sk-create-agent

Create Agent - Runtime Persona Authoring

create-agent is the sk-doc workflow packet for creating or updating one runtime agent markdown file. The executable contract lives here: decide whether an agent is the right component, place it in the active runtime directory, author current frontmatter and authority boundaries, then validate before delivery.

Use references/README.md (the overflow route map) and assets/agent-template.md only for deeper examples, exhaustive variants, and long-form reference detail. Do not make those files the primary workflow contract.

---

1. WHEN TO USE

Activation Triggers

Use this workflow when the request involves:

1. Creating a new OpenCode or Claude Code agent file.
2. Updating an agent's frontmatter, permissions, authority boundary, workflow, verification contract, or anti-patterns.
3. Converting a durable role description into a runtime persona with explicit authority and tool policy.
4. Deciding whether the requested component should be an agent, skill, or command.
5. Running or supporting /create:agent.

Keyword triggers: create agent, /create:agent, OpenCode agent, Claude Code agent, agent file, new agent, agent persona, agent frontmatter, permission object, authority boundary, agent template, runtime agent directory, agent and paired.

Create an agent only when the system needs a stable named persona with explicit tool permissions, denied capabilities, behavioral constraints, orchestration authority, or reusable execution posture.

When NOT to Use

Use another sk-doc packet when:

1. The request needs reusable knowledge, standards, templates, or long-form workflow guidance. Use create-skill.
2. The request needs a slash-command entry point without a new runtime persona. Use create-command.
3. The request needs a README, install guide, feature catalog, manual testing playbook, benchmark package, flowchart, or changelog. Use create-readme, create-feature-catalog, create-manual-testing-playbook, create-benchmark, create-flowchart, or create-changelog.
4. The request audits, validates, scores, or optimizes an existing agent document. Use create-quality-control.