Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
datafusion-query-advisor
Reviews SQL queries and DataFrame operations for optimization opportunities including predicate pushdown, partition pruning, column projection, and join ordering. Activates when users write DataFusion queries or experience slow query performance.
majiayu000/claude-skill-registry 163
-
td-ngram-splitter
N-gram generation for text preprocessing
majiayu000/claude-skill-registry 163
-
cs-sync
CS-GUIDE.md 업데이트 시 기존 CS 문서들을 새로운 가이드에 맞춰 동기화합니다. "CS 동기화", "CS 싱크", "가이드 반영" 요청 시 사용하세요.
majiayu000/claude-skill-registry 163
-
gmail-unread
Gmail の未読メッセージ一覧を取得する。「未読メール」「Gmail 未読」「未読一覧」「未読メールを見たい」「未読メッセージ」「メールの未読」「全アカウントの未読」などで起動。
majiayu000/claude-skill-registry 163
-
finetune-train
Use when training a fine-tuned model and evaluating improvement over base model. Triggers - have filtered training data, ready to submit training job, need to convert to GGUF. Requires finetune-generate first.
majiayu000/claude-skill-registry 163
-
feedback-conversations
Navigate difficult conversations and deliver constructive feedback using structured frameworks. Covers the Preparation-Delivery-Follow-up model and Situation-Behavior-Impact (SBI) feedback technique. Use when preparing for difficult conversations, giving feedback, or managing conflicts.
majiayu000/claude-skill-registry 163
-
dataset-generator
Generate evaluation datasets with adjustable difficulty levels from PDF documents for RAG system testing and benchmarking
majiayu000/claude-skill-registry 163
-
yanex-experiment-tracking
Use this skill when running, managing, or analyzing yanex experiments. Includes executing experiments via CLI, parameter sweeps, dependencies, querying experiment history, comparing results, and maintaining experiment logs. Invoke when users mention yanex, experiments, training runs, parameter sweeps, or need to track ML experiments.
majiayu000/claude-skill-registry 163
-
ambiguity-detection
Detects critical product, scope, data, risk, and success ambiguities in requirements or PRDs and expresses them as structured, decision-forcing clarification questions without proposing solutions or workflow actions.
majiayu000/claude-skill-registry 163
-
moai-foundation-git
Enterprise GitFlow automation, PR policy enforcement, Git 2.47-2.50 features, trunk-based development, comprehensive branching strategies, commit conventions, GitHub CLI 2.83.0 integration
majiayu000/claude-skill-registry 163
-
close-session
Load when user says "done", "finish", "complete", "close", "wrap up", "end session", or any system skill/project completes
majiayu000/claude-skill-registry 163
-
gemini-delegation-patterns
Strategic patterns for Claude-to-Gemini delegation. Covers decision criteria, execution patterns, result parsing, and error handling. Use when determining if a task should be delegated to Gemini CLI.
majiayu000/claude-skill-registry 163
-
torch-pipeline-parallelism
This skill provides guidance for implementing PyTorch pipeline parallelism for distributed training of large language models. It should be used when implementing pipeline parallel training loops, partitioning transformer models across GPUs, or working with AFAB (All-Forward-All-Backward) scheduling patterns. The skill covers model partitioning, inter-rank communication, gradient flow management, and common pitfalls in distributed training implementations.
majiayu000/claude-skill-registry 163
-
srt
Korean SRT (Super Rapid Train) search, reservation, and booking management
majiayu000/claude-skill-registry 163
-
schema-validation
JSON/data schema validation for construction data exchange: API payloads, file imports, BIM exports. Ensure data structure compliance before processing.
majiayu000/claude-skill-registry 163
-
feature-documentation
Эксперт feature documentation. Используй для документации функций, release notes, user guides и product documentation.
majiayu000/claude-skill-registry 163
-
seo-geo
SEO & GEO (Generative Engine Optimization) for websites.
Analyze keywords, generate schema markup, optimize for AI search engines
(ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing).
Use when user wants to improve search visibility.
majiayu000/claude-skill-registry 163
-
papi
CLI reference for paperpipe (papi). Use BEFORE MCP RAG tools. For listing, searching, showing, adding papers.
majiayu000/claude-skill-registry 163
-
git-committer
Skill for analyzing git changes, grouping them into logical atomic commits, generating conventional commit messages, and guiding through the commit process. Use when committing changes with proper conventional commit format and maintaining atomic commits.
majiayu000/claude-skill-registry 163
-
shadcn-management
Manage shadcn/ui components using MCP tools. Use when user needs to:
(1) Add new shadcn components to a project
(2) Build complex UI features requiring multiple components
(3) Research component implementations and examples
(4) Get component installation commands
Triggers: "add shadcn", "shadcn component", "build UI with shadcn", "install component", "create form", "create dialog"
majiayu000/claude-skill-registry 163
-
ptk-layout
This skill should be used when the user asks about "prompt_toolkit layout", "HSplit", "VSplit", "Window", "Float", "FloatContainer", "ConditionalContainer", "DynamicContainer", "split pane", "terminal UI layout", "prompt_toolkit containers", or needs to compose visual layouts for terminal applications.
majiayu000/claude-skill-registry 163
-
githunt
Find and rank GitHub developers by location, technology, and role. Search for candidates, get scored profiles with tech stack matches, activity, and contact info.
majiayu000/claude-skill-registry 163
-
secrets-1password
1Password Developer CLI skill for secure secrets management. This skill should be used when creating, reading, updating, or deleting secrets in 1Password vaults, injecting secrets into script execution, or setting up 1Password CLI authentication.
majiayu000/claude-skill-registry 163
-
signal-analysis
Perform signal processing, rainflow cycle counting, and spectral analysis for fatigue and time series data. Use for analyzing stress time histories, computing FFT/PSD, extracting fatigue cycles (ASTM E1049-85), and batch processing OrcaFlex signals.
majiayu000/claude-skill-registry 163