AC midas-skill
Midas Skill — Turn Your Repeated Orders Into Gold. A self-learning wealth extraction engine that takes the mundane, repetitive information streams of your daily life — office small talk, casual photos, browsing history, group chats, complaints, autopilot purchases — and distills them into actionable money signals, demand gaps, arbitrage windows, and monetization paths. You don't need a Bloomberg terminal. You need to stop ignoring the wealth signals you already encounter every day. Midas also maintains pre-built "wealth operating systems" of famous figures (Musk, Buffett, Thiel, etc.) and pattern-matches YOUR signals against THEIR playbooks to generate personalized strategies. Nuwa distills how people think. Midas distills how to turn your noise into money. Trigger words: "Midas", "turn this into gold", "what money signal is here", "deal analysis", "noise to gold", "mine this", "golden touch", "点石成金", "what am I missing", "Midas mode"
As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
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: 26. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "trigger_words"
Process rating: all ten parameters 59/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (midas-skill) differs from the folder (midas)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 100Steps. 73 steps
- 100Execution cost. Instruction body is 3341 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 953: 120–800 characters recommended
- -44 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 27 headings
- +3Step-by-step instructions: 73 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.