code review by alibaba
Code Quality Analyzer alibaba/code-quality-analyzer
Triggered when the user submits code or requests a comprehensive code quality analysis. Automatically performs static analysis, code review, and quality scoring. Analysis covers coding standards, potential bugs, performance issues, and security vulnerabilities. Trigger phrases include "analyze code quality", "comprehensive check", "code score".
What it changes View full report → Passed 20 of 22 test cases with the skill, and 17 of 22 without it.
Without skill 77%
With skill 91%
Checks it passed that the model alone missed and 1 more in the full report
4 fixed16 passed either way1 still failing1 broke
Pass-rate lift +14 pp
Tokens +19%
Agent turns 0%
Response time +7% Model gemini-3.6-flashMeasured 8/21/2026 v1 20 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/alibaba-code-quality-analyzer/SKILL.md https://app.decimal.ai/s/alibaba-code-quality-analyzer/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add alibaba-code-quality-analyzer, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/alibaba-code-quality-analyzer/ and pins it in .decimal/skills.lock
$ decimalai skills add alibaba-code-quality-analyzerCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/alibaba-code-quality-analyzer/SKILL.md https://app.decimal.ai/s/alibaba-code-quality-analyzer/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Audit this C++ vector lookup routine for quality standard compliance:
#include <vector>
#include <string>
bool contains_val(const std::vector<std::string>& vec, const std::string& target) {
for(size_t i = 0; i < vec.size(); ++i) {
if(vec[i] == target) return true;
}
return false;
}
What was checked, without and with the skill Checked Without skill With skill The response contains an evaluation section for Maintainability. The response contains an evaluation section for Performance.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 24 lines single file
Code Quality Analyzer
You are a comprehensive code quality analysis assistant capable of evaluating code along multiple dimensions.
Analysis Dimensions
Correctness : logic errors, boundary conditions, null value handlingMaintainability : code structure, naming conventions, comment completenessPerformance : algorithm efficiency, resource usage, memory managementSecurity : input validation, injection risks, sensitive data handling
Output Format
Analysis report includes:
Overall quality score (1–10)
Detailed evaluation for each dimension
Specific issue list (with locations and fix suggestions)
Improvement priority ranking
Notes
Analysis should be objective and evidence-based
Identify both strengths and weaknesses
Fix suggestions should be directly actionable
Track record Benchmark 20 / 22
test cases passed, vs 17 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License Apache-2.0Imported 8/3/2026Version v1