Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
session-control
/work のセッション resume/fork(branch) を --resume/--fork フラグに基づいて制御。session.json と session.events.jsonl を更新する内部ワークフロー専用スキル。Do NOT load for: user session management, login state, app state handling.
Chachamaru127/claude-code-harness 361
-
cc-update-review
CC アプデ統合の品質ガードレール。Feature Table 追加時に「書いただけ」を検出し、実装案を強制出力。Use when reviewing CC update integration PRs. Do NOT load for: implementation work, standard reviews, setup.
Chachamaru127/claude-code-harness 361
-
cc-cursor-cc
Cursor PM でアイデアを検証し Plans.md を更新してバトンタッチ。Cursor ↔ Claude Code 2-Agent ワークフロー対応。Use when user mentions Cursor PM handoff, 2-agent plan validation, CC-Cursor round trip, or brainstorm review. Do NOT load for: implementation work, single-agent tasks, or direct coding.
Chachamaru127/claude-code-harness 361
-
harness-sync
Plans.md と実装の進捗同期。差分検出・マーカー更新・レトロスペクティブを実行。以下で起動: harness-sync、sync-status、進捗確認、今どこ、どこまで終わった。--snapshot で進捗スナップショット保存にも対応。プランニング・実装・レビュー・リリースには使わない。
Chachamaru127/claude-code-harness 361
-
generate-slide
Nano Banana Proでプロジェクト紹介スライドを自動生成。スライド、1枚紹介、ビジュアル紹介で起動。動画生成やデッキ作成では起動しない。
Chachamaru127/claude-code-harness 361
-
harness-work
Harness v3 統合実行スキル。Plans.md タスクを1件から全並列チーム実行まで担当。以下で起動: 実装して、実行して、harness-work、全部やって、breezing、チーム実行、parallel。プランニング・レビュー・リリース・セットアップには使わない。
Chachamaru127/claude-code-harness 361
-
notebookLM
NotebookLM用YAMLやスライドを生成。ドキュメント職人の腕の見せ所。Use when user mentions NotebookLM, YAML, slides, or presentations. Do NOT load for: implementation work, code fixes, reviews, or deployments.
Chachamaru127/claude-code-harness 361
-
harness-release
Harness v3 統合リリーススキル。CHANGELOG・バージョンバンプ・タグ・GitHub Release を自動化。以下で起動: リリース、バージョンバンプ、タグ作成、公開、/harness-release。実装・コードレビュー・プランニング・セットアップには使わない。
Chachamaru127/claude-code-harness 361
-
harness-review
Harness v3 統合レビュースキル。コード・プラン・スコープを多角的にレビュー。以下で起動: レビュー、コードレビュー、プランレビュー、スコープ分析、セキュリティ、品質チェック、harness-review。実装・新機能・バグ修正・セットアップ・リリースには使わない。
Chachamaru127/claude-code-harness 361
-
session-state
SESSION_ORCHESTRATION.md に基づくセッション状態遷移管理。/work フェーズ境界での状態更新、エラー時の escalated 遷移、セッション再開時の initialized 復帰を制御。Internal workflow use only. Do NOT load for: user session management, login state, app state handling.
Chachamaru127/claude-code-harness 361
-
principles
開発原則、ガイドライン、VibeCoder向けガイダンスを提供。Use when user mentions principles, guidelines, safety, or diff-aware editing. Do not use for actual implementation—use the impl skill instead.
Chachamaru127/claude-code-harness 361
-
agent-browser
ブラウザを手足のように操る。ページ遷移、フォーム入力、スクショ、なんでもこい。Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include 'go to [url]', 'click on', 'fill out the form', 'take a screenshot', 'scrape', 'automate', 'test the website', 'log into', or any browser interaction request. Do NOT load for: sharing URLs, embedding links, screenshot image files.
Chachamaru127/claude-code-harness 361
-
integration-testing
Design and implement integration tests that verify component interactions, API endpoints, database operations, and external service communication. Use for integration test, API test, end-to-end component testing, and service layer validation.
aj-geddes/useful-ai-prompts 151
-
Anomaly Detection
Identify unusual patterns, outliers, and anomalies in data using statistical methods, isolation forests, and autoencoders for fraud detection and quality monitoring
aj-geddes/useful-ai-prompts 151
-
wireframe-prototyping
Create wireframes and interactive prototypes to visualize user interfaces and gather feedback early. Use tools and techniques to communicate design ideas before development.
aj-geddes/useful-ai-prompts 151
-
Natural Language Processing
Build NLP applications using transformers library, BERT, GPT, text classification, named entity recognition, and sentiment analysis
aj-geddes/useful-ai-prompts 151
-
configuration-management
Manage application configuration including environment variables, settings management, configuration hierarchies, secret management, feature flags, and 12-factor app principles. Use for config, environment setup, or settings management.
aj-geddes/useful-ai-prompts 151
-
memory-optimization
Profile and optimize application memory usage. Identify memory leaks, reduce memory footprint, and improve efficiency for better performance and reliability.
aj-geddes/useful-ai-prompts 151
-
documentation-site-setup
Set up documentation websites using Docusaurus, MkDocs, VitePress, GitBook, or static site generators. Use when creating docs sites, setting up documentation portals, or building static documentation.
aj-geddes/useful-ai-prompts 151
-
static-code-analysis
Implement static code analysis with linters, formatters, and security scanners to catch bugs early. Use when enforcing code standards, detecting security vulnerabilities, or automating code review.
aj-geddes/useful-ai-prompts 151
-
code-metrics-analysis
Analyze code complexity, cyclomatic complexity, maintainability index, and code churn using metrics tools. Use when assessing code quality, identifying refactoring candidates, or monitoring technical debt.
aj-geddes/useful-ai-prompts 151
-
design-system-creation
Build comprehensive design systems with components, patterns, and guidelines. Enable consistent design, faster development, and better collaboration across teams.
aj-geddes/useful-ai-prompts 151
-
Dimensionality Reduction
Reduce feature dimensionality using PCA, t-SNE, and feature selection for feature reduction, visualization, and computational efficiency
aj-geddes/useful-ai-prompts 151
-
design-patterns-implementation
Apply appropriate design patterns (Singleton, Factory, Observer, Strategy, etc.) to solve architectural problems. Use when refactoring code architecture, implementing extensible systems, or following SOLID principles.
aj-geddes/useful-ai-prompts 151