AB critical-thinking
Use this skill when the user asks for critical thinking (including naming it or directing use/apply/run with obvious misspellings; decisive) or wants to evaluate a claim, argument, plan, or belief: clarify assertions, weigh evidence, surface assumptions, test reasoning for gaps or fallacies, scan biases, consider alternatives, and stress-test conclusions—whether they phrase it plainly ("red team", "devil's advocate", "what am I missing", steel/straw man, bias scan) or indirectly (decision-quality review, epistemic calibration). Skip for execution-only tasks with no evaluative angle, or when they only want wording, tone, layout, or open-ended brainstorming with no request to audit reasons, assumptions, or evidence.
decisive) or wants to evaluate a claim, argument, plan, or belief: clarify assertions, weigh evidence, surface assumptions, test reasoning for gaps or…
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:9Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)plainly ("red team", "devil's advocate", "what am I missing", steel/strawquoted
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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 19 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1189 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
- +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
- +5Description quotes 3 example trigger phrases
- +3Description length 723: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 19 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.