Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: defects

英語版ディレクトリ

A Codex skill for generating minimal zine-style editorial poster prompts and images.

6.3K
Stars
83/100
信頼
カテゴリ: design-creative監査

Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks, PR). Dual-channel verification (DOM + pixels + vision) in a capture loop. Use for any "take/redo screenshots of the app" task.

4.5K
Stars
67/100
信頼
カテゴリ: coding-agents監査

Whole-repo audits in eight modes. Codebase — merged structural + correctness audit, should this exist AND does it do what it promises. Triggers "nuclear review", "code judo", "whole codebase review", "should this exist", "adversarial audit", "fable audit", "correctness audit", "expectation gaps". Docs/Process — doc drift, walkable journeys. Triggers "audit the docs", "doc drift", "process audit", "walk the journeys". Performance — measured-only perf audit; no finding without a number. Triggers "perf audit", "performance audit", "why is it slow", "bundle audit", "build is slow". Threat-model — abuse paths. Triggers "threat model", "STRIDE", "attack surface". Motion — animation audit. Triggers "motion audit", "audit the animations". SEO — discoverability + AEO. Triggers "seo audit", "aeo", "answer engine", "llms.txt", "rank better". Debt — `SHORTCUT:` ledger. Triggers "debt ledger", "shortcut ledger". Owns bare "audit the codebase"; single-page CWV fix loops go to /lighthouse.

42
Stars
60/100
信頼
カテゴリ: security監査

Rewrite existing text under the EW anti-AI rules and the writer's voice profile, then show a structured before/after with specific failure analysis. Use when the user pastes a draft and asks to fix, tighten, de-slop, humanize, critique, or improve it.

28
Stars
64/100
信頼
カテゴリ: security監査

Searches code specifically for potential bugs, edge cases, race conditions, and incorrect assumptions rather than general style/quality. Use when the goal is finding what's broken, not improving what already works.

21
Stars
65/100
信頼
カテゴリ: research監査

Audit or edit Sero Markdown documentation and other product prose to remove AI-writing patterns while preserving technical meaning, product terminology, links, examples, and the repository voice. Use when the user asks to humanize, de-slop, tighten, simplify, rewrite, or audit Sero documentation, README text, UI copy, release notes, plans, or specifications for AI tells. Also use when prose needs ASD-STE100 Simplified Technical English. Do not use for code review or for creative and promotional writing.

19
Stars
61/100
信頼
カテゴリ: security監査

Review a PR, a branch, or a diff in the Sero monorepo and post the findings. Use when the user asks to review code, review a PR, re-review after new commits, check a branch before merge, or double-check an earlier review. Trigger on phrases like "review this PR", "review the delta", "check the changes", "double check it", or any request that ends in review findings. Use this in place of the built-in code-review skill.

19
Stars
61/100
信頼
カテゴリ: design-creative監査

Review changes on current branch and output a structured review. Optionally post to PR with --pr flag, or apply non-blocking follow-ups inline with --apply-followups.

11
Stars
61/100
信頼
カテゴリ: coding-agents監査