查找技能

Create and use Claude Code slash commands - quick prompts, bash execution, file references

中文简介正在准备中。当前显示原文说明。

Formal theorem proving with research, testing, and verification phases

中文简介正在准备中。当前显示原文说明。

Store a learning, pattern, or decision in the memory system for future recall

中文简介正在准备中。当前显示原文说明。

OPC Architecture Understanding

中文简介正在准备中。当前显示原文说明。

TDD workflow for migrations - orchestrate agents, zero main context growth

中文简介正在准备中。当前显示原文说明。

Release preparation workflow - security audit → E2E tests → review → changelog → docs

中文简介正在准备中。当前显示原文说明。

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

中文简介正在准备中。当前显示原文说明。

System health check (MOT) for skills, agents, hooks, and memory

中文简介正在准备中。当前显示原文说明。

Analyze brownfield codebase and create initial continuity ledger

中文简介正在准备中。当前显示原文说明。

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

中文简介正在准备中。当前显示原文说明。

Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.

中文简介正在准备中。当前显示原文说明。

Generate comprehensive PR descriptions following repository templates

中文简介正在准备中。当前显示原文说明。

Explicit Identity Across Boundaries

中文简介正在准备中。当前显示原文说明。

Debug issues by investigating logs, database state, and git history

中文简介正在准备中。当前显示原文说明。

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

中文简介正在准备中。当前显示原文说明。

Find unused functions and dead code in the codebase

中文简介正在准备中。当前显示原文说明。

Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".

中文简介正在准备中。当前显示原文说明。

Completion Check: Verify Infrastructure Is Wired

中文简介正在准备中。当前显示原文说明。

Claude Code CLI commands, flags, headless mode, and automation patterns

中文简介正在准备中。当前显示原文说明。

Guide for integrating Agentica SDK with Claude Code CLI proxy

中文简介正在准备中。当前显示原文说明。

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

中文简介正在准备中。当前显示原文说明。

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

中文简介正在准备中。当前显示原文说明。

Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

中文简介正在准备中。当前显示原文说明。

Spawn Agentica multi-agent patterns

中文简介正在准备中。当前显示原文说明。