Idea Darwin
v1.0.0Idea Darwin Engine — an automated idea iteration system that evolves raw ideas through structured competition and selection. Imports ideas from ideas.md, str...
⭐ 0· 64·0 current·0 all-time
byJianyang@warmskull
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (automated idea iteration) match the instructions: parse ideas.md, create cards, run rounds, score ideas, and write reports. There are no unrelated env vars, binaries, or install steps requested.
Instruction Scope
SKILL.md instructs the agent to read an ideas.md and create a project directory (config.yaml, cards/, rounds/, reports/, graph/). That's coherent for this tool. However the instructions also tell the agent to trigger on a long list of user phrases (even when the user doesn't explicitly call /idea-darwin), which is broad and could cause unexpected activations. The skill references $ARGUMENTS for CLI-style inputs (a platform variable, not a secret).
Install Mechanism
Instruction-only skill with no install spec and no code files to download or execute. This minimizes supply-chain risk.
Credentials
No credentials, env vars, or config paths are requested. The file operations described (read ideas.md, write project files) are proportionate to the stated purpose.
Persistence & Privilege
The skill does not request always:true and has no elevated platform privileges. It will create and maintain local files (config.yaml, cards/, reports/) in the working directory — expected for its function. Because autonomous invocation is allowed by default and the SKILL.md encourages triggering on many phrases, the combination increases the chance the skill will run without an explicit user command; consider whether you want that behavior.
Assessment
This skill appears to do what it says: it will read your ideas.md and create a project directory with idea cards, round reports, and a config.yaml. It does not request any credentials or install external code. Two practical cautions: (1) SKILL.md tells the agent to auto-trigger on many phrases — if you prefer explicit control, only invoke it manually or change the trigger guidance. (2) The skill will write files in the working directory; run it in a workspace where writing/reading those files is acceptable (or back up sensitive files first). If you want extra safety, inspect the repository homepage, try the skill in a disposable/test folder, and confirm it only reads ideas.md and the created project files before using it on sensitive content.Like a lobster shell, security has layers — review code before you run it.
latestvk97eeweddj5drxwzar5wa8yeks84cg1e
License
MIT-0
Free to use, modify, and redistribute. No attribution required.