Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
mobile-forensics
Analyze mobile device data for forensic investigation. Use when investigating
incidents involving iOS or Android devices, mobile malware, data theft, or
communications analysis. Supports logical and file system extractions.
majiayu000/claude-skill-registry 163
-
nfr-assess
Assess non-functional requirements across 6 quality categories (Security, Performance, Reliability, Maintainability, Scalability, Usability) with measurable criteria, evidence-based evaluation, and automated checks. Scores each category, identifies gaps with severity ratings, and provides remediation guidance. Use during quality review to evaluate production readiness and NFR compliance.
majiayu000/claude-skill-registry 163
-
drive-share
Google Drive のファイルを共有する。「ファイルを共有」「共有設定」「共有して」「リンク共有」「アクセス権を追加」「閲覧権限を付与」などで起動。`/shiiman-google:drive-share` を実行して共有設定を変更する。
majiayu000/claude-skill-registry 163
-
test_gui
GUIアプリケーションの動作試験・デバッグを自動で行う
majiayu000/claude-skill-registry 163
-
ultrathink-orchestrator
Auto-invokes ultrathink workflow for any work request (default orchestrator)
majiayu000/claude-skill-registry 163
-
Technical Debt Patterns
Expert guide to detecting, categorizing, and prioritizing technical debt in Rails applications. Use when: (1) Auditing codebase health, (2) Planning refactoring sprints, (3) Estimating feature impact, (4) Identifying code smells, (5) Tracking deprecations. Trigger keywords: technical debt, code smell, complexity, cyclomatic, deprecation, legacy, refactor, audit, health check, god class
majiayu000/claude-skill-registry 163
-
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform
majiayu000/claude-skill-registry 163
-
ai-response-refiner
AI応答を洗練・改善するスキル。粗い出力を流暢で専門的な文章に変換。構造化、明確化、詳細化、トーン調整、専門性向上、読みやすさ改善を実施。
majiayu000/claude-skill-registry 163
-
linkedin
Create LinkedIn posts for lead generation and thought leadership. Use when projecting ideas to LinkedIn, creating post series, or reviewing LinkedIn content. Includes LinkedIn-specific voice (punchier, more personal), format rules, and weekly rhythm guidance.
majiayu000/claude-skill-registry 163
-
vendor-plan
ベンダー管理計画書を作成する。調達計画、外注管理計画の策定時に使う。
majiayu000/claude-skill-registry 163
-
Model Risk Management
Identifying, assessing, and mitigating risks associated with the use of machine learning models in business processes.
majiayu000/claude-skill-registry 163
-
Vector Database Patterns
Comprehensive guide to vector databases including Pinecone, Qdrant, Weaviate, embedding strategies, and similarity search.
majiayu000/claude-skill-registry 163
-
ralph-calibrate
Run Ralph calibration checks to analyze intention drift, technical quality, and self-improvement opportunities. Use when user asks to "ralph calibrate", "check drift", "analyze sessions", or needs to verify work alignment.
majiayu000/claude-skill-registry 163
-
git-pushing
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", or similar git workflow requests.
majiayu000/claude-skill-registry 163
-
solana-kit-migration
Helps developers understand when to use @solana/kit vs @solana/web3.js (v1), provides migration guidance, API mappings, and handles edge cases for Solana JavaScript SDK transitions
majiayu000/claude-skill-registry 163
-
cloudflare-turnstile-secondsky-claude-skills-2
majiayu000/claude-skill-registry 163
-
log-skill
记录执行过程的 Skill。当需要保存执行记录、工作日志时触发。触发词：记录、log、日志、work log、保存记录。
majiayu000/claude-skill-registry 163
-
clarify-spec
AKTIVIERT SICH AUTOMATISCH bei vagen Auftraegen. LIEBER EINMAL ZU OFT NACHFRAGEN als falsch implementieren.
Erkennungsmerkmale (EINES genuegt!):
- Auftrag <25 Woerter
- Keine konkreten Dateinamen/Pfade
- Vage Verben: besser, optimieren, fixen, machen, aendern, verbessern, anpassen, erweitern, refactoren, aufraumen, ueberarbeiten
- Unsichere Sprache: irgendwie, vielleicht, mal eben, schnell, einfach, bisschen, koennte, sollte
- Fehlende Erfolgskriterien: Kein damit, sodass, weil, um zu
- Relative Begriffe ohne Kontext: schneller, besser, schoener, einfacher
Output ist STRUKTURIERTES JSON fuer prompt-architect Skill.
Escape: mach einfach, keine Rueckfragen, entscheide selbst ueberspringt Klaerung.
majiayu000/claude-skill-registry 163
-
ai-ml-data-science
End-to-end data science patterns (modern best practices): problem framing -> data -> EDA -> feature engineering (with feature stores) -> modelling -> evaluation -> reporting, plus SQL transformation (SQLMesh). Emphasizes MLOps integration, drift monitoring, and production-ready workflows.
majiayu000/claude-skill-registry 163
-
apply-all-findings
Use after code review - implement ALL findings; any finding not fixed MUST have tracking issue created; no finding disappears without trace
majiayu000/claude-skill-registry 163
-
ln-150-presentation-creator
Builds interactive HTML presentation with 6 tabs (Overview, Requirements, Architecture/C4, Tech Spec, Roadmap, Guides). Creates presentation/README.md hub. L2 Worker under ln-100-documents-pipeline.
majiayu000/claude-skill-registry 163
-
replay-blackbox-sensei-hacker-inav-claude
Replay blackbox sensor data to flight controller (SITL or HITL)
majiayu000/claude-skill-registry 163
-
agent-typescript-pro
Expert TypeScript developer specializing in advanced type system usage, full-stack development, and build optimization. Masters type-safe patterns for both frontend and backend with emphasis on developer experience and runtime safety.
majiayu000/claude-skill-registry 163
-
refactor
[UDS] Guide refactoring decisions and strategy selection
majiayu000/claude-skill-registry 163