agent-sdk-dev
Expert guide for claude-agent-sdk development questions - tools, subagents, permissions, hooks, sessions, MCP integration, and best practices.
发现 research 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 claude-agent-sdk development questions - tools, subagents, permissions, hooks, sessions, MCP integration, and best practices.
The Pattern Recognizer of the PM Brain. Analyzes company and product strategy, aligns tactical work with strategic objectives, and produces executive-level memos. Use for
The "Recall Engine". Fetches history, decisions, and tasks related to a person or topic.
Process meeting transcripts into notes.
Manage tasks and priorities.
The Librarian of the Mind. Searches, inspects, and explains available AI skills. Use for
The Meta-Architect of the Brain. Generates new AI agent skills based on the Gamma-Class v2.0 Schema. Use for
The Entry Point and Air Traffic Controller for the PM Brain. Transforms chaotic input (hashtags, raw text, voice notes) into structured, routed artifacts. Use for ambiguous input,
The Meeting Intelligence Hub of the PM Brain. Transforms chaotic meeting transcripts into structured artifacts with multi-entity extraction and parallel skill activation. Use for
The Glue of the PM Brain. Owns task lifecycle, brain dump triage, reconciliation, and archive automation. Use for
Research current online documentation and information. Use when working with external libraries, frameworks, APIs, services, version-specific issues, trends, or any topic where LLM training cutoff may impact ac...
Secure coding with Claude Code - vulnerability prevention, secrets, security review
Guide for configuring Claude Code permissions effectively. Use when setting up security policies, configuring allow/deny patterns, managing tool permissions, or implementing team security standards. Covers perm...
Reference guide for Claude Code extensions. CONSULT BEFORE implementing skills, creating hooks, slash commands, or MCP servers. Use when building Claude Code extensions, understanding extension differences, or...
Guide for creating and integrating MCP (Model Context Protocol) servers with Claude Code. Use when building external tool integrations, connecting to databases, creating custom capabilities, or adding API wrapp...
Search and analyze Claude Code transcripts for past decisions, solutions, and discussions. Use when recalling past context, finding solutions to previously-solved problems, understanding session history, or res...
Guide for managing Claude Code memory effectively. Use when setting up project memory, optimizing CLAUDE.md files, configuring rules directories, or establishing cross-session knowledge patterns. Covers memory...
Run Claude Code integration tests in isolated Lima VM sandboxes. Use for E2E testing, hook validation, session survival tests, and any scenario requiring isolated Claude execution.
Deep search across all past Claude Code sessions for decisions, solutions, and discussions
Guide for creating full Claude Code plugins that bundle commands, agents, hooks, MCP servers, and LSP servers. Use when building distributable extensions, packaging multiple components together, or preparing pl...
Guide for creating custom Claude Code subagents (Task tool agents). Use when building specialized autonomous agents for specific domains or workflows. Covers agent definition, frontmatter options, tool restrict...
Guide for creating custom Claude Code slash commands - shortcuts for frequently-used prompts and workflows. Use when creating reusable prompts, automating common tasks, or building team workflows. Covers frontm...
Guide for using Claude Code programmatically via CLI flags and SDKs. Use for automation, CI/CD pipelines, scripting, and building tools on top of Claude Code. Covers --print mode, output formats, session manage...
Guide for using Claude Code with Chrome browser integration. Use when automating browser tasks, debugging web apps, testing UI, or extracting data from websites. Covers setup, capabilities, and common workflows...
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。