ReddRadar
Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
tessa
TESSA (TCR and Expression Joint Clustering) is a Bayesian model that integrates T-cell receptor (TCR) sequence profiling with transcriptomes of T cells. It maps the functional landscape of the TCR repertoire by learning unified representations across modalities. The process employs BriseisEncoder to capture TCR sequence features, creating numerical embeddings that reconstruct Atchley Factor matrices and CDR3 sequences.
majiayu000/claude-skill-registry 163
-
violetconnect-patterns
Code patterns for implementing VioletConnect features - Redux, axiosWrapper, AppContext, API routes
majiayu000/claude-skill-registry 163
-
schema-design
Universal database schema design principles: normalization strategy, data types, primary keys, constraints, anti-patterns, and red flags. Apply when designing schemas, reviewing database architecture, or refactoring data models.
majiayu000/claude-skill-registry 163
-
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
majiayu000/claude-skill-registry 163
-
nextjs-15-specialist
Use when working with Next.js 15 features, App Router, Server Components, Server Actions, or data fetching patterns. Ensures correct usage of Server vs Client Components and modern Next.js patterns.
majiayu000/claude-skill-registry 163
-
patch-engineer
Patch engineer persona focused on security fix quality, code correctness, testing strategies, and regression prevention
majiayu000/claude-skill-registry 163
-
fiber-scheduling-theory
Apply deep knowledge of Fiber scheduling to reason about rendering priorities, preemption, and starvation avoidance.
majiayu000/claude-skill-registry 163
-
langgraph-hitl
Human-in-the-loop integration for LangGraph workflows with approval and intervention points
majiayu000/claude-skill-registry 163
-
forge-analyzer
Analyze vague user ideas and recommend architecture based on actual needs, not predefined categories. Front-end for clarifying ambiguous requests before routing to appropriate skillmaker tools.
majiayu000/claude-skill-registry 163
-
sentry-setup-ai-monitoring
Setup Sentry AI Agent Monitoring in any project. Use this when asked to add AI monitoring, track LLM calls, monitor AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI. Automatically detects installed AI SDKs and configures the appropriate Sentry integration.
majiayu000/claude-skill-registry 163
-
quantization
Model quantization for efficient inference and training. Covers precision
types (FP32, FP16, BF16, INT8, INT4), BitsAndBytes configuration, memory
estimation, and performance tradeoffs.
majiayu000/claude-skill-registry 163
-
claude-worktree-manager
Create and manage Claude-specific worktrees with automated setup and cleanup. Use this skill (via Skill tool or direct script) when asked to "create a worktree", "new worktree", "worktree for feature/staging", "setup isolated environment", or "cleanup old worktrees". Script path is auto-detected when using Skill tool. Handles smart naming, .env copying, background pnpm install, and automatic cleanup of stale worktrees.
majiayu000/claude-skill-registry 163
-
gcp-batch-inference
Running batch inference on Google Cloud (also known as Vertex AI)
majiayu000/claude-skill-registry 163
-
subagent-creator
创建具有自定义系统提示和工具配置的专业化 Claude Code 子代理。当用户要求创建新的子代理、自定义代理、专业助手，或为 Claude Code 配置特定任务的 AI 工作流时使用。
majiayu000/claude-skill-registry 163
-
github-operations
Use when Codex must inspect or update GitHub resources (issues, PRs, workflows) through the official remote GitHub MCP server.
majiayu000/claude-skill-registry 163
-
nnsight-basics
Core nnsight concepts for neural network interpretability. Use when setting up models, tracing activations, saving values, or making basic interventions on model internals.
majiayu000/claude-skill-registry 163
-
task-memory-consolidation
Parse memory.yaml and consolidate recurring patterns into skills. Use when memory.yaml grows large, when patterns recur 3+ times, or during RSID Ideate stage. Automates the memory-to-skill pipeline.
majiayu000/claude-skill-registry 163
-
2-bam-filtration
majiayu000/claude-skill-registry 163
-
laravel-data-writer
Skill for creating and editing Spatie Laravel Data classes following Prowi conventions. Use when working with Data classes, DTOs, or data transfer objects. Enforces proper constructor-based properties, annotation-based validation, and Collection usage.
majiayu000/claude-skill-registry 163
-
ring:regulatory-templates-gate2
Gate 2 sub-skill - validates uncertain mappings from Gate 1 and confirms
all field specifications through testing.
majiayu000/claude-skill-registry 163
-
pylabrobot
Laboratory automation toolkit for controlling liquid handlers, plate readers, pumps, heater shakers, incubators, centrifuges, and analytical equipment. Use this skill when automating laboratory workflows, programming liquid handling robots (Hamilton STAR, Opentrons OT-2, Tecan EVO), integrating lab equipment, managing deck layouts and resources (plates, tips, containers), reading plates, or creating reproducible laboratory protocols. Applicable for both simulated protocols and physical hardware control.
majiayu000/claude-skill-registry 163
-
skilzy-creator
Comprehensive toolset for creating, converting, validating, and packaging Skilzy-compliant AI agent skills. This skill should be used when users want to initialize a new skill, convert a Claude skill archive to the Skilzy format, validate an existing skill's structure and compliance, or package a skill for distribution to the Skilzy registry.
majiayu000/claude-skill-registry 163
-
semo-help
SEMO 도움말 및 Semicolon 팀 컨텍스트 응답 (공통 Skill). Use when (1) /SEMO:help 커맨드,
(2) "도움말", "SEMO란", "어떻게 해" 키워드, (3) SEMO 사용법 질문.
majiayu000/claude-skill-registry 163
-
plan-down
Method clarity-driven planning workflow using zen-mcp tools (chat, planner, consensus). Phase 0 uses chat to judge if user provides clear implementation method. Four execution paths based on automation_mode × method clarity - Interactive/Automatic × Clear/Unclear. All paths converge at planner for task decomposition. Produces complete plan.md file. Use when user requests "create a plan", "generate plan.md", "use planner for planning", "help me with task decomposition", or similar planning tasks.
majiayu000/claude-skill-registry 163