frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web…
Capture user intent through guided conversation. Exploratory phase with high degrees of freedom.
$ npx -y skills add fabriqaai/specs.md --skill intent-capture --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/intent-captureContext preview
The summary Claude sees to decide when to auto-load this skill.
Capture user intent through guided conversation. Exploratory phase with high degrees of freedom.
name: intent-capture description: Capture user intent through guided conversation. Exploratory phase with high degrees of freedom. version: 1.0.0
<objective> Capture user intent through guided conversation. </objective>
<triggers>
</triggers>
<degrees_of_freedom> **HIGH** — This is a creative, exploratory phase. Ask open-ended questions. Don't constrain prematurely. </degrees_of_freedom>
<llm critical="true"> <mandate>NEVER assume requirements — ALWAYS ask clarifying questions</mandate> <mandate>Capture the "what" and "why" — leave the "how" for decomposition</mandate> <mandate>Let user describe freely — don't interrupt</mandate> </llm>
<flow> <step n="1" title="Initial Question"> <ask>What do you want to build?</ask> <listen>Let user describe freely. Don't interrupt.</listen> </step>
<step n="2" title="Elicit Context"> <action>Based on response, ask follow-up questions:</action>
<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> </step>
<step n="3" title="Summarize Understanding"> <output> Let me make sure I understand:
**Goal**: {summarized goal}
**Users**: {who benefits}
**Problem**: {what pain this solves}
**Success Criteria**:
**Constraints**:
Is this accurate? [Y/n/edit] </output> <check if="response == n or edit"> <action>Ask specific clarifying questions</action> <goto step="3"/> </check> </step>
<step n="4" title="Generate Intent Brief"> <action>Create intent ID from title (kebab-case)</action> <action>Generate intent brief using template: templates/brief.md.hbs</action> <action>Create directory: .specs-fire/intents/{intent-id}/</action> <action>Save: .specs-fire/intents/{intent-id}/brief.md</action> </step>
<step n="5" title="Update State"> <action>Add intent to state.yaml</action> <action>Set intent status to "in_progress"</action> </step>
<step n="6" title="Transition"> <output> **Intent captured**: "{intent-title}"
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> </step> </flow>
<output_artifacts>
| Artifact | Location | Template | |----------|----------|----------| | Intent Brief | `.specs-fire/intents/{id}/brief.md` | `./templates/brief.md.hbs` | </output_artifacts>
<success_criteria> <criterion>User intent fully understood through dialogue</criterion> <criterion>Goal, users, problem clearly captured</criterion> <criterion>Success criteria defined</criterion> <criterion>Constraints identified</criterion> <criterion>Intent brief saved to correct location</criterion> <criterion>State.yaml updated with new intent</criterion> </success_criteria>
AI-native development framework with pluggable flows for every use case. Choose the flow that matches your project needs: Ideation for creative brainstorming, Simple for quick specs, FIRE for adaptive execution, or AI-DLC for full methodology with DDD.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web…
Review code written during a run, auto-fix no-brainer issues, and suggest improvements requiring confirmation. Invoked after…
Execute work items based on their assigned mode (autopilot, confirm, validate). Supports single-item and multi-item (batch/wide)…
Plan the scope of a run by discovering available work items and suggesting groupings. Invoked before run-execute.
Display current run status and progress. Shows work item, mode, duration, and files changed.
Generate implementation walkthrough for human review after run completion. Documents decisions, changes, and verification steps.