AC ai-code-scanner
AI-powered code review tool with API backend for security & quality analysis (代码审查工具+安全质量检测API). Scan code for security vulnerabilities, quality issues, and best practice violations via real API backend. Features: (1) API-powered static analysis detecting 50+ dangerous patterns across Python/JavaScript/TypeScript/Go/Java/Rust, (2) Security scanning: eval(), hardcoded passwords, command injection, XSS, deserialization risks, (3) Quality rules: TODO/FIXME detection, debug statements, empty catch blocks, HTTP vs HTTPS, (4) Code quality scoring (0-100) with approve/reject recommendation, (5) Executable review.sh script for CLI code review. Free tier: 20 reviews/month. Use when: code review, security audit, code quality check, PR review, static analysis, code scanning. Triggers: code review, security audit, code quality, PR review, static analysis, code scanning, Python security, JavaScript security, code review API, security scanner, code review tool, 代码审查, 安全检测, 代码质量, 代码扫描, 静态分析, 安全审计.
As a process C 57/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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: 3. 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 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 667 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
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)
- +3Description length 997: 120–800 characters recommended
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 16 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.