AC code-review
Multi-dimensional code audit using structured subagent delegation. Use when reviewing a GitHub release, PR, or codebase. Systematically inspects security, concurrency/state-machine safety, UX/implementation logic, test quality, and simplicity/over-engineering. Spawns parallel subagents for deep verification with Four-Eyes cross-validation on critical findings. Synthesizes findings into a Confirmed/Critical-to-Low priority matrix. Trigger phrases: review this release, audit this codebase, check this PR for issues, 代码审查, review 代码, 审查这个版本, /deep-code-review, /code-review, /review-code
As a process C 50/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 7. 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 50/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (code-review) differs from the folder (deep-code-review)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Failures and branches. 6 branches
- 100Steps. 54 steps
- 100Execution cost. Instruction body is 2412 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 589: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 54 items
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.