查找技能

Save current session context to claude-mem

中文简介正在准备中。当前显示原文说明。

Cross-session Claude Code instance messaging via claude-peers-mcp broker

中文简介正在准备中。当前显示原文说明。

Control and inspect the built-in Web UI (packages/serve) — start, stop, status, open

中文简介正在准备中。当前显示原文说明。

Show all available commands

中文简介正在准备中。当前显示原文说明。

Analyze GitHub issues against current codebase and perform automated triage with priority assessment

中文简介正在准备中。当前显示原文说明。

Advisory model escalation based on task outcome tracking

中文简介正在准备中。当前显示原文说明。

Manage semantic versions for npm packages

中文简介正在准备中。当前显示原文说明。

Full R017 verification (5+3 rounds) before commit

中文简介正在准备中。当前显示原文说明。

PostToolUse hook that compresses Playwright MCP tool output using Haiku summarization — Layer 4 of the token defense stack

中文简介正在准备中。当前显示原文说明。

10-team parallel deep analysis with cross-verification for any topic, repository, or technology. Use when user invokes /research or asks for comprehensive research.

中文简介正在准备中。当前显示原文说明。

Memory persistence operations using claude-mem

中文简介正在准备中。当前显示原文说明。

Redis best practices for caching, data structures, and in-memory data architecture

中文简介正在准备中。当前显示原文说明。

Coordinates QA workflow across planning, writing, and execution agents. Use when user requests testing, quality assurance, or test documentation.

中文简介正在准备中。当前显示原文说明。

Load a skill profile to switch active plugin set. Use when user wants to focus on a specific workflow (web-app/data-eng/harness-dev/minimal) and reduce skill enumeration block size per

中文简介正在准备中。当前显示原文说明。

Pre-generation architecture check — detect R006 separation-of-concerns and compilation metaphor violations before code generation begins

中文简介正在准备中。当前显示原文说明。

Opt-in post-PR analysis and improvement suggestions for code quality enhancement

中文简介正在准备中。当前显示原文说明。

Analyze release workflow findings and recommend follow-up actions — execute immediately or register as issues

中文简介正在准备中。当前显示原文说明。

Invoke and resume YAML-defined pipelines by name — /pipeline auto-dev runs the full release pipeline

中文简介正在准备中。当前显示原文说明。

Template for pre-reasoning → action → post-verification model allocation

中文简介正在准备中。当前显示原文说明。

Safety constraints and quality gates for pipeline and workflow execution

中文简介正在准备中。当前显示原文说明。

Data pipeline architecture patterns for ETL/ELT design, orchestration, and data quality frameworks

中文简介正在准备中。当前显示原文说明。

Multi-agent structured debate with anti-groupthink mechanisms — Devil's Advocate, minority opinion protection, 2-round hard cap. Use when divergent perspectives matter more than consensus (architecture decisions, design tradeoffs, contested specifications).

中文简介正在准备中。当前显示原文说明。

Generate comprehensive optimization report

中文简介正在准备中。当前显示原文说明。

Apply bundle size optimizations

中文简介正在准备中。当前显示原文说明。