skill-elicitation-agent — Claude Code subagent: what it does
skill-elicitation-agent interviews you about the skill you have in mind, then hands back a full Claude skill spec: examples, triggers, file layout and test cases.
no license ★ 1,357 updated 2026-03-01
.claude/agents/skill-elicitation-agent.mdWhat skill-elicitation-agent does
The agent works in stages. First it asks for a couple of concrete cases: what a user would type and what should come out of it. Those cases get picked apart to see which code is rewritten every time (a candidate for scripts/), which docs are consulted again and again (references/), which boilerplate is reused (assets/). Questions about scope, complexity and tool access come after that.
What you get back is a spec document: metadata with a third-person description, the situations where the skill should fire on its own, a structure type (single SKILL.md, multi-file, tool-restricted, with assets), a plan for loading context in stages, and test cases. Before handing off, the agent checks the description, single responsibility, a minimal tool list and the examples.
It does not write the skill itself. The spec goes to skill-generator-agent, which builds the files, so without that agent you move the document into SKILL.md by hand. Tools on hand: Read, Write, Grep, Glob and WebFetch.
What it helps with
- turn a vague idea into a written skill spec
- collect concrete usage examples and trigger phrases
- decide between a single-file skill and one with scripts or assets
- check the skill description for third-person wording and trigger keywords
- plan staged context loading and test cases before generation
Example prompts for the agent
- Draft a skill spec for database migrations, start with concrete usage examples
- Interview me about a code review checklist skill and write the specification
- Turn my PDF processing request into a skill spec with scripts and test cases
How to install skill-elicitation-agent
Manually: put the files in place
.claude/agents/skill-elicitation-agent.mdFor all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention
Manually: put the files in place
.codex/agents/skill-elicitation-agent.tomlCodex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/
Manually: put the files in place
.cursor/agents/skill-elicitation-agent.mdCursor also reads .claude/agents/
Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean
Questions about skill-elicitation-agent
How do I install skill-elicitation-agent in Claude Code?
Copy the agent file from the qdhenry/Claude-Command-Suite repository to .claude/agents/skill-elicitation-agent.md in your project.
What does skill-elicitation-agent do?
It interviews you about the skill you want: asks for concrete examples, narrows down scope and complexity, then assembles a spec with triggers, file layout and test cases.
Which tools does it have?
Read, Write, Grep, Glob and WebFetch. Writing covers the spec file, and WebFetch pulls in skill documentation when needed.