | `/skill:idea`, `/skill:proposal`, `/skill:develop`, `/skill:review`, `/skill:yolo` |
Always use the live host `doc.chorus-ai.dev`. `docs.chorus-ai.dev` (with an "s") is a dead link — never use it.
Read more
name: docs description: Chorus documentation router — consult the live Chorus docs site to answer product-usage questions (UI workflow, agent/plugin setup, API/MCP, deployment, operations). license: AGPL-3.0 metadata: author: chorus version: "0.16.0" category: project-management mcp_server: chorus
Docs Skill
This skill is a **thin router to the live Chorus documentation site** (`https://doc.chorus-ai.dev`). Use it to answer questions about **how to use, configure, deploy, or operate Chorus** — grounding the answer in the current published docs instead of memory.
It is **not** a workflow skill: it does not drive the AI-DLC pipeline. For that, use `/skill:idea`, `/skill:proposal`, `/skill:develop`, `/skill:review`, or `/skill:yolo`.
---
When to Use
Use this skill whenever the user asks a **product-usage** question about Chorus, such as:
- **UI workflow** — how the Idea → Proposal → Task → Verify pipeline works in the web app, what a control does, how statuses flow.
- **Agent setup** — creating an API key, permissions and role presets, connecting an agent.
- **Plugin setup** — installing/configuring the Claude Code / Codex / OpenClaw / Kiro / Pi plugin.
- **API / MCP** — the REST API, the MCP tool surface, authentication, real-time events.
- **Deployment** — self-hosting, the CDK stack, environment configuration.
- **Operations / troubleshooting** — running Chorus, diagnosing connection or setup problems.
Do **NOT** use it to *drive* the pipeline (claiming ideas, writing proposals, executing tasks) — that is what the stage skills above are for. This skill answers "how does the product work / how do I set it up"; the stage skills *do* the work.
---
Access Convention
The docs site is agent-friendly. Follow this three-step convention every time. **Do NOT** answer from memory, and **do NOT** hardcode a page list — the index is the source of truth and pages change over time.
1. **Fetch the index.** Get `https://doc.chorus-ai.dev/llms.txt` — a machine-readable index that lists every documentation page with a one-line summary and its `.md` URL. **The index is a single, unlocalized file that lives ONLY at the root `/llms.txt`. Never prefix it with a locale — `https://doc.chorus-ai.dev/zh/llms.txt` (and `/ja/`, `/ko/`) does NOT exist and returns 404.** 2. **Fetch the relevant page(s) as raw Markdown.** Pick the page(s) that match the question from the index, then fetch the raw Markdown by **appending `.md`** to the page URL (e.g. `https://doc.chorus-ai.dev/guides/getting-started` → `https://doc.chorus-ai.dev/guides/getting-started.md`). 3. **Ground the answer and link the human page.** Base your answer on the fetched Markdown, and link the human-facing page (the `.md` URL **without** the `.md` suffix) so the user can open it in a browser.
Use whatever web-fetch capability your environment provides (your built-in fetch tool, `curl`, etc.) — this skill states the convention, not a specific tool binding.
---
Locale
The `/llms.txt` index itself is **not** localized — there is exactly one, at the root. Localization applies to **pages**, not the index:
- The index always lives at `https://doc.chorus-ai.dev/llms.txt` and lists the root (`en`) page URLs. **Do not look for `/zh/llms.txt` — it does not exist.**
- `en` is the root (unprefixed): `https://doc.chorus-ai.dev/...`
- `zh`, `ja`, `ko` are **path-prefixed pages**: take a page path from the index and prepend the locale — `https://doc.chorus-ai.dev/zh/...`, `/ja/...`, `/ko/...`
- Appending `.md` works on the prefixed pages too (e.g. `https://doc.chorus-ai.dev/zh/guides/getting-started.md`).
- **Match the user's language** when the docs exist in it; fall back to `en` otherwise.
---
Relationship to the Workflow Skills
This skill **complements** the AI-DLC workflow skills — it does not replace them:
| The user wants to… | Use | |--------------------|-----| | Learn how to use / configure / deploy / operate Chorus | **this skill** (`/skill:docs`) | | Drive an idea / write a proposal / execute or verify a task | `/skill:idea`, `/skill:proposal`, `/skill:develop`, `/skill:review`, `/skill:yolo` |
Always use the live host `doc.chorus-ai.dev`. `docs.chorus-ai.dev` (with an "s") is a dead link — never use it.
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
Repo: Chorus-AIDLC/Chorus
Other skills on chorus.
- /blog
Write release blog posts for Chorus — problem-first narrative, bilingual (zh/en), following the project's editorial style.
Open skill - /e2e-verification
Use when manually verifying a Chorus frontend change in a real browser — finding local login credentials, driving the running dev server with the Playwright MCP, logging in, navigating to a page, and capturing snapshots/screenshots for e2e acceptance.
Open skill - /openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
Open skill - /openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
Open skill - /openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
Open skill - /openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
Open skill

