brainstorm-workflow
Design and evolve the strict multi-stage brainstorming workflow, including prompts, validation rules, stage outputs, and transition policies.
Skill by Guillaume-Lombardo
Chalk Labs
Need help deploying brainstorm-workflow?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/guillaume-lombardo-brainstorm-workflow
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
Use cases: design, productivity
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/brainstorm-workflow
What's inside
- Skill name
brainstorm-workflow- Description
- Design and evolve the strict multi-stage brainstorming workflow, including prompts, validation rules, stage outputs, and transition policies.
- License
- MIT
- Instructions
- 53 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Brainstorm Workflow Skill ## Purpose Keep the product focused on strict project framing through ordered stages and explicit artifacts. ## Workflow Rules 1. Preserve the fixed stage order. 2. Separate LLM analysis from rule-based transition validation. 3. Keep one prompt file per responsibility. 4. Keep stage outputs aligned with typed schemas. 5. Treat Markdown documents as first-class persisted artifacts. ## Required Outputs Per Turn Every assistant turn must produce: - `summary` - `facts` - `assumptions` - `decisions` - `uncertainties` - `open_questions` - `risks` - `markdown` - `stage_is_clear_enough` - `transition_decision_reason` ## Stage Design Rules - Never skip a stage. - Never invent missing business information. - Explicitly mark uncertainty and contradictions. - Ask targeted questions until required fields are clear enough. - Only advance when coded validation rules and bounded LLM analysis agree. ## Prompt Organization - `src/brainstorm_agent/resources/prompts/v*/system.md`: global behavior and invariants - `src/brainstorm_agent/resources/prompts/v*/stages/`: one file per workflow stage - `src/brainstorm_agent/resources/prompts/v*/evaluation/completeness.md`: completeness and blocking holes - `src/brainstorm_agent/resources/prompts/v*/evaluation/contradiction-challenge.md`: contradiction and ambiguity review - `src/brainstorm_agent/resources/prompts/v*/rendering/step-markdown.md`: Markdown rendering instructions ## Deliverables - Updated stage contracts - Updated prompt assets - Updated validation logic plan - ADR reference when stage architecture changes materially
From Guillaume-Lombardo/brainstorm-agent, MIT.
More from Guillaume-Lombardo/brainstorm-agent
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 30, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Guillaume-Lombardo
- 0.473score
setup-ai-project-tooling
Guillaume-Lombardo
Use when installing standard AI-agent project tooling such as AGENTS.md, PLAN.md, CONTEXT.md, and project-local skills.
SkillCFreshness: CClaude Code +9 - 0.469score
code-review
Guillaume-Lombardo
Use when reviewing code for bugs, regressions, risks, and missing tests.
SkillCFreshness: CClaude Code +9 - 0.469score
dependency-upgrade
Guillaume-Lombardo
Use when upgrading dependencies with changelog review, compatibility checks, and focused tests.
SkillCFreshness: CClaude Code +9 - 0.469score
ci-diagnose
Guillaume-Lombardo
Use when diagnosing failing CI jobs, logs, environment differences, and flaky checks.
SkillCFreshness: CClaude Code +9 - 0.469score
repo-handoff
Guillaume-Lombardo
Use when preparing repository state, conventions, and next steps for another maintainer or agent.
SkillCFreshness: CClaude Code +9 - 0.469score
adr-writing
Guillaume-Lombardo
Use when writing architecture decision records with context, decision, rationale, and consequences.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get brainstorm-workflow running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
brainstorm-workflow skill. Agent Mart. https://agentmart.dev/skills/guillaume-lombardo-brainstorm-workflow (last updated 2026-10-24)