Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
td-movavg-forecast
Moving average based forecasting for smoothed predictions
majiayu000/claude-skill-registry 163
-
hybrid-cloud-networking
Configure secure, high-performance connectivity between on-premises infrastructure and cloud platforms using VPN and dedicated connections. Use when building hybrid cloud architectures, connecting data centers to cloud, or implementing secure cross-premises networking.
majiayu000/claude-skill-registry 163
-
evidence-selfloop
Evidence self-loop for surveys: read evidence bindings + evidence packs, then write an actionable upstream TODO plan (which stage/skill to fix) before writing more prose.
Writes `output/EVIDENCE_SELFLOOP_TODO.md`.
**Trigger**: evidence self-loop, evidence loop, evidence gaps, binding gaps, blocking_missing, 证据自循环, 证据缺口回路.
**Use when**: C4 outputs exist (`outline/evidence_bindings.jsonl`, `outline/evidence_drafts.jsonl`) but writing looks hollow or C5 is BLOCKED due to thin evidence.
**Skip if**: you are still pre-C3 (no notes/evidence bank yet), or you want to draft anyway and accept a lower evidence bar.
**Network**: none.
**Guardrail**: analysis-only; do not edit evidence/writing artifacts; do not invent facts/citations; only write the TODO report.
majiayu000/claude-skill-registry 163
-
ppt
PPT 演示文稿创建、编辑和分析。当需要处理演示文稿时使用，支持：(1) 创建新演示文稿，(2) 修改和编辑内容，(3) 处理布局和样式，(4) 添加图表和表格
majiayu000/claude-skill-registry 163
-
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
majiayu000/claude-skill-registry 163
-
color-contrast-checker
Color Contrast Checker - Auto-activating skill for Frontend Development.
Triggers on: color contrast checker, color contrast checker
Part of the Frontend Development skill category.
majiayu000/claude-skill-registry 163
-
commands-frontmatter-adapter
Parse Claude command frontmatter and expose body/meta for Codex CLI.
majiayu000/claude-skill-registry 163
-
hello-extended
Multi-language greetings in 6 languages. Use for non-English greetings or multiple people.
majiayu000/claude-skill-registry 163
-
tsh-pricing
TSH pricing logic with Zoho Inventory pricebooks. Use when:
(1) Displaying product prices on any page
(2) Working with different price lists (Consumer, Wholesale, Technical, Retail)
(3) Implementing price display for public vs authenticated users
(4) Debugging "Contact for price" issues
(5) Adding pricing to new components
(6) Understanding customer price list assignment
majiayu000/claude-skill-registry 163
-
bellog-structure
Provides file organization and naming conventions for the Bellog project. Triggers when creating new files or reorganizing code.
majiayu000/claude-skill-registry 163
-
RSpec Test Generator
Generates complete, runnable RSpec tests for Rails models, services, controllers, and background jobs following project conventions. Use when new code is created without corresponding tests, when refactoring existing code, or when explicitly asked to add test coverage.
majiayu000/claude-skill-registry 163
-
recursive-improvement
Drive iterative refinement loops with evidence capture, evaluation checkpoints, and stop conditions for skills, prompts, or agents.
majiayu000/claude-skill-registry 163
-
create-command
Guide for creating custom Claude Code slash commands with proper structure, argument handling, frontmatter configuration, and best practices. Use when the user wants to create slash commands, custom commands, reusable prompts, or mentions creating/designing/building commands.
majiayu000/claude-skill-registry 163
-
setting-up-experiment-tracking
Implement machine learning experiment tracking using MLflow or Weights & Biases. Configures environment and provides code for logging parameters, metrics, and artifacts. Use when asked to "setup experiment tracking" or "initialize MLflow". Trigger with relevant phrases based on skill purpose.
majiayu000/claude-skill-registry 163
-
soc2-compliance-checker
Soc2 Compliance Checker - Auto-activating skill for Security Advanced.
Triggers on: soc2 compliance checker, soc2 compliance checker
Part of the Security Advanced skill category.
majiayu000/claude-skill-registry 163
-
docker-optimization
Optimize Docker images and containers for size, build speed, and runtime performance
majiayu000/claude-skill-registry 163
-
react-headless-dev
SEED React Headless component development specialist. Use when developing unstyled, logic-only components in packages/react-headless folder. Focuses on data-driven primitives, custom hooks, and state management without styling concerns.
majiayu000/claude-skill-registry 163
-
managing-stacked-prs
Manages stacked pull requests using git-spice. Creates smaller, reviewable PRs that build on each other, submits them for review, handles feedback, and maintains clean stack history. Use when working with git-spice, stacked PRs, or managing dependent branches.
majiayu000/claude-skill-registry 163
-
book-report
Comprehensive research and analysis of books with actionable insights, hidden gems, and personalized recommendations. Use when the user requests book research, book reports, book analysis, or says "Research Book" followed by a book title. Adapts to project context (professional, personal, academic, hobby).
majiayu000/claude-skill-registry 163
-
run-shell-command-with-long-output
majiayu000/claude-skill-registry 163
-
CLI Testing Patterns
This skill should be used when performing exploratory testing of command-line tools and scripts, including help text validation, option testing, error handling verification, and output validation. Triggers when testing CLI commands, scripts, build tools, or command-line interfaces.
majiayu000/claude-skill-registry 163
-
claude-hooks
Claude Code hooks configuration specialist. Use when creating hooks for tool validation, logging, notifications, or custom automation in Claude Code.
majiayu000/claude-skill-registry 163
-
scvi-tools
Deep generative models for single-cell omics. Use when you need probabilistic batch correction (scVI), transfer learning, differential expression with uncertainty, or multi-modal integration (TOTALVI, MultiVI). Best for advanced modeling, batch effects, multimodal data. For standard analysis pipelines use scanpy.
majiayu000/claude-skill-registry 163
-
documenting-architecture
Generate architecture overview documentation from codebase analysis. Uses tree-sitter-analyzer for precise code structure extraction. Triggers: architecture overview, project structure, module diagram.
majiayu000/claude-skill-registry 163