AC first-principles-thinking
Use this skill when the user asks for first-principles thinking or first principles (including naming them or directing use/apply/run with obvious misspellings; decisive) or wants to reason from bedrock—stripping borrowed analogies and convention, surfacing fundamentals, then rebuilding the reasoning chain and implications. Use when they want to reason from scratch, challenge industry defaults, want physics-style business breakdowns, or sanity-check whether copying incumbents still makes sense, even if they never say first principles. Skip when they want a quick convention-following checklist with no rebuild of assumptions, or purely social coordination with no modeling ask.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (first-principles-thinking) differs from the folder (first-principles-reasoning)
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 11 steps
- 100Execution cost. Instruction body is 608 tokens
- 100Running it twice. No mutating operations
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 683: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 11 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.