Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Code Reviewer — measured AI agent skill | DecimalAI

stijnman/code-reviewer

SkillScore100Maintained

Reviews code changes for bugs, style, security, and maintainability. Use aft erwriting code or when user says review code, code review, check my PR. Trig gers: review code, code review, check my changes. Use when the user needs th is capability.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull stijnman-code-reviewer

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-code-reviewer/SKILL.md

Raw file: /s/stijnman-code-reviewer/SKILL.md ↗ · machine-readable summary at /s/stijnman-code-reviewer.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +4% lift+14% tokens0% turns100% of whole cases pass with skill (23/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-22	✗→✓	▲ Improved	77%	0%
case-01	✓→✓	＝ Same ✓	47%	0%
case-02	✓→✓	＝ Same ✓	-11%	0%
case-03	✓→✓	＝ Same ✓	36%	0%
case-04	✓→✓	＝ Same ✓	21%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/code-reviewer/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Code Reviewer

When to Use

User says review code or task matches this capability
User says code review or task matches this capability
User says check my PR or task matches this capability
User says review my changes or task matches this capability

Workflow

Read diff or changed files; understand intent.
Check: correctness, edge cases, security, tests, style.
Categorize findings: critical / major / minor / nit.
Suggest concrete fixes with file:line references.

Integrations

auto-tester
goal-verifier
self-refine-loop

Error Handling

| Failure | Response | |---------|----------| | No diff available | Ask user for files or git diff. |

Gotchas

Critical security issues block merge recommendation.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/code-reviewer would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.