AC code-quality-guard
Pair-style code quality reviewer: twelve book-grounded decay risks (R1–R6, T1–T6) plus release-safety and first-paint UX checks. Findings always use Iron Law (Symptom → Source → Consequence → Remedy) and a 0–100 review-index Health Score. Triggers when: user asks to review code/PR/diff, "any issues", "ready to merge", smells, refactoring, tech debt, test quality, coverage, or architecture health; or says 「结对评审」/「发版前扫一眼」/ code-quality-guard. Do NOT trigger for: greenfield "how do I write X" with no code, pure syntax questions, or tool/framework questions with no shared code.
Pair-style code quality reviewer: twelve book-grounded decay risks (R1–R6, T1–T6) plus release-safety and first-paint UX checks.
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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
-
medium Dangerous commands
cmd-destructive-fsREADME.md:37Destructive filesystem command (wipes root/home/drive) (code comment; documentation of a security skill)│ └── hooks.json # 可选：PreToolUse 拦截 rm -rf / git push --force
commentsecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 14. 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 60/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 18 steps, 3 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1481 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 580: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.