Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
copilotkit-pitch-deck
Production-ready CopilotKit pitch deck wizard in main application. Use when enhancing AI conversation features, optimizing Edge Function integration, debugging chat interface, or improving pitch deck generation flow. System is PRODUCTION READY (98/100).
majiayu000/claude-skill-registry 163
-
bdd-practices
Writes behavior specifications in Gherkin format. Use when defining features from user perspective or creating acceptance tests.
majiayu000/claude-skill-registry 163
-
better-auth-v2
Production-ready authentication system using Better Auth v2 with latest features. Includes OAuth providers, advanced RBAC, multi-tenant support, and security best practices.
majiayu000/claude-skill-registry 163
-
gemini-batch
This skill should be used when the user asks to "use Gemini Batch API", "process documents at scale", "submit a batch job", "upload files to Gemini", or needs large-scale LLM processing. Includes production gotchas and best practices.
majiayu000/claude-skill-registry 163
-
research-trigger
Natural language wrapper for research command - automatically triggers /research when users ask questions requiring deep research, best practices lookup, or multi-source information gathering
majiayu000/claude-skill-registry 163
-
nav-marker
Create context save points to preserve conversation state before breaks, risky changes, or compaction. Use when user says "save my progress", "create checkpoint", "mark this point", or before clearing context.
majiayu000/claude-skill-registry 163
-
overview
Overview of Claude Code capabilities, features, and use cases. Use when user asks about what Claude Code is, what it can do, or general capabilities.
majiayu000/claude-skill-registry 163
-
specswarm-ship
Systematic quality validation, test verification, and safe merging workflow for deployment/release operations. ALWAYS asks for confirmation when user wants to ship, deploy, merge, release, or complete features to production, merge to main branch, or finalize features. This is a DESTRUCTIVE operation (merges and deletes branches).
majiayu000/claude-skill-registry 163
-
tg-ingest
Primary Telegram interface. Full-featured CLI for message export, DM management, group sync, contact scoring, and thread state. Use when user mentions "telegram", "tg", "@username", or telegram-specific terms. Triggers: "telegram messages", "export telegram", "telegram DMs", "telegram groups", "sync telegram", "@username messages", "telegram contacts". This is STANDALONE - do not defer to unified-messages for telegram operations.
majiayu000/claude-skill-registry 163
-
enter-world
Launch the Adventure Engine application for an adventure project. Use when the user wants to "enter" a world, "start" or "launch" an adventure session, or begin interactive gameplay. Fires off the application in the background using the current working directory as the adventure project root.
majiayu000/claude-skill-registry 163
-
roadmap-frameworks
Master product roadmaps including roadmap types (timeline, outcome-based, Now-Next-Later), communication strategies, and prioritization. Use when creating roadmaps, communicating strategy, prioritizing initiatives, or evolving product direction. Covers roadmap formats, communication tactics, and roadmap best practices from product leaders.
majiayu000/claude-skill-registry 163
-
astro-images-joshribakoff-fightingwithai-com
majiayu000/claude-skill-registry 163
-
virtualization
GPU passthrough and virtualization for Bazzite. KVM/VFIO setup, Looking Glass (kvmfr),
USB hotplug for VMs, and libvirt configuration. Use when users need GPU passthrough
or advanced virtualization features.
majiayu000/claude-skill-registry 163
-
julien-mcp-basic-memory
Install Basic Memory MCP for persistent memory between Claude sessions. Use when user needs memory/context persistence via uvx.
majiayu000/claude-skill-registry 163
-
greet-skill
This skill should be used when the user says "hello", "hi", or "greet me".
majiayu000/claude-skill-registry 163
-
research-patterns
Research methodology and best practices for finding existing patterns
majiayu000/claude-skill-registry 163
-
qualitative-research
Use when conducting customer discovery interviews, user research, surveys, focus groups, or observational research requiring rigorous analysis - provides systematic 6-phase framework with mandatory bias prevention (reflexivity, intercoder reliability, disconfirming evidence search) and reproducible methodology; peer to hypothesis-testing for qualitative vs quantitative validation
majiayu000/claude-skill-registry 163
-
prd-creator
This skill should be used when creating, validating, or converting Product Requirements Documents (PRDs) to LLM-native format. Use this skill when the user asks to write a PRD, review a PRD for compliance, convert an existing PRD to machine-readable format, or ensure PRD quality for AI agent consumption. This skill is optimized for users working with agentic coding frameworks who need strict requirement specifications to prevent context poisoning, hallucination, and mesa-optimization.
majiayu000/claude-skill-registry 163
-
mechinterp-investigator
Orchestrate a systematic research program to investigate and meaningfully label SAE features
majiayu000/claude-skill-registry 163
-
empathy-mapping
Create structured visualizations of stakeholder perspectives (says, thinks, does, feels) to build deep understanding. Use when conducting user research or validating assumptions.
majiayu000/claude-skill-registry 163
-
violetconnect
VioletConnect core features - merchant onboarding application architecture
majiayu000/claude-skill-registry 163
-
laravel-exceptions
Custom exceptions with static factories and HTTP responses. Use when working with error handling, custom exceptions, or when user mentions exceptions, custom exception, error handling, HTTP exceptions.
majiayu000/claude-skill-registry 163
-
prioritization-effort-impact
Use when ranking backlogs, deciding what to do first based on effort vs impact (quick wins vs big bets), prioritizing feature roadmaps, triaging bugs or technical debt, allocating resources across initiatives, identifying low-hanging fruit, evaluating strategic options with 2x2 matrix, or when user mentions prioritization, quick wins, effort-impact matrix, high-impact low-effort, big bets, or asks "what should we do first?".
majiayu000/claude-skill-registry 163
-
external-docs
Verify external libraries, APIs, and frameworks against current documentation before writing code. Use when about to implement features using external dependencies, when writing import statements for third-party libraries, when unsure if a pattern or method is current, or when the user mentions grounding or verification.
majiayu000/claude-skill-registry 163