查找技能

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

中文简介正在准备中。当前显示原文说明。

Use before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.

中文简介正在准备中。当前显示原文说明。

Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.

中文简介正在准备中。当前显示原文说明。

Comprehensive A3 one-page problem analysis with root cause and action plan

中文简介正在准备中。当前显示原文说明。

Systematic Fishbone analysis exploring problem causes across six categories

中文简介正在准备中。当前显示原文说明。

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

中文简介正在准备中。当前显示原文说明。

Create well-formatted commits with conventional commit messages and emoji

中文简介正在准备中。当前显示原文说明。

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

中文简介正在准备中。当前显示原文说明。

Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure

中文简介正在准备中。当前显示原文说明。

Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering

中文简介正在准备中。当前显示原文说明。

Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

中文简介正在准备中。当前显示原文说明。

Search the FPF knowledge base and display hypothesis details with assurance information

中文简介正在准备中。当前显示原文说明。

Reconcile the project's FPF state with recent repository changes

中文简介正在准备中。当前显示原文说明。

Manage evidence freshness by identifying stale decisions and providing governance actions

中文简介正在准备中。当前显示原文说明。

Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.

中文简介正在准备中。当前显示原文说明。

Reset the FPF reasoning cycle to start fresh

中文简介正在准备中。当前显示原文说明。

creates draft task file in .specs/tasks/draft/ with original user intent

中文简介正在准备中。当前显示原文说明。

Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns

中文简介正在准备中。当前显示原文说明。

Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification

中文简介正在准备中。当前显示原文说明。

Evaluate solutions through multi-round debate between independent judges until consensus

中文简介正在准备中。当前显示原文说明。