Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
majiayu000/claude-skill-registry 163
-
vapor
Vapor framework guardrails, patterns, and best practices for AI-assisted development.
Use when working with Vapor projects, or when the user mentions Vapor.
Provides Fluent ORM, async Swift, routing, middleware, and server-side Swift guidelines.
majiayu000/claude-skill-registry 163
-
bedrock-fine-tuning
Amazon Bedrock Model Customization with fine-tuning, continued pre-training, reinforcement fine-tuning (NEW 2025 - 66% accuracy gains), and distillation. Create customization jobs, monitor training, deploy custom models, and evaluate performance. Use when customizing Claude, Titan, or other Bedrock models for domain-specific tasks, adapting to proprietary data, improving accuracy on specialized workflows, or distilling large models to smaller ones.
majiayu000/claude-skill-registry 163
-
problem-solving
[Utilities] Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), and scale uncertainty (scale game). Triggers: problem-solving, structured thinking, decision framework, simplification cascade, collision-zone thinking, meta-pattern, inversion exercise, scale game.
majiayu000/claude-skill-registry 163
-
tla-spec
TLA+ specification correctness guide — evidence-backed methodology for writing correct temporal logic specs, covering canonical form, abstraction selection, safety/liveness decomposition, fairness, TLC soundness, and distributed systems patterns, with every rule grounded in literature
majiayu000/claude-skill-registry 163
-
create-task
Create a GitHub issue, add it to a project, and set all metadata (status, priority, labels, milestone, type). Use when user wants to create a new task/issue.
majiayu000/claude-skill-registry 163
-
esper:continue
Resume an interrupted session. Reads the active increment, assesses progress, and picks up where the last session left off.
majiayu000/claude-skill-registry 163
-
claude-restart-resume
Quick restart to reload configuration changes (skills, settings, hooks, MCP services). Use PROACTIVELY after modifying .claude/ files. Preserves conversation history.
majiayu000/claude-skill-registry 163
-
pdf
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
majiayu000/claude-skill-registry 163
-
legacy-modernization
Analyze, document, and modernize legacy systems (COBOL, Mainframe, Fortran).
majiayu000/claude-skill-registry 163
-
skill-seekers
-Automatically convert documentation websites, GitHub repositories, and PDFs into Claude AI skills in minutes.
majiayu000/claude-skill-registry 163
-
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
majiayu000/claude-skill-registry 163
-
midnight-tooling:midnight-setup
Use when setting up Midnight development environment, installing Compact compiler and developer tools, configuring proof server, verifying prerequisites, or getting started with Midnight development.
majiayu000/claude-skill-registry 163
-
prompt-caching
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.
majiayu000/claude-skill-registry 163
-
context-save
当用户发送"换窗口处理-"时调用。总结当前窗口的上下文信息、已完成任务、未完成任务，保存到 docs/context-sessions/ 目录，便于新窗口恢复。
majiayu000/claude-skill-registry 163
-
Behavior Trees Skill
Behavior tree design and implementation for robot decision making
majiayu000/claude-skill-registry 163
-
tldr-overview
Generate high-level codebase overview
majiayu000/claude-skill-registry 163
-
Linear Automation
Automate Linear issue tracking, cycle planning, roadmap management, and engineering workflows
majiayu000/claude-skill-registry 163
-
qa-engineer-anton-abyzov-specweave
Expert QA engineer for test strategy and automation. Use when writing tests, fixing failing tests, or improving test coverage.
majiayu000/claude-skill-registry 163
-
plan-interview
Adaptive interview-driven spec generation. Use when converting rough plans into comprehensive specifications, needing structured requirements gathering, or transforming ideas into implementation-ready documentation.
majiayu000/claude-skill-registry 163
-
types
Reference for Splitrail's core data types. Use when working with ConversationMessage, Stats, DailyStats, or other type definitions.
majiayu000/claude-skill-registry 163
-
standards-creator
Create phase-appropriate standards files using latest documentation from context7 and web sources. Invoked by prepare-standards command to generate missing standards files based on task requirements.
majiayu000/claude-skill-registry 163
-
tech-stack-confirmation
Use after completing the requirement-analysis skill and producing a PRD document. This skill guides the process of confirming the technology stack (development languages, frameworks, databases, testing tools, infrastructure) based on PRD requirements. It should be triggered when a user has a PRD and needs to make technology selection decisions, or when the user asks to 'confirm tech stack', 'select technologies', 'do technology evaluation', or 'create architecture decisions' for a project. It should NOT be used for requirements gathering (use requirement-analysis instead) or for detailed system design/implementation planning.
majiayu000/claude-skill-registry 163
-
py-test-bot
Execute BioETL py-test-bot profile for role-specific workflow and constraints.
majiayu000/claude-skill-registry 163