AC code-audit
Use this skill only when the user explicitly asks for a code audit, security audit, risk-focused PR/diff review, repo or module audit, regression-risk review, project-intent drift check, or validation of another reviewer/agent's findings. Do not use for routine implementation, ordinary debugging, refactoring, test writing, docs proofreading, architecture brainstorming, frontend design review, or general "review" requests unless the user asks for audit, risk, security, regression, or evidence-backed findings. The skill reads README/AGENTS/docs first, inspects code/diffs/tests, and uses a user-specified or strongest available non-development reviewer model/subagent when policy allows; if none is available, it discloses that same-model audits can share blind spots.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- 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: 12. 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 61/100
- 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 (code-audit) differs from the folder (hollis-code-audit)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 53 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 14 branches, has a failure section
- 100Execution cost. Instruction body is 2351 tokens
- 100Running it twice. Mutating operations check current state
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 772: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.