AC authority-bias
Activate when: someone says 'should we trust the expert on this?', 'they're a professor/CEO/MD so they must be right', 'I don't want to push back on them', 'we deferred to the board and it blew up', or is evaluating a charismatic founder, assessing due diligence on a high-credential deal, or building a team where senior voices dominate.
Activate when: someone says 'should we trust the expert on this?', 'they're a professor/CEO/MD so they must be right', 'I don't want to push back on them'…
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:57Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**S6 — Structural counter (if you are the authority):** Explicitly invite dissent ("give me 3 reasons against") · separate suggestions from directives · install red team / premortem. -
low Risky intent
intent-offensive-securitySKILL.md:109Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- No red team / premortem / devil's advocate on a high-stakes call
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Missing closing "quote at line 2, column 353: …nce on a high-credential deal, or building a team where senior voices dominate. ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1882 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 338: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 26 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.