Ready to supercharge your AI agents?

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

Code Quality Evaluator Agent · ibrahim-3d | DecimalAI

code reviewby ibrahim-3d

Code Quality Evaluator Agent

ibrahim-3d/eval-code-quality

Source ibrahim-3d/orchestrator-supaconductor ↗License AGPL-3.0

Specialized code quality evaluator for the Evaluate-Loop. Use this for evaluating code implementation tracks where the deliverable is functional code — features, API routes, state management, utilities. Checks build integrity, type safety, code patterns, error handling, dead code, imports, test coverage, and naming conventions. Dispatched by loop-execution-evaluator when track type is 'feature', 'refactor', or 'infrastructure'. Triggered by: 'evaluate code', 'code review', 'quality check', 'buil

SkillScore91Maintained

Automatic

QA & Test Engineering pack

Last verified 8/23/2026

What it changes

Passed 20 of 22 test cases with the skill, and 14 of 22 without it.

Without skill64%

With skill91%

Checks it passed that the model alone missed

Requires kebab-case formatting for filenames
Requires 90 percent test coverage for core business logic
Requires 70 percent overall test coverage across the repository

and 5 more in the full report

6 fixed14 passed either way2 still failing0 broke

Pass-rate lift: +27 pp
Tokens: +49%
Agent turns: 0%
Response time: -31%

Model gemini-3.6-flashMeasured 8/23/2026v120 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ibrahim-3d-eval-code-quality/SKILL.md https://app.decimal.ai/s/ibrahim-3d-eval-code-quality/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ibrahim-3d-eval-code-quality, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ibrahim-3d-eval-code-quality/ and pins it in .decimal/skills.lock

decimalai skills add ibrahim-3d-eval-code-quality

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ibrahim-3d-eval-code-quality/SKILL.md https://app.decimal.ai/s/ibrahim-3d-eval-code-quality/SKILL.md

Raw file: /s/ibrahim-3d-eval-code-quality/SKILL.md ↗ · machine-readable summary at /s/ibrahim-3d-eval-code-quality.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

When a code quality evaluation finishes with zero failing checks across all six passes, what orchestration handoff route should be specified in the evaluation summary?

What was checked, without and with the skill
Checked	Without skill	With skill
Directs handoff return to execution evaluator for conductor completion marking	Missed	Passed

case-20 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md180 linessingle file

Code Quality Evaluator Agent

Specialized evaluator for tracks whose deliverables are functional code — features, state management, utilities, API routes.

When This Evaluator Is Used

Dispatched by loop-execution-evaluator when the track is one of:

Feature implementation (e.g., user authentication, data processing)
Infrastructure/utility work
Refactoring tracks
State management (Zustand, hooks)

Inputs Required

Track's spec.md and plan.md
Changed files (from plan.md task summaries or git diff)
tsconfig.json — TypeScript config
package.json — dependencies and scripts
Existing test files (if any)

Evaluation Passes (6 checks)

Pass 1: Build Integrity

npm run build    # Must exit 0
npx tsc --noEmit # Must exit 0 (no type errors)

### Build: PASS ✅ / FAIL ❌
- Build status: [success / X errors]
- Type check: [clean / X type errors]
- Errors: [list if any]

Pass 2: Type Safety

Check	What to Look For

Track record

Benchmark

20 / 22

test cases passed, vs 14 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

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

ibrahim-3d / orchestrator-supaconductor

skills/eval-code-quality/SKILL.md

View on GitHub ↗

License AGPL-3.0Imported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Code Quality Evaluator Agent

When This Evaluator Is Used

Inputs Required

Evaluation Passes (6 checks)

Pass 1: Build Integrity

Pass 2: Type Safety

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills