Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
skill-developer
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.
majiayu000/claude-skill-registry 163
-
create-roadmap
Create a Now/Next/Later outcome-oriented roadmap when the user asks to plan a roadmap, prioritize features, or define product direction
majiayu000/claude-skill-registry 163
-
abaqus-job
Create and manage Abaqus jobs. Use when user asks to run the analysis, submit the job, execute the model, or generate input file.
majiayu000/claude-skill-registry 163
-
pptx
QUERY LENGTH LIMIT EXCEEDED. MAX ALLOWED QUERY : 500 CHARS
majiayu000/claude-skill-registry 163
-
git-commit
Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.
majiayu000/claude-skill-registry 163
-
obviously-awesome
Define product positioning by mapping competitive alternatives, unique attributes, and best-fit customers to the right market category. Use when the user mentions "positioning", "competitive alternatives", "how to position", "market category", "why customers dont get it", "positioning canvas", "repositioning", or "category creation". Also trigger when launching a new product, entering a crowded market, or diagnosing why prospects dont understand the products value. Covers positioning canvas and team workshops. For customer jobs analysis, see jobs-to-be-done. For go-to-market, see crossing-the-chasm.
majiayu000/claude-skill-registry 163
-
kernel-services
Advanced Zephyr RTOS kernel services. Covers inter-thread communication using Zbus (pub/sub), behavioral management with the State Machine Framework (SMF), background processing via work queues, and persistent configuration with the Settings subsystem. Trigger when building modular application architectures, complex state-driven logic, or requiring persistent data storage.
majiayu000/claude-skill-registry 163
-
mocking-strategies
Mocks vs stubs vs spies, dependency injection for testing, jest.mock/unittest.mock/gomock, and when NOT to mock. Use when the user needs to isolate dependencies in tests, asks about mocking external services, or has tests tightly coupled to implementation details.
majiayu000/claude-skill-registry 163
-
capacity
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements.
USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability.
DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
majiayu000/claude-skill-registry 163
-
skill-rails-upgrade
Analyze Rails apps and provide upgrade assessments
majiayu000/claude-skill-registry 163
-
esm
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships.
For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.
majiayu000/claude-skill-registry 163
-
Observability Patterns
Debugging and monitoring patterns for the distributed offline-first architecture
majiayu000/claude-skill-registry 163
-
chro-advisor
People leadership for scaling companies. Hiring strategy, compensation design, org structure, culture, and retention. Use when building hiring plans, designing comp frameworks, restructuring teams, managing performance, building culture, or when user mentions CHRO, HR, people strategy, talent, headcount, compensation, org design, retention, or performance management.
majiayu000/claude-skill-registry 163
-
automating-contacts
Automates macOS Contacts via JXA with AppleScript dictionary discovery. Use when asked to "automate contacts", "JXA contacts automation", "macOS address book scripting", "AppleScript contacts", or "Contacts app automation". Covers querying, CRUD, multi-value fields, groups, images, and ObjC bridge fallbacks.
majiayu000/claude-skill-registry 163
-
don-apis
Dutch Government API design rules, OpenAPI specifications, and API architecture guidelines. Use when building REST APIs for Dutch government projects, creating OpenAPI specs, or implementing API design patterns like webhooks and event-driven architecture.
majiayu000/claude-skill-registry 163
-
webinars
Use when planning, producing, and repurposing webinars or virtual events for GTM campaigns.
majiayu000/claude-skill-registry 163
-
spring-boot-testing
Expert Spring Boot 4 testing specialist that selects the best Spring Boot testing techniques for your situation with Junit 6 and AssertJ.
majiayu000/claude-skill-registry 163
-
csharp-tunit
Get best practices for TUnit unit testing, including data-driven tests
majiayu000/claude-skill-registry 163
-
bmad-wds-wireframes
Generate outline wireframes from page specifications
majiayu000/claude-skill-registry 163
-
summon
Autonomous orchestrator processing manifest work items through the development lifecycle with budget tracking.
majiayu000/claude-skill-registry 163
-
openai-agents-sdk
Expert guidance for building multi-agent AI applications using the OpenAI Agents SDK for Python. Use when (1) creating agents with handoffs, tools, guardrails, or sessions, (2) implementing structured outputs with Pydantic models, (3) building agentic workflows, (4) debugging and tracing agent execution, (5) working with provider-agnostic LLM applications (OpenAI, Anthropic, LiteLLM), or (6) implementing customer support, legal research, financial analysis, or autonomous task completion systems.
majiayu000/claude-skill-registry 163
-
Getting Started with Skills
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
majiayu000/claude-skill-registry 163
-
lead-scoring
Use this skill when defining ideal customer profiles, building scoring models, identifying intent signals, or qualifying leads. Triggers on lead scoring, ICP definition, scoring models, intent signals, MQL, SQL, lead qualification, BANT, and any task requiring lead prioritization or qualification framework design.
majiayu000/claude-skill-registry 163
-
peasy
USE FOR: Implementing business rules as composable, testable rule objects using the Peasy framework. Use when building middle-tier validation pipelines for commands and services that require rule chaining, async validation, and conditional execution.
DO NOT USE FOR: Simple argument null checks (use CommunityToolkit Guard), form-level input validation (use FluentValidation or DataAnnotations), or full CQRS/event-sourcing frameworks (use MediatR or Wolverine).
majiayu000/claude-skill-registry 163