feature-spec-author
Draft detailed engineering specs from an approved PRD. Use when generating or updating the engineering specification for a feature, before implementation begins.
发现 文档写作 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。
Draft detailed engineering specs from an approved PRD. Use when generating or updating the engineering specification for a feature, before implementation begins.
Analyze reproduction evidence to identify the root cause of bugs. Use after reproduction to trace execution and find the exact location and reason for the failure.
Engineering critic for backlog prioritization debates. Challenges proposed rankings with feasibility concerns, hidden complexity, and realistic effort estimates.
Analyzes code changes for quality issues, code smells, SOLID violations, LLM-generated code problems, and refactoring opportunities. Reports findings with severity, evidence, and suggested fixes.
Design fix plans based on root cause analysis. Use after root cause is identified to plan specific code changes and test cases needed to fix the bug.
Split complex issues into smaller, implementable sub-issues. Called automatically when ComplexityGate determines an issue needs splitting.
Review and score engineering specs against a quality rubric. Use when evaluating a spec draft before implementation to ensure it meets quality standards and identifies potential issues.
Reviews code quality analyst findings. Validates issues are real, severity is appropriate, and suggested refactorings are practical.
Executes behavioral API tests by spinning up the service and making real HTTP requests. Validates status codes, response structure, and data correctness.
Review and score engineering specs against a startup-focused quality rubric. Penalize over-engineering and reward simplicity.
Champion prioritization of discovered opportunities. Advocates for the most impactful, actionable items based on team velocity, business value, and technical feasibility.
Implementation Agent: Full TDD workflow in a single context window. Writes tests, implements code, and iterates until all tests pass.
Chief Architect review - critically evaluate peer feedback on an engineering spec. Integrate valid suggestions, push back on scope creep, and maintain alignment with the PRD. Enforce startup simplicity.
Analyze test failures and suggest fixes for Feature Swarm verification. Use when tests fail during the verification phase to diagnose root cause and determine if automatic recovery is possible.
Generate GitHub issues from an approved engineering specification. Use to break down a spec into implementable, atomic tasks with dependencies, sizing, and labels.
Validate generated GitHub issues for completeness and implementability. Reviews each issue for clear scope, actionable acceptance criteria, and sufficient context for implementation.
Synthesizes analyst findings with critic feedback. Produces final recommendations and generates TDD-compatible refactor plans for approved issues.
Validates API contracts by discovering consumers and ensuring responses match their expectations. Detects breaking changes.
This skill should be used when the user needs to integrate with Hubble Network Platform API for IoT device management, packet data retrieval, webhook configuration, metrics tracking, user management, or billing...
Testing patterns for litefs-py and litefs-django. Use when writing tests, setting up fixtures, understanding test organization, or configuring pytest marks. Triggers: test, pytest, unit test, integration test,...
Neovim設定の相談と編集を行うスキル。プラグインの追加、キーバインドの設定、LSPの設定、UIのカスタマイズなど、init.luaの編集全般をサポートします。
Godot Engine game development. Use for Godot projects, GDScript/C#, scenes (.tscn), Resources, signals, UI, rendering, and macOS/iOS export.
Resolve disagreements between agents or approaches using test-based adjudication. Use when agents disagree, when multiple valid approaches exist, when the user asks "which approach", or when making architectura...
Retrieve relevant context from past sessions before starting implementation. Use when beginning work on a task, when the user describes what to build, when about to write significant code, or when stuck on a pr...
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。