技術寫作
5624 skills in 文件 > 技術寫作
create-agent-skills
This skill provides expert guidance for creating, writing, building, and refining Claude Code Skills. It should be used when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
nuxt-ui
Use when implementing or debugging UI features with Nuxt UI components, designing forms, tables, modals, or any user interface work - fetches current documentation to ensure accurate component APIs
documentation
Project documentation patterns using README.md with visual diagrams. For creating and maintaining product-level documentation that's accessible in-app via CMD-I.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
git-commit
Generate meaningful commit messages from git changes following conventional commits format. Use when user says "commit", "create commit", or needs help writing commit messages.
backend-queries
Write efficient and secure database queries following best practices for SQL injection prevention, N+1 query optimization, and performance for PostgreSQL (Bun.sql, Prisma, Supabase) and Firestore. Use this skill when writing or modifying database queries, implementing data fetching logic, working with ORMs (Prisma, TypeORM, Entity Framework), using Bun.sql native driver, querying Firestore collections, or implementing caching strategies. Apply when working on service files (services/*.ts, repositories/*.ts, *Service.cs), query builder implementations, data access layers, or any code that fetches or manipulates data. This skill ensures parameterized queries to prevent SQL injection (never interpolate user input), eager loading to prevent N+1 problems, selective column fetching (no SELECT *), strategic indexing on WHERE/JOIN/ORDER BY columns, transactions for related operations, query timeouts for performance, caching expensive queries, prepared statements with Bun.sql for repeated queries, and query-driven mod
generating-commit-messages
Generates clear commit messages from git diffs. Use when writing commit messages or reviewing staged changes.
documentation-standards
How user-facing and internal documentation should be written and maintained.
julien-mcp-notion-pro
Install Notion Pro MCP for secondary workspace. Use when user has multiple Notion workspaces.
update-readme
Autonomously audit the entire repository and update the main README with comprehensive, accurate documentation of the current codebase
leap-review
Validate LEAP compliance before PR submission. Checks branch structure, required documentation, and markdown formatting.
research-orchestration
Use when brainstorming completes and user selects research-first option - manages parallel research subagents (up to 4) across codebase, library docs, web, and GitHub sources, synthesizing findings and auto-saving to memory before planning
amazon-writing
Use when writing narrative memos, 6-pagers, 1-pagers, press releases, or PRFAQs in Amazon style. Applies Amazon's no-PowerPoint writing standards with data over adjectives, active voice, and the "so what" test.
tempo
Guide for implementing Grafana Tempo - a high-scale distributed tracing backend for OpenTelemetry traces. Use when configuring Tempo deployments, setting up storage backends (S3, Azure Blob, GCS), writing TraceQL queries, deploying via Helm, understanding trace structure, or troubleshooting Tempo issues on Kubernetes.
audio-design
Game audio design patterns for creating sound effects and UI audio. Use when designing sounds for games, writing AI audio prompts (ElevenLabs, etc.), creating feedback sounds, or specifying audio for abilities/UI. Includes psychological principles from Kind Games, volume hierarchy, frequency masking prevention, and prompt engineering for AI audio generation.
claude-commands
Guide for creating custom slash commands for Claude Code. Use this skill when you need to extend Claude Code's capabilities with custom workflows, plugin commands, or reusable prompts defined in Markdown.
docs-seeker
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
documentation-writer
This skill should be used when an agent is assigned to write a section of technical documentation. Provides guidance on breaking down large tasks, using doc-coauthoring workflow, and coordinating with VibeKanban task management. Use when task description mentions "write section", "document this component", or "expand documentation".
prisma-diagram
Generate PRISMA 2020 flow diagrams for systematic reviews. Use when: (1) Conducting systematic literature reviews, (2) Documenting screening process, (3) Reporting study selection for publications, (4) Demonstrating PRISMA compliance, (5) Creating transparent review methodology documentation.
markdown-expert
Enforce markdown linting standards for all documentation to prevent common AI mistakes like missing code language tags, emphasis as headings, and missing blank lines