clarify-demand
Skill8 starsChanged 8 months agoMITView on GitHub
Conversational demand clarification and feasibility research before formal work item registration
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-codebaseSkill
- create-feature-specSkill
- define-prdSkill
- define-tech-specSkill
- manage-workSkill
- prepare-releaseSkill
- record-decisionSkill
- run-tddSkill
- validate-checkpointSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 29
Ask the user to clarify the following (skip items they've already provided):
- Distinctive: line 37
Keep the conversation natural.
- Distinctive: line 75
If they want changes, loop back to the relevant phase.
- Distinctive: line 80
Bias toward smaller tracks: When in doubt, recommend Small over Medium.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
clarify-demand
Conversational demand clarification and feasibility research before formal work item registration.
Purpose
This skill helps users go from a vague idea to a concrete work item registration. It runs before /manage-work register to ensure the right track, scope, and description are chosen.
Works on any branch (including main).
4-Phase Workflow
Phase 1: Demand Clarification
Ask the user to clarify the following (skip items they've already provided):
- Problem — What problem are you solving? What's broken or missing?
- Users — Who benefits from this? (end users, developers, ops, etc.)
- Done Criteria — How will you know it's done? What does success look like?
- Constraints — Any technical, time, or compatibility constraints?
- Scope Signal — Is this a bug fix, a single feature, a multi-component change, or a system-level change?
Keep the conversation natural. Ask follow-up questions if answers are vague. One or two rounds is usually enough.
Phase 2: Feasibility Research
Perform read-only codebase analysis:
- Does existing code support this, or is new infrastructure needed?
- What files/modules would be affected?
- Are there existing patterns to follow?
- What are the risks (high coupling, missing tests, architectural debt)?
Skip this phase for obvious Micro/Small items where the scope is clear and the change is localized.
Phase 3: Synthesis
Produce an Intake Brief (displayed in conversation, not persisted to disk):
## Intake Brief
**Problem**: [1-2 sentences]
**Users**: [who benefits]
**Feasibility**: [summary from Phase 2, or "Skipped — scope is clear"]
**Complexity**: [Low / Medium / High]
**Recommended Track**: [Micro / Small / Medium / Large]
**Rationale**: [why this track]
**Suggested Description**: "<description for register command>"
**Suggested ID**: <numeric ID>Phase 4: Handoff
Present the Intake Brief to the user. If they confirm:
/manage-work register "<description>" <ID> <track>If they want changes, loop back to the relevant phase.
Guidelines
- Ephemeral output: The Intake Brief lives in the conversation only — no files are written.
- Bias toward smaller tracks: When in doubt, recommend Small over Medium. Users can always upgrade.
- Don't over-research: Phase 2 should take 1-2 minutes, not 10. Quick scan, not deep dive.
- Natural language: This is a conversation, not a form. Adapt to the user's communication style.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

