Ready to supercharge your AI agents?

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

Yamada UI/PR Review Anti Patterns — measured AI agent skill | DecimalAI

yamada-ui/pr-review-anti-patterns

NewSkillScoreMaintained

Add or remove entries in .agents/references/pr-review-anti-patterns/. Use when the user wants to document a review miss from one or more merged PRs, or remove a stale anti-pattern entry.

agent-toolingby yamada-ui

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

Automatic

Coding pack

decimalai skills pull yamada-ui-pr-review-anti-patterns

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/yamada-ui-pr-review-anti-patterns/SKILL.md

Raw file: /s/yamada-ui-pr-review-anti-patterns/SKILL.md ↗ · machine-readable summary at /s/yamada-ui-pr-review-anti-patterns.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

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 2h ago

—-42% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	-22%	0%
case-05	✗→✓	▲ Improved	-50%	0%
case-07	✗→✓	▲ Improved	-46%	0%
case-09	✗→✓	▲ Improved	-61%	0%
case-11	✗→✓	▲ Improved	-59%	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 — 8/3/2026

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

yamada-ui / yamada-ui

.agents/skills/pr-review-anti-patterns/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 3 files

Skill contents

references/

assets/

SKILL.md

Overview

Add or remove entries in the PR Review Anti-Patterns, which collect cases from past PRs where each AI approved changes that the maintainer disagreed with, or where each AI approved based on incorrect knowledge or interpretation.

Gotchas

When adding, modifying, or deleting files, always do so in a new worktree branched from origin/main.
Keep the PR title as a single sentence that is clear to others. Do not reuse the commit message as the PR title.
Write the title and summary of each PR Review Anti-Patterns entry using search-friendly keywords so that the relevant entry is easy to find.

Steps

0: Branching

Branch on each step based on whether $ARGUMENTS is provided.

If arguments are provided: proceed to step 1.a.
If no arguments are provided: proceed to step 1.b.

1.a: Add

Follow the procedure to execute.

1.b: Delete