Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
sentence-transformers
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.
majiayu000/claude-skill-registry 163
-
Model Optimization
Comprehensive guide for ML model optimization techniques including quantization, pruning, knowledge distillation, and inference optimization.
majiayu000/claude-skill-registry 163
-
rr-debugger
Deterministic debugging with rr record-replay. Use when debugging crashes, ASAN faults, or when reverse execution is needed. Provides reverse-next, reverse-step, reverse-continue commands and crash trace extraction.
majiayu000/claude-skill-registry 163
-
ue
UE (user experience engineering) skill for defining end-to-end user experience behavior and interaction logic. Use for tasks like flow design, interaction models, state machines, error recovery, input validation, usability heuristics, accessibility, and turning UX intent into testable acceptance criteria for implementation.
majiayu000/claude-skill-registry 163
-
skill-creation-guide
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.
majiayu000/claude-skill-registry 163
-
uncertainty-routing
Route tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning and 10-30x cost reduction while maintaining accuracy. Use for cost optimization, confidence-based delegation, routine vs complex task routing, and resource efficiency. Triggers on "optimize cost", "model routing", "confidence threshold", "small model first", "escalate on uncertainty".
majiayu000/claude-skill-registry 163
-
obsidian-internal-links
Follow and resolve Obsidian internal links ([[link]] syntax) to navigate interconnected notes within an Obsidian vault. Use when exploring note relationships, following references between documents, building knowledge graphs, or understanding how notes connect together. Supports recursive link traversal with configurable depth.
majiayu000/claude-skill-registry 163
-
validate-inputs
Check function inputs for correctness and safety. Use when implementing defensive programming.
majiayu000/claude-skill-registry 163
-
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
majiayu000/claude-skill-registry 163
-
fluxwing-enhancer-trabian-fluxwing-skills-2
majiayu000/claude-skill-registry 163
-
dag-confidence-scorer
Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
majiayu000/claude-skill-registry 163
-
pipedrive
Manage sales pipeline with Pipedrive's visual deal-focused CRM.
majiayu000/claude-skill-registry 163
-
substrate-vulnerability-scanner
Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks. Use when auditing Substrate runtimes or FRAME pallets.
majiayu000/claude-skill-registry 163
-
sop-dogfooding-continuous-improvement
majiayu000/claude-skill-registry 163
-
risk-buffer-calculator
计算每Phase风险缓冲百分比，基于复杂度、依赖和未知因素进行启发式分析。当需要风险评估、缓冲时间规划、资源预留时使用。主要用于L3项目的严格风险管理。
majiayu000/claude-skill-registry 163
-
build-alexa-skill
majiayu000/claude-skill-registry 163
-
dev-brainstorm
REQUIRED Phase 1 of /dev workflow. Uses Socratic questioning to understand requirements before exploration.
majiayu000/claude-skill-registry 163
-
cv-content-manager
Create, edit, and sync CV content using the knowledge base as source of truth. Unified skill for case studies, blog posts, experience updates, and variant content. Replaces cv-content-generator and cv-content-editor.
majiayu000/claude-skill-registry 163
-
Cross-Team Interfaces
Comprehensive guide to defining and managing cross-team interfaces including APIs, events, data schemas, and process contracts for independent team operation
majiayu000/claude-skill-registry 163
-
managing-appwrite-functions
Handles backend logic that cannot run in the browser. Use for sensitive tasks like price calculation, cleanup, or payment verification.
majiayu000/claude-skill-registry 163
-
solana-kit
Complete guide for @solana/kit - the modern, tree-shakeable, zero-dependency JavaScript SDK from Anza. Covers RPC connections, signers, transaction building with pipe, signing, sending, and account fetching with full TypeScript support.
majiayu000/claude-skill-registry 163
-
Schema
This skill should be used when the user asks about "Effect Schema", "Schema.Struct", "Schema.decodeUnknown", "data validation", "parsing", "Schema.transform", "Schema filters", "Schema annotations", "JSON Schema", "Schema.Class", "Schema branded types", "encoding", "decoding", "Schema.parseJson", or needs to understand how Effect handles data validation and transformation.
majiayu000/claude-skill-registry 163
-
faion-api-developer
API development: REST, GraphQL, OpenAPI, versioning, auth, rate limiting.
majiayu000/claude-skill-registry 163
-
mcp-servers-seanchatmangpt-ggen-2
majiayu000/claude-skill-registry 163