Ready to supercharge your AI agents?

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

Get Started Free →

Code Review Gate — measured AI agent skill | DecimalAI

a5c-ai/code-review-gate

SkillScore32Maintained

Perform code review with quality scoring and configurable threshold enforcement.

by a5c-ai

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

Automatic

Coding pack

decimalai skills pull a5c-ai-code-review-gate

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-code-review-gate/SKILL.md

Raw file: /s/a5c-ai-code-review-gate/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-code-review-gate.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

Runs

—

no usage data yet

Used when offered

—

offered 312 · activation not measurable for prompt-injection usage

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

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 9d ago

—-28% tokens0% turns32% of whole cases pass with skill (7/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	-48%	0%
case-12	✗→✓	▲ Improved	-61%	0%
case-17	✗→✓	▲ Improved	-57%	0%
case-21	✗→✓	▲ Improved	-70%	0%
case-22	✗→✓	▲ Improved	-73%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

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

a5c-ai / babysitter

library/methodologies/automaker/skills/code-review-gate/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v2

Skill contents

SKILL.md

Code Review Gate

Capabilities

Performs architect-level code review enforcing four core principles: DRY (no unnecessary duplication), YAGNI (no speculative features), proper abstraction (correct encapsulation), and test coverage (adequate automated tests). Provides numeric quality scores and specific file:line feedback.

Tool Use Instructions

Use Read to examine code changes and test files
Use Grep to search for duplication patterns and anti-patterns
Use Glob to verify test file coverage
Use Bash to run lint, test, and coverage commands
Use Write to generate review reports

Process Integration

Used in maestro-orchestrator.js Phase 4 (Architect Code Review)
Used in maestro-development.js (PR Review Cycle)
Used in maestro-hotfix.js (Expedited Review)
Maps to tasks: maestro-architect-code-review, maestro-dev-architect-review, maestro-hotfix-review
Agents: Architect, Code Reviewer
Quality convergence loop: rejected code returns to coder for fixes
Checks are "turned up to 11" by default

Want to see if a5c-ai/code-review-gate 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.