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: confuse

英語版ディレクトリ

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

25K
Stars
77/100
信頼
カテゴリ: engineering / code quality監査

An AI agent skill that generates KiCad footprints from datasheets, packaged as a SKILL.md for use in agent runtimes like Claude Code.

28
Stars
70/100
信頼
カテゴリ: utility監査

Use when the user wants to write a blog post about a feature, product change, PR, git diff, or any technical topic - accepts marketing briefs, PRs, git refs, codebase paths, or freeform descriptions as input

39
Stars
60/100
信頼
カテゴリ: coding-agents監査

Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.

33
Stars
64/100
信頼
カテゴリ: coding-agents監査

Review documentation for accuracy, completeness, and missing information that users may need

11
Stars
58/100
信頼
カテゴリ: automation監査

Cadre RenooLab spécialisé pour diagnostiquer puis développer une entreprise artisanale, un négoce ou un fournisseur BTP : positionnement, prestations, planning vide, acquisition, prospects, visibilité, contenu, vente, devis non signé, fidélisation, services, KPI, CRM et demandes dispersées entre WhatsApp, papier et e-mail. Toujours charger pour croissance, clientèle, différenciation, communication ou outils. Un fournisseur voulant rejoindre RenooLab relève de ce workflow, jamais du profil artisan. Marge, facture émise et impayé relèvent de la rentabilité.

3
Stars
65/100
信頼
カテゴリ: research監査