Ready to supercharge your AI agents?

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

Get Started Free →

Review · yeachan-heo | DecimalAI

code reviewby yeachan-heo

Review

yeachan-heo/omc-review

Source yeachan-heo/oh-my-claudecode ↗License MIT

Evaluate finished work for defects, risk, and simplification before it ships

SkillScore71Maintained

Automatic

Coding pack

Last verified 9/26/2026

What it changes

Passed 17 of 24 test cases with the skill, and 13 of 24 without it.

Without skill54%

With skill71%

Checks it passed that the model alone missed

The response refrains from outputting a full refactored implementation of checkout.py.
The response explains that review should occur in a separate context from active authoring.
The response clarifies that the review output is advisory rather than an automated CI process blocker.

and 1 more in the full report

4 fixed13 passed either way7 still failing0 broke

Pass-rate lift: +17 pp
Tokens: +12%
Agent turns: 0%
Response time: +15%

Model gemini-3.6-flashMeasured 9/26/2026v117 of 24 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/yeachan-heo-omc-review/SKILL.md https://app.decimal.ai/s/yeachan-heo-omc-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yeachan-heo-omc-review, 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/yeachan-heo-omc-review/ and pins it in .decimal/skills.lock

decimalai skills add yeachan-heo-omc-review

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

curl -fsSL --create-dirs -o .claude/skills/yeachan-heo-omc-review/SKILL.md https://app.decimal.ai/s/yeachan-heo-omc-review/SKILL.md

Raw file: /s/yeachan-heo-omc-review/SKILL.md ↗ · machine-readable summary at /s/yeachan-heo-omc-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

I am currently editing `src/api/auth.py` in this active context turn. As the author making changes right now, perform the canonical review on my draft while drafting the rest of `auth.py` in this same context turn.

What was checked, without and with the skill
Checked	Without skill	With skill
The response explains that review should occur in a separate context from active authoring.	Missed	Passed

case-15 · gemini-3.6-flash · 9/26/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md37 linessingle file

Review

Use this skill to evaluate work that already exists. Review never authors the change it is judging.

This is the canonical review workflow. merge-readiness routes here, and ai-slop-cleaner is an opt-in lane within it.

Goal

Find what is actually wrong, ranked by severity, with enough detail to act on.

Workflow

Establish what changed and what it was meant to do.
Read the change against that intent.
Check correctness first, then risk, then simplification.
Verify each candidate finding before reporting it.
Report findings most-severe first.

What to check

Correctness — logic defects, edge cases, error paths, concurrency
Risk — security boundaries, destructive operations, data integrity
Reuse — existing utilities or patterns the change should have used
Simplification — code that could be deleted or collapsed
Coverage — behavior that ships untested

Rules

Separate lanes: the reviewer must not be the author's same active context.
Verify before reporting. A plausible-sounding finding that does not reproduce is noise.
State severity honestly; do not pad the list to look thorough.
"No findings" is a valid result when the work is sound.
Advisory by default — review informs, it does not gate. Hard gates (release, security, destructive operations) stay separate and fail closed.

Output

Findings, most-severe first, each with file, line, and concrete failure scenario
What was checked and found clean
Anything that could not be assessed

Track record

Benchmark

17 / 24

test cases passed, vs 13 / 24 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 v5 — 8/24/2026

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

yeachan-heo / oh-my-claudecode

skills/review/SKILL.md

View on GitHub ↗

License MITImported 8/24/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Review

Goal

Workflow

What to check

Rules

Output

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills