Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
scientific-slides
使用 Nano Banana Pro AI 构建科研报告和演示幻灯片。可生成高质量、视觉效果出色的 PDF 演示文稿，包含 AI 生成的幻灯片内容。适用于会议报告、学术研讨会报告、论文答辩幻灯片或各类科学演讲。提供幻灯片结构设计、版式与设计指导、时间安排建议以及视觉效果校验。
majiayu000/claude-skill-registry 163
-
jeecgboot-starter
majiayu000/claude-skill-registry 163
-
streamlit-development
Developing, testing, and deploying Streamlit data applications on Snowflake. Use this skill when you're building interactive data apps, setting up local development environments, testing with pytest or Playwright, or deploying apps to Snowflake using Streamlit in Snowflake.
majiayu000/claude-skill-registry 163
-
md-merge
Merges markdown chunks back into a single document, reversing the split operation with integrity checks.
majiayu000/claude-skill-registry 163
-
pricing-governance
Use to run pricing councils, track decisions, and enforce approval workflows.
majiayu000/claude-skill-registry 163
-
rate-sheet-comparison
FirstMile Xparcel rate sheet year-over-year comparison tool. Use when user provides two rate sheet Excel files (prior year and current year) and wants to compare Xparcel Expedited and Ground rates. Triggers on phrases like "compare rate sheets", "rate comparison", "2025 vs 2026 rates", "analyze pricing changes", "rate sheet analysis", or when two FirstMile Xparcel rate sheet files are mentioned. Generates Excel output with side-by-side rates, $ difference, % difference, weight band summaries, and conditional formatting.
majiayu000/claude-skill-registry 163
-
tooluniverse
Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural biology, proteomics, and drug discovery. This skill provides access to 600+ scientific tools including machine learning models, datasets, APIs, and analysis packages. Use when searching for scientific tools, executing computational biology workflows, composing multi-step research pipelines, accessing databases like OpenTargets/PubChem/UniProt/PDB/ChEMBL, performing tool discovery for research tasks, or integrating scientific computational resources into LLM workflows.
majiayu000/claude-skill-registry 163
-
terra-sdk
Terra SDK integration for Python, JavaScript, iOS, Android, React Native, and Flutter. Use when implementing Terra in applications, choosing SDKs, or integrating mobile health sources.
majiayu000/claude-skill-registry 163
-
share-transcript
This skill should be used when the user asks to "share this session", "upload transcript", "create gist", "share conversation", or wants to publish the current Claude Code session as a GitHub Gist.
majiayu000/claude-skill-registry 163
-
edition-data-author
Creates and validates catalog items for edition JSON files including spells, qualities, gear, augmentations, weapons, armor, adept powers, foci, and complex forms. Use when adding new items to core-rulebook.json or sourcebook files, or when validating existing catalog entries.
majiayu000/claude-skill-registry 163
-
reaction-adder
Slack メッセージにリアクションを追加する。「リアクション追加」「リアクションつけて」「👍つけて」「絵文字で反応」「リアクションで返信」「いいねして」「リアクション送って」などで起動。公式Slack MCPの `slack_add_reaction` を使用。
majiayu000/claude-skill-registry 163
-
test-data-generation
Provides patterns and examples for generating test data using factory libraries. Use this skill when you need to create realistic and maintainable test data for your application. It covers factory patterns (e.g., Factory Boy for Python, Polly.js for JavaScript), handling relationships between models, using traits for data variations, sequence generation for unique values, and cleanup strategies. Trigger this skill for tasks involving test fixtures, data seeding for tests, or factory implementation.
majiayu000/claude-skill-registry 163
-
log-learning
Log key learnings to progress.txt during PRD iteration. Use when you discover codebase patterns, encounter gotchas, make important decisions, or learn something that would help future work sessions. Triggers on: log learning, add to progress, capture insight, record pattern, note gotcha, save lesson.
majiayu000/claude-skill-registry 163
-
dyad:multi-pr-review
Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are classified as high/medium/low severity (sloppy code that hurts maintainability is MEDIUM). Results are aggregated using consensus voting - only issues identified by 2+ agents where at least one rated it medium or higher severity are reported. Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues mentioned in a collapsible section.
majiayu000/claude-skill-registry 163
-
Backward Compatibility Rules
Comprehensive guide to backward compatibility rules for APIs, databases, and data contracts with migration strategies and testing approaches
majiayu000/claude-skill-registry 163
-
using-quality-engineering
Use when user asks about E2E testing, performance testing, chaos engineering, test automation, flaky tests, test data management, or quality practices - routes to specialist reference sheets with deep expertise instead of providing general guidance
majiayu000/claude-skill-registry 163
-
context-optimization
This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.
majiayu000/claude-skill-registry 163
-
producer-implementation
Producer implementation patterns for API operations and business logic
majiayu000/claude-skill-registry 163
-
component-docs-batcher
批量生成和维护前端组件库文档的自动化工具。专为 Monorepo 组件库设计（如 atom-ui-mobile），通过对比组件文件和文档的修改时间，自动生成任务清单并批量生成符合规范的完整组件文档。支持以下场景：(1) 定期批量更新组件文档，(2) 单个组件文档维护，(3) 新组件文档初始化。自动识别主要组件文件，跳过 index.ts、store、hooks 等辅助文件，文档路径为组件目录下的 index.zh-CN.md。
majiayu000/claude-skill-registry 163
-
docker-k8s
Docker, Docker Compose, and Kubernetes patterns for containerization and orchestration
majiayu000/claude-skill-registry 163
-
git-pr-prep
Prepares a Pull Request by staging changes, verifying against acceptance criteria, and creating the PR via GH CLI. Use this skill when a feature is complete and ready for review.
majiayu000/claude-skill-registry 163
-
silent-failure-hunter
Use when asked to detect silent failures/weak error handling or explicitly asked to run the silent-failure-hunter subagent.
majiayu000/claude-skill-registry 163
-
macos-cleaner
分析并通过智能清理建议回收 macOS 磁盘空间。当用户报告磁盘空间问题、需要清理 Mac 或想了解什么占用了存储空间时，应使用此技能。专注于安全的交互式分析，在执行任何删除操作前需要用户确认。
majiayu000/claude-skill-registry 163
-
governance-and-risk
Use when making architectural decisions without documentation, skipping risk analysis, accepting risks without mitigation, or treating governance as optional bureaucracy - enforces mandatory DAR/RSKM based on project risk level
majiayu000/claude-skill-registry 163