Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
lightfriend-db-migration
Step-by-step guide for modifying database schema using Diesel migrations
majiayu000/claude-skill-registry 163
-
meeting-minutes-generator
Generate structured construction meeting minutes. Track action items, decisions, and attendees.
majiayu000/claude-skill-registry 163
-
communicate-with-cs
Communication coaching for working with a Cs (The Editor) DISC type — precise, reserved, thorough. Covers do's, don'ts, meetings, email, feedback, and conflict. Powered by Crystal's DISC framework.
majiayu000/claude-skill-registry 163
-
ssdt-cicd-best-practices-2025
Modern CI/CD best practices for SQL Server database development with tSQLt, state-based deployment, and 2025 patterns
majiayu000/claude-skill-registry 163
-
use-wallet
Integrate Algorand/AVM wallet connections using @txnlab/use-wallet v4.x. Use when building dApps that need wallet connectivity (Pera, Defly, Lute, Kibisis, Exodus, WalletConnect, etc.), transaction signing, data signing (ARC-60/SIWA), network switching, or wallet state management in vanilla JS/TS, React, Vue, SolidJS, or Svelte applications. Also covers the companion UI component library @txnlab/use-wallet-ui-react for drop-in wallet buttons and menus.
majiayu000/claude-skill-registry 163
-
implementation
Writes new features, refactors code, implements functionality following best practices
majiayu000/claude-skill-registry 163
-
debugging
Four-phase debugging framework that ensures root cause identification before fixes. Use when encountering bugs, test failures, unexpected behavior, or when previous fix attempts failed. Enforces investigate-first discipline ('debug this', 'fix this error', 'test is failing', 'not working').
majiayu000/claude-skill-registry 163
-
skills-frankxai-arcanea-records-5
majiayu000/claude-skill-registry 163
-
youtube-script-writer
Write YouTube video scripts using search-first, stakes-based methodology. Use when the user needs to write a video script, create hooks/intros, or structure video content. Optimizes for both search ranking (keyword-targeted titles) and retention (escalating stakes, mid-video climax, show-don't-explain).
majiayu000/claude-skill-registry 163
-
aget-make-decision
Make decisions with documented rationale
majiayu000/claude-skill-registry 163
-
warren-buffett
Agente que simula Warren Buffett — o maior investidor do seculo XX e XXI, CEO da Berkshire Hathaway, discipulo de Benjamin Graham e socio intelectual de Charlie Munger.
majiayu000/claude-skill-registry 163
-
release
Create a new release of unityctl. Analyzes changes since last tag, determines version bump type (major/minor/patch), updates version, builds, commits, tags, and creates a draft GitHub release with changelog.
majiayu000/claude-skill-registry 163
-
vercel-env-sync
Sync environment variables from local .env to a Vercel project and trigger redeploy. Use this skill whenever the user wants to update Vercel env vars, fix a missing API key on production, sync .env to Vercel, redeploy after env changes, or says something like "update Vercel env", "add key to Vercel", "env not working on prod", "redeploy Vercel".
majiayu000/claude-skill-registry 163
-
patents-search
Search global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.
majiayu000/claude-skill-registry 163
-
Debug Adapter Protocol
Expert skill for implementing Debug Adapter Protocol for debugger integration
majiayu000/claude-skill-registry 163
-
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
majiayu000/claude-skill-registry 163
-
magento-events-cron
Implement Magento 2 events, observers, cron jobs, and message queues. Use when building event-driven logic, scheduled tasks, or asynchronous processing.
majiayu000/claude-skill-registry 163
-
prd-ml
Generate a Product Requirements Document (PRD) for a data science, machine learning, or MLOps feature/project. Use when planning an ML experiment, model deployment, data pipeline, or MLOps process. Triggers on: create a prd for ml, write prd for model, plan this ml feature, spec out pipeline, mlops prd.
majiayu000/claude-skill-registry 163
-
handoff-gemini
Delegate tasks to Gemini CLI to save Claude context
majiayu000/claude-skill-registry 163
-
cube
Expert guidance for Cube, the headless BI and semantic layer that sits between your data warehouse and analytics applications. Helps developers define data models, create metrics APIs, and build analytics features in applications with consistent, governed access to business metrics.
majiayu000/claude-skill-registry 163
-
maui-safe-area
.NET MAUI safe area and edge-to-edge layout guidance for .NET 10+. Covers SafeAreaEdges property, SafeAreaRegions enum, per-edge control, keyboard avoidance, Blazor Hybrid CSS safe areas, migration from legacy APIs, and platform-specific behavior for Android, iOS, and Mac Catalyst. USE FOR: "safe area", "edge-to-edge", "SafeAreaEdges", "SafeAreaRegions", "keyboard avoidance", "notch insets", "status bar overlap", "iOS safe area", "Android edge-to-edge", "content behind status bar". DO NOT USE FOR: general layout or grid design (use maui-collectionview), app lifecycle handling (use maui-app-lifecycle), or theming (use maui-theming).
majiayu000/claude-skill-registry 163
-
code-review
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
majiayu000/claude-skill-registry 163
-
qcsd-refinement-swarm
QCSD Refinement phase swarm for Sprint Refinement sessions using SFDIPOT product factors, BDD scenario generation, and requirements validation.
majiayu000/claude-skill-registry 163
-
pathml
Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection/segmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows.
majiayu000/claude-skill-registry 163