Skip to content
Agentmart
Submit a tool

brainstorming

Design-first workflow with HARD-GATE — no code until design is approved

Skill by MaxFerAlten

IndexedMIT
Write a review

Chalk Labs

Need help deploying brainstorming?

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.

Book a call

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/maxferalten-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.

We use your email only for this newsletter. Privacy

About

Design-first workflow with HARD-GATE — no code until design is approved

Use cases: design, productivity

No 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/brainstorming

What's inside

Skill name
brainstorming
Description
Design-first workflow with HARD-GATE — no code until design is approved
License
MIT
Instructions
56 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Brainstorming — Design-First HARD-GATE

## HARD-GATE RULE

**NO CODE MAY BE WRITTEN until ALL of the following gates are passed.**
This is non-negotiable. Any attempt to write, edit, or generate implementation
code before gate approval MUST be rejected.

## Flow

1. **Explore**: Understand the problem space. Read existing code, docs, tests. Identify constraints, dependencies, and affected surfaces.
2. **Clarify**: Ask the user focused questions to resolve ambiguities. Do NOT assume. Each question must reduce ambiguity measurably.
3. **Propose 3 Approaches**: Generate at least 3 distinct solution approaches with trade-offs (complexity, risk, performance, maintainability).
4. **Design Document**: Produce a structured design doc with:
   - Objectives (what success looks like)
   - Constraints (what must NOT change)
   - UX/API surface (how it looks to consumers)
   - Risks (what could go wrong)
   - Expected outputs (files to create/modify, tests to write)
5. **Self-Review**: Critique your own design. Identify weak points, missing edge cases, over-engineering.
6. **User Approval**: Present the design and WAIT for explicit user approval before ANY implementation.

## Gates

- [ ] Problem space explored (existing code read)
- [ ] Ambiguities resolved (questions asked and answered)
- [ ] 3+ approaches proposed with trade-offs
- [ ] Design document complete (objectives, constraints, risks, outputs)
- [ ] Self-review performed
- [ ] User has explicitly approved the design

## Rules

- NEVER skip straight to code. The purpose of this skill is to THINK FIRST.
- If the user says "just do it" or "skip design", remind them of the HARD-GATE and ask which gates they want to mark as passed.
- All design artifacts are saved to `.tenderclaw/designs/`.
- The design document must list EVERY file that will be created or modified.
- No placeholder code. No TODO comments. No "implement later" stubs.

## Anti-Patterns

- Writing code before the design is approved
- Skipping the self-review step
- Proposing only one approach
- Leaving ambiguities unresolved
- Design docs without concrete file paths

## Agents

- oracle (research & architecture analysis)
- metis (strategy & gap analysis)
- prometheus (requirements gathering)

Task: {{ARGUMENTS}}

From MaxFerAlten/tenderclaw, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Apr 17, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from MaxFerAlten

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 brainstorming 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying brainstorming?

CallGet help
Cite this page

brainstorming skill. Agent Mart. https://agentmart.dev/skills/maxferalten-brainstorming (last updated 2026-10-24)