Agent skill
intent-capture
Capture user intent through guided conversation. Exploratory phase with high degrees of freedom.
Install this agent skill to your Project
npx add-skill https://github.com/fabriqaai/specs.md/tree/main/src/flows/fire/agents/planner/skills/intent-capture
SKILL.md
<degrees_of_freedom> HIGH — This is a creative, exploratory phase. Ask open-ended questions. Don't constrain prematurely. </degrees_of_freedom>
<question if="unclear who benefits">
Who is this for? Who will use this feature?
</question>
<question if="unclear problem">
What problem does this solve? What's painful today?
</question>
<question if="unclear scope">
What's the minimum that would be valuable? What can wait?
</question>
<question if="unclear constraints">
Any technical constraints? Existing systems to integrate with?
</question>
<question if="unclear success">
How will you know this is working? What does success look like?
</question>
**Goal**: {summarized goal}
**Users**: {who benefits}
**Problem**: {what pain this solves}
**Success Criteria**:
- {criterion 1}
- {criterion 2}
- {criterion 3}
**Constraints**:
- {constraint 1}
- {constraint 2}
Is this accurate? [Y/n/edit]
</output>
<check if="response == n or edit">
<action>Ask specific clarifying questions</action>
<goto step="3"/>
</check>
Saved to: .specs-fire/intents/{intent-id}/brief.md
---
Ready to break this into work items? [Y/n]
</output>
<check if="response == y">
<invoke_skill>work-item-decompose</invoke_skill>
</check>
<output_artifacts>
| Artifact | Location | Template |
|---|---|---|
| Intent Brief | .specs-fire/intents/{id}/brief.md |
./templates/brief.md.hbs |
| </output_artifacts> |
<success_criteria> User intent fully understood through dialogue Goal, users, problem clearly captured Success criteria defined Constraints identified Intent brief saved to correct location State.yaml updated with new intent </success_criteria>
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
run-status
Display current run status and progress. Shows work item, mode, duration, and files changed.
run-plan
Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.
walkthrough-generate
Generate implementation walkthrough for human review after run completion. Documents decisions, changes, and verification steps.
code-review
Review code written during a run, auto-fix no-brainer issues, and suggest improvements requiring confirmation. Invoked after tests pass.
run-execute
Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (batch/wide) runs.
Didn't find tool you were looking for?