Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
remember
This skill should be used when the user says "remember", "note this", "add to CLAUDE.md", "don't forget", "keep in mind", or asks to store a preference, convention, or project-specific instruction. Stores memories in the project's CLAUDE.md file.
majiayu000/claude-skill-registry 163
-
parzival-save-insight
Save a Parzival insight or learning to Qdrant for cross-session memory
majiayu000/claude-skill-registry 163
-
Quit Alcohol
Track sobriety with alcohol-free streaks, craving management, and recovery milestones.
majiayu000/claude-skill-registry 163
-
mcp-tools
Expert guidance for the Model Context Protocol (MCP) - connect AI agents to external tools, services, and data sources. Use when working with: (1) Building MCP servers to expose tools, resources, and prompts, (2) Integrating MCP clients with AI applications, (3) Protocol transports (stdio, HTTP SSE), (4) Tool execution and resource management, (5) JSON-RPC message handling, (6) Server-client architecture, (7) Production deployments. Supports Python SDK with async patterns.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
personality
Manage voice assistant personalities. List, create, switch, edit, delete, export, or import personalities.
majiayu000/claude-skill-registry 163
-
content-hash-cache-pattern
Use when caching expensive file processing results. SHA-256 content-hash keying with frozen CacheEntry and service layer wrapper.
majiayu000/claude-skill-registry 163
-
refactor-plan
Plan a multi-file refactor with proper sequencing and rollback steps
majiayu000/claude-skill-registry 163
-
project-review
Complete project health check: verify tests, documentation, database snapshots, migration progress, and suggest next steps. Run after completing any task or iteration.
majiayu000/claude-skill-registry 163
-
bmad-pm
pm agent
majiayu000/claude-skill-registry 163
-
architecture-patterns
Provides architectural pattern knowledge for designing feature implementations including MVC, event-driven, microservices, and CQRS patterns. Use when designing system architecture or choosing implementation patterns.
majiayu000/claude-skill-registry 163
-
thirdweb
Thirdweb v5 SDK usage in AutoClaw. Use when working with wallet connection, social login, SIWE authentication, or thirdweb client/provider setup. Triggers on: "thirdweb", "wallet connect", "inAppWallet", "social login", "SIWE", "ConnectButton", "thirdweb auth", "thirdweb provider".
majiayu000/claude-skill-registry 163
-
harness-review
コード・プラン・スコープを多角的にレビュー。品質の番人、参上。Use when user mentions reviews, code review, plan review, scope analysis, security, performance, quality checks, PRs, diffs, or change review. Do NOT load for: implementation work, new feature development, bug fixes, or setup.
majiayu000/claude-skill-registry 163
-
33god-workflow-generator
Generate complete workflow implementations from semantic descriptions for the 33GOD ecosystem. Use when (1) implementing new event-driven workflows, (2) creating services that span filesystem → API → Bloodbank → processing, (3) adding orchestration flows that combine Node-RED + Python services, (4) registering new services in the 33GOD registry, or (5) when the user provides a workflow description like "watch directory, process files, publish events."
majiayu000/claude-skill-registry 163
-
campaign-analysis
This skill should be used when the user asks to "analyze campaign performance", "check campaigns", "investigate CPL/CVR", "review ad performance", "generate client report", "check ads", "run monthly review", mentions client names (last-minute, nota, Homescape, DMP), or needs campaign optimization insights across Google Ads, Meta, GA4, and Search Console. Also triggers when asked to "write knowledge", "update knowledge", "what do we know about [client]", "check landing page quality", or "check organic search".
majiayu000/claude-skill-registry 163
-
app-intents
Implement App Intents for Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence on iOS. Covers AppIntent actions, AppEntity and EntityQuery models, AppShortcutsProvider phrases, IndexedEntity Spotlight indexing, WidgetConfigurationIntent, SnippetIntent, and assistant schemas. Use when exposing app actions or entities to system surfaces.
majiayu000/claude-skill-registry 163
-
peer-review
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revision. For evaluating claims/evidence quality use scientific-critical-thinking; for quantitative scoring frameworks use scholar-evaluation.
majiayu000/claude-skill-registry 163
-
memory-systems
Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.
majiayu000/claude-skill-registry 163
-
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
majiayu000/claude-skill-registry 163
-
lit
Web Components development with Lit including custom elements, reactive properties, shadow DOM, and interoperability.
majiayu000/claude-skill-registry 163
-
toolfs-memory
Persistent key-value storage for session data, conversation context, and agent state. Use this skill when the user requests storing or retrieving memory entries such as "Store this in memory", "Remember this preference", "Recall the previous conversation", or "List all memory entries".
majiayu000/claude-skill-registry 163
-
product-marketing-context
When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Creates `.claude/product-marketing-context.md` that other marketing skills reference.
majiayu000/claude-skill-registry 163
-
project-report
Generate project status reports (single or all projects)
majiayu000/claude-skill-registry 163
-
azure-payment-hsm
Expert knowledge for Azure Payment Hsm development including troubleshooting, best practices, decision making, architecture & design patterns, security, and configuration. Use when designing Payment HSM VNets/FastPath, payShield Manager access, HA/DR topologies, SKUs, or traffic inspection, and other Azure Payment Hsm related development tasks. Not for Azure Dedicated HSM (use azure-dedicated-hsm), Azure Key Vault (use azure-key-vault), Azure Cloud Hsm (use azure-cloud-hsm), Azure Security (use azure-security).
majiayu000/claude-skill-registry 163