From dm-work
Use when the user wants to explore approaches or discuss design before implementation. Explores intent, requirements, and design through collaborative dialogue.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dm-work:brainstormingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn ideas into fully formed designs through natural collaborative dialogue.
Turn ideas into fully formed designs through natural collaborative dialogue.
Process: Understand context → Ask questions one at a time → Explore approaches → Present design incrementally → Validate each section.
Before asking questions:
Rules:
Focus on:
Before exploring approaches, run these four checks on the idea:
| Check | Question | Red Flag |
|---|---|---|
| Clarity | Can someone explain what this does in one sentence? | They describe internals, not outcomes |
| Timeline | Is the value immediate or does it compound over time? | Neither — value is vague or hypothetical |
| Perception | Can the user see/feel it working? | Value is invisible or requires explanation |
| Discovery | Does the user seek this out, or must they stumble into it? | Must be explained repeatedly to new users |
Any red flags → address them as design constraints in Phase 2, not afterthoughts.
Once you understand the goal:
Example:
I see three approaches:
1. **Component-based** (recommended) - Fits your existing pattern,
easiest to test, but more files.
2. **Inline** - Fewer files, but harder to reuse and test.
3. **Hook-based** - Most flexible, but adds complexity you may not need.
I'd go with #1 because [reasoning]. Thoughts?
Once approach is chosen:
Cover:
Write validated design to:
docs/plans/YYYY-MM-DD-<topic>-design.md
Commit to git.
Ask: "Ready to set up for implementation?"
Then:
dm-work:worktrees to create isolated workspacedm-work:orchestrator patterns for delegation| Principle | Why |
|---|---|
| One question at a time | Don't overwhelm |
| Multiple choice preferred | Easier to answer |
| YAGNI ruthlessly | Remove unnecessary features |
| Explore alternatives | Always 2-3 approaches before settling |
| Incremental validation | Present design in sections |
| Be flexible | Go back when something doesn't fit |
| Don't | Do Instead |
|---|---|
| Jump to implementation | Understand first, design second |
| Ask 5 questions at once | One question per message |
| Present monolithic design | Break into 200-300 word sections |
| Skip trade-off discussion | Always propose 2-3 approaches |
| Assume you understand | Validate understanding with user |
1. Check project context (files, docs, commits)
2. Ask questions one at a time (prefer multiple choice)
3. Propose 2-3 approaches with trade-offs
4. Present design in sections, validate each
5. Write to docs/plans/YYYY-MM-DD-<topic>-design.md
6. If implementing: worktree → beads → orchestrate
npx claudepluginhub rbergman/dark-matter-marketplace --plugin dm-workGuides ideas into approved designs through dialogue: explores context, clarifies requirements one question at a time, proposes approaches with trade-offs, iterates sections until approval, then documents.
Refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation before writing code or plans.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.