Development

How-To guide patterns for documentation - task-oriented guides for users with specific goals

Explanation documentation patterns for understanding-oriented content - conceptual guides that explain why things work the way they do

Core technical documentation writing principles for voice, tone, structure, and LLM-friendly patterns. Use when writing or reviewing any documentation.

Mandatory verification steps for all code reviews to reduce false positives. Load this skill before reporting ANY code review findings.

Analyzes feedback logs to identify patterns and suggest improvements to review skills. Use when you have accumulated feedback data and want to improve review accuracy.

Schema for tracking code review outcomes to enable feedback-driven skill improvement. Use when logging review results or analyzing review quality.

Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.

Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns. Use when cleaning up AI-generated code or reviewing for agent-introduced cruft.

Perform 12-Factor Agents compliance analysis on any codebase. Use when evaluating agent architecture, reviewing LLM-powered systems, or auditing agentic applications against the 12-Factor methodology.

Extract architectural decisions from conversations. Identifies problem-solution pairs, trade-off discussions, and explicit choices. Use when analyzing session transcripts for ADR generation.

Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.

Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.

Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or optimizing API calls.

Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.

Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.

Guide creation of AI Developer Workflows (ADWs) that combine deterministic orchestration code with non-deterministic agents. Use when building automated development pipelines, designing AFK agent systems, or implementing the PITER framework.

使用 8 维度框架评估测试完整性。 使用时机：撰写测试、审查测试覆盖率、确保测试品质。 关键字：test coverage, completeness, dimensions, 8 dimensions, test quality, 测试覆盖, 测试完整性, 八维度。

[UDS] 测试驱动开发（TDD）的参考资料：红-绿-重构循环、FIRST 原则与 Arrange-Act-Assert 结构。 Use when: 在实现前先写一个会失败的测试、用 Arrange-Act-Assert 组织测试、以 FIRST 检视既有测试。 Not for: 交互式地驱动 RED/GREEN 循环——该部分已移至采用层（XSPEC-095）；测量测试覆盖了多少代码——请用 /coverage。 Keywords: TDD, test first, Red Green Refactor, FIRST, Arrange Act Assert, unit test, 测试驱动开发, 红绿重构, 单元测试.

引導規格驅动开发 (SDD) 工作流程，在实作前規划变更。 使用时机：建立規格、提案、規划功能、使用 OpenSpec 或类似工具。 关鍵字：spec, specification, SDD, proposal, openspec, design doc, 規格, 提案, 设计文件。

[UDS] 系统考古——从逻辑、数据、运行时三个维度对既有系统做逆向工程。 Use when: 为没有文档的系统补上文档、从既有代码回推规格、绘制未知的数据模型或运行时拓扑。 Not for: 动工前评估健康度与风险——请用 /discover；从已批准的规格正向推导测试——请用 /spec-derive。 Keywords: reverse engineering, system archeology, legacy code, spec extraction, data model, runtime, 逆向工程, 系统考古, 规格提取, 数据模型.

引导重构决策和大规模代码改进。 使用时机：重构代码、遗留系统现代化、技术债、重写决策。 关键字：refactor, rewrite, legacy, strangler, technical debt, 重构, 重写, 技术债.