# Commentary agent skills

Install portable Commentary skill folders into a compatible agent and choose a skill for a specific task.

Canonical: https://commentary.dev/docs/build/agent-skills



This guide covers the published [commentary-skills v0.6.2 release](https://github.com/commentary-dev/commentary-skills/releases/tag/v0.6.2), at source commit `6903701f26de9076dc47823adca92037be3edd1e`. Its portable skills guide compatible agents through authorized Commentary workflows. A skill is instruction content, not an access grant, API token, human decision, or provider permission.

## Install a skill folder

1. Check that your agent harness supports the `SKILL.md` folder format.
2. Clone or download the published `v0.6.2` tag. For Git, use `git clone --branch v0.6.2 --depth 1 https://github.com/commentary-dev/commentary-skills.git`.
3. Copy the complete selected `skills/<skill-name>/` folder to the skill directory documented by your agent. Preserve `SKILL.md`, `references/`, `agents/`, and other files.
4. Restart or refresh the agent harness if it only discovers skills at startup.
5. Ask the agent to use the installed skill by name for a task that matches its purpose.

The skill repository also provides generated plugin bundles for compatible plugin hosts. Use its own installation guide and reviewed release assets for those hosts; a source checkout or ZIP build candidate does not prove a plugin release was published.

## Pick a task-specific skill

The published v0.6.2 release contains the following 21 skills. Each page explains purpose, installation, invocation, workflow, environment, and authority limits.

### Durable human-in-the-loop work

- [Ask Human](/docs/build/skills/commentary-ask-human)
- [Request Approval](/docs/build/skills/commentary-request-approval)
- [Submit Revision](/docs/build/skills/commentary-submit-revision)
- [Escalate Review](/docs/build/skills/commentary-escalate-review)
- [Async Workflow](/docs/build/skills/commentary-async-workflow)
- [Inbox Triage](/docs/build/skills/commentary-inbox-triage)
- [Workspace discovery](/docs/build/skills/commentary-workspace)

### Review workflows

- [Draft Review](/docs/build/skills/commentary-draft-review)
- [Brainstorm Review](/docs/build/skills/commentary-brainstorm-review)
- [PR Review](/docs/build/skills/commentary-pr-review)
- [Live Preview Review](/docs/build/skills/commentary-live-preview-review)
- [Review agentic plans](/docs/build/skills/review-agentic-plans)

### Forms and research

- [Form creation](/docs/build/skills/commentary-form-creation)
- [Form rendering](/docs/build/skills/commentary-form-rendering)
- [Form results](/docs/build/skills/commentary-form-results)
- [Form result visualizations](/docs/build/skills/commentary-form-result-visualizations)
- [Research workflow](/docs/build/skills/commentary-research-workflow)
- [Effective Forms](/docs/build/skills/design-effective-forms)
- [Product research design](/docs/build/skills/design-product-research)
- [Form design compatibility router](/docs/build/skills/commentary-form-design)

### Request and question design

- [Effective Interactions](/docs/build/skills/design-effective-interactions)

## Authority and environment

Skills use the CLI, HTTP API, or MCP as appropriate for the installed toolchain. Install and authorize those transports separately. Prefer short-lived, narrowly scoped credentials. Never give an agent authority to fabricate a human Decision, send a message without authorization, create Git commits or PRs, or claim verification without evidence.

There is no published `@commentary-dev/agent-sdk` npm package. Use HTTP or MCP. No `COMMENTARY_TOKEN` is included in or stored by a skill. Configure credentials using the transport's own secure mechanism.

## Canonical skill pages