groove-work-brainstorm — Claude Code skill: overview and install
Clarifies scope through conversation, enforces YAGNI to curb creep, and flags open questions before formal project planning starts.
npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a claude-codeWhat groove-work-brainstorm does
The skill initiates an interactive conversation to pin down project scope before implementation planning begins. It asks probing questions, writes down crucial decisions alongside their rationale, and logs unresolved topics. Unnecessary features get discarded right away because the workflow deliberately enforces YAGNI.
Implementation steps stay strictly out of this phase. Detailed technical planning belongs to /groove-work-plan. The final output lands either in a dedicated brainstorm document using the template at skills/groove-work-brainstorm/templates/brainstorm-doc.md or directly inside the task body of your configured issue tracker.
The skill relies on .groove/index.md to identify tasks.backend. Whenever that backend is set to something other than none, it calls /groove-utilities-task-create to record a stage task titled YYYY-MM-DD, Brainstorm.
What it helps with
- define and constrain scope before drafting implementation plans
- document core architectural choices alongside rationale
- capture open questions without rushing into immediate answers
- log a brainstorm stage task inside the configured project backend
Example prompts for the agent
- Start a brainstorm session for the authentication refactor
- Help me define the scope and decisions for Stripe checkout
- Clarify requirements for the notifications microservice
How to install groove-work-brainstorm
1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a claude-code2Manually: put the files in place
~/.claude/skills/groove-work-brainstorm/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/groove-work-brainstorm/
1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a codex2Manually: put the files in place
.agents/skills/groove-work-brainstorm/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a cursor2Manually: put the files in place
.cursor/skills/groove-work-brainstorm/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install andreadellacorte/groove groove-work-brainstorm2Manually: put the files in place
.github/skills/groove-work-brainstorm/SKILL.md1Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a gemini-cli2Platform CLI
gemini skills install https://github.com/andreadellacorte/groove --path skills/groove-work-brainstormManually: put the files in place
.devin/skills/groove-work-brainstorm/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about groove-work-brainstorm
How do I install groove-work-brainstorm in Claude Code?
Run npx skills add andreadellacorte/groove --skill groove-work-brainstorm -a claude-code. This installs the skill file into ~/.claude/skills/groove-work-brainstorm/SKILL.md.
What does groove-work-brainstorm do?
It runs an interactive dialogue to define scope, pushes back against feature creep, and records architectural choices along with open questions.
Why does this skill skip writing an implementation plan?
Groove delegates concrete scheduling and coding steps to /groove-work-plan. This brainstorming stage focuses entirely on scoping and surfacing open dilemmas.
Source text
SKILL.md · MIT
--- name: groove-work-brainstorm description: "Clarify scope through dialogue, surface key decisions and open questions. Use before planning." license: MIT allowed-tools: Read Write Edit Glob Grep Bash(git:*) AskUserQuestion metadata: author: andreadellacorte --- # groove-work-brainstorm ## Outcome Scope is clarified through dialogue. Key decisions and open questions are surfaced. Output is captured as a brainstorm doc or task in the configured backend. ## Acceptance Criteria - Scope is clearly defined and deliberately constrained (YAGNI applied) - Key decisions are listed with rationale - Open questions are listed (not resolved — resolution happens in plan) - Output exists either as a brainstorm doc or as a task body in the backend - Stage task created in backend: `YYYY-MM-DD, Brainstorm` ## Constraints - Read `tasks.backend` from `.groove/index.md` to determine backend - Use template at `skills/groove-work-brainstorm/templates/brainstorm-doc.md` for doc output - Enforce YAGNI — scope is deliberately constrained at this stage; push back on scope creep - Do not start planning implementation here — that belongs in `/groove-work-plan` - Ask clarifying questions before finalising scope; do not assume - If user provides $ARGUMENTS, use as the topic/title for the brainstorm - Create stage task via `/groove-utilities-task-create` if `tasks != none` (title `YYYY-MM-DD, Brainstorm`)
© andreadellacorte · MIT · andreadellacorte/groove
