idea-darwin
Darwinian idea evolution engine — toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- idea-darwin
- risk
- safe
- source
- community
- date_added
- 2026-04-07
- description
- Darwinian idea evolution engine — toss rough ideas onto an evolution island, let them compete, crossbreed, and mutate through structured rounds to surface your strongest concepts.
03 SKILL.md 正文
Idea Darwin Engine
A round-based idea iteration system that treats ideas as competing organisms — scoring, selecting, crossing, and evolving them through structured rounds to surface the strongest concepts.
Overview
Most idea management tools are filing cabinets: they store ideas, tag them, and let them rot. Idea Darwin flips the paradigm — instead of organizing ideas, it lets them compete. Every idea is a living species on an evolution island. Each round, the fittest get deepened, different ideas cross-pollinate to produce unexpected hybrids, and external stimuli trigger mutations.
When to Use This Skill
- Use when you have many scattered ideas and need to systematically evaluate and develop them
- Use when you want to discover unexpected connections between ideas from different domains
- Use when you need structured iteration rather than one-shot brainstorming
- Use when you want a scoring framework to prioritize which ideas deserve more investment
Core Concepts
Evolution Island Metaphor
Your ideas are alive on this island. Like organisms, they follow three core laws:
- Evolution — Each round, the system deepens the most viable ideas through structured research: filling logical gaps, clarifying paths, identifying risks.
- Crossbreeding — The system cross-pollinates different ideas. A technical approach from work meets an observation from daily life, producing directions you never imagined.
- Mutation — External stimuli (industry news, theories, conversations) trigger mutations, spawning entirely new species.
Species Cards
Every idea gets a structured card recording: core question, full description, lineage (parent/child IDs), 6-dimensional scores, and change history.
6-Dimensional Scoring
| Dimension | Weight | What It Measures |
|---|---|---|
| Novelty | 10% | Genuine breakthrough or repetition? |
| Feasibility | 20% | Technically and resource-wise achievable? |
| Value | 20% | Impact if successful? |
| Logic | 20% | Internally consistent, no gaps? |
| Cross Potential | 10% | Can spark something new when combined? |
| Verifiability | 20% | Can we design a validation path? |
Idea Lifecycle
seed → exploring → refining → crossing → validated → dormant
The user always has final say on all life-or-death decisions. The system only recommends.
Step-by-Step Guide
1. Write Your Ideas
Create an ideas.md file:
## Personal knowledge base that learns my style
I want a system that reads everything I write and gradually learns how I think.
## Commute-to-podcast converter
Record voice memos during my commute, auto-convert them into podcast scripts.
2. Initialize Your Island
/idea-darwin init
3. Start Evolving
/idea-darwin round
4. Keep Feeding the Island
Append new ideas to ideas.md, add environmental variables to stimuli.md.
Examples
Example 1: Initialize
/idea-darwin init --budget 8 --actions 3
Example 2: Run Multiple Rounds
/idea-darwin round 3
Example 3: Manage Ideas
/idea-darwin dormant IDEA-0005
/idea-darwin wake IDEA-0005
Best Practices
- Do: Write ideas as rough as you want — the system structures them
- Do: Add external stimuli to prevent idea convergence
- Do: Run disruption rounds to surface overlooked ideas
- Don't: Over-curate initial ideas — let evolution filter
- Don't: Ignore the "Decisions Needed" section in briefings
Additional Resources
- GitHub Repository
- Available in 3 languages: English, Chinese, Japanese
- ClawHub:
clawhub install idea-darwin
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.