AB socratic-dialogue
Reasoning rigor and anti-sycophancy guard for high-stakes decisions. Refuses to answer until the question is anchored to operational definitions, cross-examined against prior commitments, and validated by an internal faithfulness check. For high-stakes, ambiguous, or strategically loaded reasoning.
As a process B 78/100 · Nearly there — weak spots: consistency, running it twice, 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-securityreferences/methodology-socratic-dialogue.md:114Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)The model will sometimes rate its own confidence higher than it should (sycophancy, fluency bias). The Faithfulness Check (Focused Self-Query) is the safety net. The model is asked to generate **quest
quoted
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 78/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (socratic-dialogue) differs from the folder (socratic-dialog)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Execution cost. Instruction body is 1913 tokens
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +3Description length 299: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.