GitHub
agent-configuration
Configure agent specs, inheritance, skills, and tools in .parac/ workspace. Use when setting up or customizing agents.
☆ 0查看技能
content media llm ai AI 技能
发现 content media 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。
分类目录: content media llm ai
content media llm ai 清除筛选
全部技能
GitHub
meta-capabilities
Advanced AI capabilities for paracle_meta including web search, code execution, MCP integration, and autonomous agent spawning. Use when you need enhanced AI functionality beyond basic generation.
☆ 0查看技能
GitHub
tool-integration
Create custom tools, integrate external APIs, and manage tool registry. Use when extending agent capabilities with new tools.
☆ 0查看技能
GitHub
init-reviewer-notes
Create a template file for human reviewers to write free-form feedback before AI code review.
☆ 0查看技能
GitHub
process-reviewer-feedback
Convert free-form reviewer notes to structured feedback format with interactive clarification.
☆ 0查看技能
GitHub
writer
Iterative writing loop. Gemini 3 Pro writes, Claude Agent SDK reviews autonomously. Use for blog posts, docs, technical content needing quality iteration.
☆ 0查看技能
GitHub
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or...
☆ 0查看技能
GitHub
agent-organizer
Assemble and coordinate multi-agent teams: decompose tasks, select skills/agents, design workflows, and manage execution with monitoring and recovery.
☆ 0查看技能
GitHub
skill-editor
Use when drafting or revising an agent skill spec in an environment that already has a general skill creator. Apply user-specific preferences to tighten triggers, reduce redundancy, keep scope safe, and keep th...
☆ 0查看技能
GitHub
product-prd
Generate a Product Requirements Document (PRD) for feature development. Creates PRDs with user stories optimized for AI agent execution.
☆ 0查看技能
GitHub
hypothesis-debugging
Structured code debugging through hypothesis formation and falsification planning. Use when diagnosing bugs, unexpected behaviour, or system failures where the root cause is unclear. Produces a hypothesis docum...
☆ 0查看技能
GitHub
mcp-builder
Build custom Model Context Protocol servers to extend Claude's capabilities
☆ 0查看技能
GitHub
sequential-thinking
Complete guide to using Sequential Thinking MCP server with Claude Code
☆ 0查看技能
GitHub
subagent-driven-development
Quality-gated iteration with multi-agent workflows for complex tasks
☆ 0查看技能
GitHub
deep-research
Turn ambiguous questions into documented, executable plans with traceable artifacts
☆ 0查看技能
GitHub
mcp-builder
Build custom Model Context Protocol servers to extend Claude's capabilities
☆ 0查看技能
GitHub
supabase
Complete guide to using Supabase MCP servers with Claude Code
☆ 0查看技能
GitHub
intelligent-routing
Enable AI to make intelligent decisions about where to place new things and how to find existing things
☆ 0查看技能
GitHub
serena
Complete guide to using Serena MCP server for AI-powered code analysis with Claude Code
☆ 0查看技能
GitHub
code-generation
AI-assisted code generation workflows, prompting strategies, and best practices for working with Claude Code
☆ 0查看技能
GitHub
subagent-driven-development
Quality-gated iteration with multi-agent workflows for complex tasks
☆ 0查看技能
GitHub
31-analyze-think-150
[31] ANALYZE. Universal deep thinking methodology for any situation requiring quality reasoning. Use when solving problems, debugging, making decisions, analyzing code, planning, reviewing, or anytime you need...
☆ 0查看技能
GitHub
00-meta-chain-flow-150
[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, builds an optimal chain, explains why each skill is needed, and executes step-by-step with use...
☆ 0查看技能
GitHub
11-continue-session-150
[11] CONTINUE. Resume an existing session. Use when continuing previous work to load AGENTS.md, MEMORY.md, and the chosen session log, then confirm readiness.
☆ 0查看技能
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。