Ready to supercharge your AI agents?

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

Review · ccch1mneyyy | DecimalAI

code reviewby ccch1mneyyy

Review

ccch1mneyyy/review

Source ccch1mneyyy/dsh-tui ↗License MIT

Use when asked to review a codebase or a change, or when the /review command runs — assess design, correctness, maintainability, and test coverage with actionable feedback.

NewMaintained

Automatic

Coding pack

Last verified 9/9/2026

What it changes

Passed 6 of 12 test cases with the skill, and 6 of 12 without it.

Without skill50%

With skill50%

Checks it passed that the model alone missed

Checks resource cleanup across affected boundaries.
States explicitly that there are no actionable findings.
Separates demonstrated defects from optional simplifications.

and 1 more in the full report

4 fixed7 passed either way7 still failing4 broke

Pass-rate lift: 0 pp
Tokens: -11%
Agent turns: 0%
Response time: -6%

Model gemini-3.6-flashMeasured 9/9/2026v211 of 22 cases passed with skill · 12 comparable

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/ccch1mneyyy-review/SKILL.md https://app.decimal.ai/s/ccch1mneyyy-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ccch1mneyyy-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/ccch1mneyyy-review/ and pins it in .decimal/skills.lock

decimalai skills add ccch1mneyyy-review

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

curl -fsSL --create-dirs -o .claude/skills/ccch1mneyyy-review/SKILL.md https://app.decimal.ai/s/ccch1mneyyy-review/SKILL.md

Raw file: /s/ccch1mneyyy-review/SKILL.md ↗ · machine-readable summary at /s/ccch1mneyyy-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 asked for a review of my PR in `Logger.ts`. All guards, tests, and logic are fully sound. How should the review result be communicated?

What was checked, without and with the skill
Checked	Without skill	With skill
States explicitly that there are no actionable findings.	Missed	Passed
Refrains from manufacturing nitpicks.	Passed	Passed

case-22 · gemini-3.6-flash · 9/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md7 linessingle file

Review the requested scope and report actionable findings. If the user also asked for fixes, implement and verify them after establishing the cause.

Identify the target and actual base. For a stacked PR, compare with its parent branch; for a local change, include the requested staged or unstaged work. Read changed code with its callers and relevant tests.
Trace behavior across the affected boundaries: DSH event projection, channel actions, input precedence, or terminal lifecycle. Check failure paths and resource cleanup, and whether tests cover the changed behavior rather than mirror the implementation. Before calling code dead or an abstraction unnecessary, check exports, dynamic registration, compatibility requirements, and other consumers.
Verify each suspected issue against the implementation and existing guards. Report its location, concrete trigger, impact, and smallest useful fix, ordered by severity. Separate demonstrated defects from optional simplifications.
Use a short call tree or before/after diff when it explains an ownership or ordering problem more clearly than prose. Show only the affected path and use real symbols from the code.
State what was reviewed and any verification limits. If there are no actionable findings, say so; do not manufacture nits or add a compulsory praise section.

Track record

Benchmark

6 / 12

test cases passed, vs 6 / 12 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 — 9/9/2026

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

ccch1mneyyy / dsh-tui

skills/review/SKILL.md

View on GitHub ↗

License MITImported 9/9/2026Version v2

Other skills for the same job

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

yeachan-heo/omc-reviewEvaluate finished work for defects, risk, and simplification before it shipsClose match+17 pp pass-rate lift

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