brainstorming
Use for genuinely open, load-bearing product or architecture decisions after inspecting the project.
Skill by BB-84C
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bb-84c-brainstorming
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/brainstorming
What's inside
- Skill name
brainstorming- Description
- Use for genuinely open, load-bearing product or architecture decisions after inspecting the project.
- License
- MIT
- Instructions
- 63 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- SKILL.md
- frame-template.html · scripts/
- helper.js · scripts/
- server.cjs · scripts/
- start-server.sh · scripts/
- stop-server.sh · scripts/
- spec-document-reviewer-prompt.md
- visual-companion.md
SKILL.md (first lines)
# Resolve Open Design Decisions ## When this workflow helps Use brainstorming when product behavior, architecture, interaction design, a contract, or another load-bearing choice remains genuinely open after inspecting the project. The goal is to resolve uncertainty that would otherwise change the construction path or user-visible result. Do not create a separate design ceremony for a specified local change with one reasonable path. Explain why that path is determined, then implement directly. ## Ground the decision first 1. Inspect the relevant project structure, existing behavior, constraints, and durable instructions before asking the user to choose. 2. Identify only the missing information that affects the decision. Bundle related questions when one answer depends on the others; avoid a question sequence that does not change the outcome. 3. Compare approaches only when multiple materially viable approaches remain after investigation. Do not invent weak alternatives to reach a count. 4. If one path remains, recommend it plainly and explain what made it determined. ## Explain at the right level Explain a real choice through the overall project architecture, the logical relationship between modules, construction consequences, and the product or operational behavior affected. Use an accessible analogy when it clarifies the relationship. Do not lead with code symbols unless the user asks for code detail or an identifier is needed to explain a blocker. For an unresolved load-bearing decision, present one coherent approval request that covers the decision, trade-offs, and consequences. Do not split a single approval into repeated process gates. ## Repository operations and durable artifacts Before recommending or taking commit, push, branch, or worktree actions, inspect the current context for an existing preference. Ask once when the preference is absent and the choice changes the workflow. Never push without clear authority. Write a design document when it provides durable value for multi-step execution, handoff, or future maintenance. A brief determined change does not need one. ## After the decision After approval, choose the lightest suitable execution path for the task shape: - direct implementation for a bounded determined change; - a focused plan when dependencies or durable handoff need one; or - delegated execution when bounded worker context improves the work. Keep the decision connected to the product outcome during implementation rather than turning the design into a second set of ceremony requirements. ## Visual companion When a visual question would be clearer as a mockup, diagram, or layout comparison, offer the visual companion then. Keep conceptual requirements and textual trade-offs in the conversation when a visual surface adds no clarity.
From BB-84C/superpowers-lite, MIT.
More from BB-84C/superpowers-lite
- 0.499score
subagent-driven-development
BB-84C
Consult before delegating implementation when an approved plan benefits from worker context isolation and durable coordination.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
using-superpowers
BB-84C
Consult directly matching task playbooks before substantial design, debugging, implementation, review, or completion work without forcing full workflow…
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
writing-skills
BB-84C
Use when creating, revising, validating, or deploying a reusable agent skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
using-git-worktrees
BB-84C
Use when isolation may materially improve feature work; preserve existing isolation and repository preferences.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
systematic-debugging
BB-84C
Consult before attempting a fix when root cause or behavior is unclear, failures repeat, components interact, or guessing would be unsafe.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
executing-plans
BB-84C
Use when a written plan needs coordinated inline execution.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
requesting-code-review
BB-84C
Use independent review at meaningful semantic or risk boundaries and before substantive whole-change closeout.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
dispatching-parallel-agents
BB-84C
Use when parallel workers have a net benefit over coordinated sequential work.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
writing-plans
BB-84C
Consult when multi-round implementation, context compaction, or worker handoff requires a durable execution contract.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
finishing-a-development-branch
BB-84C
Use when a real branch, integration, or discard decision needs an authorized closeout.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
verification-before-completion
BB-84C
Consult before making a substantive completion claim; require current trustworthy evidence and semantic acceptance.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
receiving-code-review
BB-84C
Consult after receiving review feedback and before implementation when the feedback needs evidence-based evaluation.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 12, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/BB-84C/superpowers-lite
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from BB-84C
- 0.499score
subagent-driven-development
BB-84C
Consult before delegating implementation when an approved plan benefits from worker context isolation and durable coordination.
SkillCFreshness: C★ 1Claude Code +9 - 0.499score
using-superpowers
BB-84C
Consult directly matching task playbooks before substantial design, debugging, implementation, review, or completion work without forcing full workflow…
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
using-git-worktrees
BB-84C
Use when isolation may materially improve feature work; preserve existing isolation and repository preferences.
SkillCFreshness: C★ 1Claude Code +9 - 0.496score
writing-skills
BB-84C
Use when creating, revising, validating, or deploying a reusable agent skill.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
systematic-debugging
BB-84C
Consult before attempting a fix when root cause or behavior is unclear, failures repeat, components interact, or guessing would be unsafe.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
executing-plans
BB-84C
Use when a written plan needs coordinated inline execution.
SkillCFreshness: C★ 1Claude Code +9
Cite this page
brainstorming skill. Agent Mart. https://agentmart.dev/skills/bb-84c-brainstorming (last updated 2026-10-24)