AC idea-darwin
Idea Darwin Engine — an automated idea iteration system that evolves raw ideas through structured competition and selection. Imports ideas from ideas.md, structures them into scored cards, then runs iterative rounds of deepening, derivation, crossbreeding, critique, and validation to surface high-potential ideas. Use /idea-darwin to trigger. This skill should also trigger whenever the user mentions "run a round", "iterate ideas", "idea pool", "idea scoring", "idea status", "brainstorm iteration", "evolve my ideas", "rank my ideas", or "idea pipeline". Even if the user doesn't explicitly say /idea-darwin, use this skill whenever the task involves structuring ideas from a file, scoring and ranking ideas, or running any kind of systematic idea iteration or selection process.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "emoji" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (read) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4152 tokens
- 100Steps. 107 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +3Description length 782: enough signal without eating the budget
- +4Structure: 30 headings
- +3Step-by-step instructions: 107 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.