skill-writer
Expert guide for creating, structuring, and documenting Agent Skills following the official specification. Use when you need to create a new Agent Skill, understand the Agent Skills format, or improve existing...
发现 tools llm ai 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Expert guide for creating, structuring, and documenting Agent Skills following the official specification. Use when you need to create a new Agent Skill, understand the Agent Skills format, or improve existing...
Generate comprehensive invocation documents for scroll-driven visual essays. Use when the user wants to create a visual essay, immersive explainer, interactive documentary, scroll-driven narrative, or cinematic...
Manages exploratory computational analysis sessions using RAYVEN CLI. Use when doing data analysis, scientific computing, machine learning experiments, or any exploratory work where you try approaches, iterate,...
Universal context management with proactive recommendations. Agent checks context levels and recommends compaction/summarization to users. Always active as foundation for context optimization.
Prompt engineering standards for AI interactions with cache optimization. Use when writing AI prompts, optimizing context usage, or structuring AGENTS.md files. Covers prompt caching, token efficiency, and prog...
Agent skills authoring guide for AGENTS.md and SKILL.md files. Use when creating or editing agent instructions, rules, or documentation. Covers progressive disclosure, rule loading, XML tag usage, and token bud...
XML tag standards for AI prompts and documentation. Use when writing prompts, documentation, or AGENTS.md files. Covers approved tags for Claude, GPT-5, Gemini, and Harmony formats with markdown rendering rules...
Claude Code context management with /compact and /clear commands, CLAUDE.md persistence, and Tool Search optimization. Use when operating in Claude Code IDE or when context exceeds 60%. Activate for context opt...
Ralph Loop integration patterns for iterative AI development. Use when starting Ralph loops, managing iterations, or recovering from context compaction. Covers TDD, debugging, context management, and memory per...
Core agent steering with HHH framework (Helpful, Honest, Harmless), exploration-before-implementation workflow, and anti-sycophancy rules. Use when guiding AI agent behavior, handling disagreements, or establis...
Design and integrate n8n workflows with the Studio-535 ecosystem. Focuses on automation best practices, error handling, and secure API communication. Use when working with workflow JSON files or planning automa...
Generate images using Google Gemini/Imagen API. Use when the user asks to create, generate, or make an image, picture, photo, illustration, artwork, or visual content.
Comprehensive task management API development assistance using FastAPI, SQLModel, and pytest. Use when Claude needs to work with task management systems for: (1) Creating task models and database schemas, (2) I...
Comprehensive SQLModel development assistance including model creation, relationship handling, database operations, and integration with FastAPI. Use when Claude needs to work with SQLModel projects for: (1) Cr...
Comprehensive FastAPI development assistance including project setup, route creation, database integration, authentication, and deployment. Use when Claude needs to work with FastAPI projects for: (1) Creating...
Comprehensive API development utilities and helper functions for FastAPI, SQLModel, and pytest. Use when Claude needs to work with API development for: (1) Creating common API patterns and utilities, (2) Implem...
Prevent file conflicts between multiple AI agents working in parallel
Prepare optimal context package before delegating tasks to sub-agents
Analyze tasks and recommend optimal sub-agent(s) for execution
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Codex should use this skill whenever asked to write some sort of internal communications...
セッションの会話から恒久的な振る舞いルールを抽出し、AGENTS.md と突き合わせて追加すべきものを提示する。出力は rules と agents_md_patch の二部構成。
Use claude_code MCP as a third-party co-agent to gather alternative opinions, unblock stalemates, or delegate scoped tasks (reviews, ideas, draft edits) while you remain the decision-maker. Trigger when seeking...
Python backend developer for FastAPI, Django, Flask APIs with SQLAlchemy, Django ORM, Pydantic validation. Implements REST APIs, async operations, database integration, authentication, data processing with pand...
**AUTO-ACTIVATE when user mentions**: new feature, add functionality, implement, create, build, "I want to", unclear requirements, vague ideas. Asks 3 core questions to clarify requirements. Generates requirem...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。