Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
generating-faqs-and-help-content
Builds comprehensive FAQs and help center articles from customer questions and product documentation. Use when the user asks about FAQ pages, help centers, knowledge bases, support documentation, or customer questions.
majiayu000/claude-skill-registry 163
-
tiktok-targeted-analysis
Analyzes user-provided TikTok URLs to generate comprehensive video breakdowns, 1 replication script (100% structure copy), and AI video generation prompts for Veo 3.1/Sora in copy-paste ready markdown code blocks
majiayu000/claude-skill-registry 163
-
ethereal-persona
Design and implement the personality, conversational style, and emotional behavior of the Ethereal "Digital Spirit". Use this skill when updating system prompts, mood logic, or implementing new interactive behaviors. Ensures the spirit remains witty, concise, and mysteriously connected to the system's pulse.
majiayu000/claude-skill-registry 163
-
general-research
Conducts systematic internet research through strategic questioning and multi-source analysis. Gathers information from web sources (not codebase), cross-references claims across multiple sources, evaluates source credibility using tier system (official docs, expert blogs, community resources), identifies patterns and consensus, and produces structured reports in .research/. Use when user needs to gather knowledge from internet, find best practices, compare solutions, evaluate technologies, understand industry trends, or investigate topics thoroughly. Triggers include "research online", "gather information about", "find best practices for", "compare solutions", "evaluate", "investigate topic", "what do sources say", "look up", "search for information".
majiayu000/claude-skill-registry 163
-
pytorch-fsdp2
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
majiayu000/claude-skill-registry 163
-
memorylane-awolf81-memory-lane-70be8503
majiayu000/claude-skill-registry 163
-
bash-defensive-patterns
Master defensive Bash programming techniques for production-grade scripts. Use when writing robust shell scripts, CI/CD pipelines, or system utilities requiring fault tolerance and safety.
majiayu000/claude-skill-registry 163
-
diagramming
Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual documentation.
majiayu000/claude-skill-registry 163
-
rust-cache
Redis 缓存管理、连接池、TTL策略、模式匹配删除、性能优化
majiayu000/claude-skill-registry 163
-
ultraqa
QA cycling workflow - test, verify, fix, repeat until goal met
majiayu000/claude-skill-registry 163
-
debugging-checklist
Provide a systematic debugging checklist. Use when a junior developer is stuck and needs a structured approach.
majiayu000/claude-skill-registry 163
-
Audit UI/UX Consistency
COMPREHENSIVE UI/UX audit combining code analysis AND visual screenshot analysis. Detects design system violations, visual inconsistencies across views, button/card/modal style variants, color palette chaos, theme breaks, and accessibility issues. Provides detailed visual evidence and prioritized fixes. INCLUDES Storybook design decision workflow for user-driven choices. CRITICAL - Must analyze actual rendered screenshots, not just code.
majiayu000/claude-skill-registry 163
-
agent-evaluation
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
majiayu000/claude-skill-registry 163
-
positional-revelation
Generate stories where ordinary people become crucial through their structural position in systems. Use when you want protagonists who aren't chosen ones but accidental pivots, when mundane jobs should reveal conspiracies, or when you need structurally inevitable involvement rather than coincidence.
majiayu000/claude-skill-registry 163
-
quick
Streamlined code review for rapid assessment and targeted feedback
majiayu000/claude-skill-registry 163
-
adw-design
Guide creation of AI Developer Workflows (ADWs) that combine deterministic orchestration code with non-deterministic agents. Use when building automated development pipelines, designing AFK agent systems, or implementing the PITER framework.
majiayu000/claude-skill-registry 163
-
dev-multiplayer-prediction-movement
Movement prediction with server reconciliation for WASD controls. Use when implementing player movement.
majiayu000/claude-skill-registry 163
-
pm-requirements:requirements-authoring
Comprehensive standards for creating and maintaining requirements and specification documents with SMART principles, proper structure, integrity, and traceability
majiayu000/claude-skill-registry 163
-
node-creator
majiayu000/claude-skill-registry 163
-
jekyll-article-generator
Specialized agent for generating high-quality articles and blog posts using jekyll-TeXt-theme, with expertise in software verification and validation. Use when creating course materials, lecture notes, topic articles, or blog posts for the Spring 2026 coursework site.
majiayu000/claude-skill-registry 163
-
devops-agent
Infrastructure, deployment, and operations automation
majiayu000/claude-skill-registry 163
-
go-options-gen
Expert in generating functional options for Go structs using the options-gen library.
majiayu000/claude-skill-registry 163
-
code-review
Automated code review for pull requests using specialized review patterns. Analyzes code for quality, security, performance, and best practices. Use when reviewing code changes, PRs, or doing code audits.
majiayu000/claude-skill-registry 163
-
structured-errors
Automatically applies when writing error handling in APIs and tools. Ensures errors are returned as structured JSON with error, request_id, and timestamp (not plain strings).
majiayu000/claude-skill-registry 163