搜索

receiving-code-review

233Kcode-generation

用于接收代码审查反馈时，在实施建议之前，特别是当反馈看起来不明确或技术上可疑时——需要技术严谨性和验证，而非表演性同意或盲目实施

obra

build

1.1Ktesting-qa

针对 SPEC.md 进行先规划后执行的实现。原生单线程循环，无子代理。测试或构建失败时，在重试前自动调用 backprop 技能——失败的验证总会考虑新的 §V 不变量是否能防止再次发生。当用户要求构建、实现、执行规范或处理特定 §T 任务时触发（`build §T.3`、`build --next`、`implement next task`、`run the build`）。期望 SPEC.md 存在；如果不存在，则交由 spec 技能处理。

spec

1.1Ktesting-qa

在仓库根目录创建、修订或反向传播缺陷到 SPEC.md。作为项目规格的唯一修改者。当用户要求编写规格、启动新规格、从现有代码提炼规格、添加不变量、修订章节（§G、§C、§I、§V、§T、§B）或通过反向传播记录缺陷时触发。常见表述：“为……编写规格”、“新规格”、“缺陷：……”、“修订 §V.3”、“从代码提炼规格”、“规格化这个想法”。读取并遵循 FORMAT.md 中的原始编码规则以及 §T 和 §B 的管道表格式。

check

1.1Kresearch-knowledge

只读漂移检测器。将 SPEC.md 与当前代码进行差异比较，并按严重程度分组报告违规情况。不写入任何内容——通过 spec 或 build 技能建议修复方法，但绝不调用它们。当用户要求检查漂移、审计规范、验证不变量，或询问代码是否仍符合规范时触发。表述方式："check drift"、"audit the spec"、"does the code still match §V"、"check invariants"、"spec vs code"。

backprop

1.1Ktesting-qa

Bug 到 Spec 的反向回溯协议。当发现 Bug 或测试失败时，追查根因，判断新增 §V 不变量是否能防止复发，并将记录追加至 §B。这是 SDD（规范驱动开发）区别于常规“先规划后执行”模式中最精妙的一环。触发场景包括：测试失败、Bug 报告、事故复盘或用户明确要求。

caveman

1.1Kbackend-api

用于 SPEC.md 及规范相关文档的穴居人编码。由 /spec、/build、/check 加载。相比散文节省约 75% 的 token，同时保持精确。在写入 SPEC.md 或用户说出“caveman”、“compress this”、“be brief”时触发。

tend

442testing-qa

Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.

weed

442backend-api

Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to check spec-code alignment, compare specs against implementation, audit for spec drift or violations, sync specs with code or code with specs, or verify whether the implementation matches what the spec says.

elicit

441security

Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help shaping it into a specification.

propagate

441backend-api

Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.

distill

441backend-api

Extract an Allium specification from an existing codebase. Use when the user has existing code and wants to distil behaviour into a spec, reverse engineer a specification from implementation, generate a spec from code, turn implementation into a behavioural specification, or document what a codebase does in Allium terms.

allium

437testing-qa

给你的AI代理比提示更有用的东西。通过清晰性实现速度。

saga

140agent-workflows

运行一个自主的、规范驱动的开发“saga”，用于中大型功能，使用编排器代理和一组工作子代理。当用户调用 /saga、要求自主端到端构建一个较大的功能且人工干预最少、希望获得一个全面的规范并分解为里程碑和任务（具有严密的验证标准）以便并行实现、或者希望编排器将实现委托给工作代理同时保留自己的上下文窗口时，使用此技能。触发短语包括“run a saga”、“autonomously implement this feature”、“spec it out then build it with subagents”、“orchestrate this big feature end-to-end”或“build this with workers and validate each step”。当被要求继续、恢复或从 saga 目录（例如 ~/.sagas 下）接手现有 saga 时，也使用此技能。

warpdotdev

spec-driven-implementation

124design-ui

驱动以规范为先的工作流程，用于实现重要功能：在实现前编写 PRODUCT.md，必要时编写 TECH.md，并在实现过程中保持两份规范更新。适用于开始一个重大功能、规划由智能体驱动的实现，或用户希望将产品和技术规范纳入版本控制时使用。

warpdotdev

intent-driven-development

240Ksecurity

Turn ambiguous or high-impact product and engineering changes into scoped, verifiable acceptance criteria before or alongside implementation. Use when a user asks to clarify a feature, define acceptance criteria, de-risk a security/data/migration/integration change, prepare implementation requirements for another agent, or make a complex request testable. Do not trigger for trivial edits, straightforward fixes, active debugging, code review, or implementation requests whose acceptance conditions are already clear unless the user explicitly invokes this skill.

affaan-m

develop

959design-ui

Run /develop to build a feature, UI or backend, from an approved design, a page, component, API, service, or data slice. If something load bearing is undecided and no spec records it, it stops and routes you to /architect; otherwise it reads the spec plus AGENTS.md, builds, and advances the scope.

jsmastery-pro

frontend-design-ui-ux

4design-ui

Produce a distinctive, LOCKED design language plus an implementation-ready UX/UI spec, written to `.ulpi/design/`: a per-brief visual identity (palette, type, signature), the design system to build on, user flows and states, component briefs, and accessibility constraints. Commits to a bold aesthetic direction, bans AI-slop by name, and locks the identity so every screen and future session stays consistent. Can visit inspiration links with the browse skill to extract real design DNA. Ends with a build handoff that a delegated engineering agent implements — a DESIGN-SPEC skill that produces the spec, never production UI code. Use for new features, redesigns, or design-system work where the build should follow a locked spec.

ulpi-io

revenue-centric-design

614design-ui

面向SaaS和初创企业产品的设计手册，涵盖转化、留存和变现——落地页与CRO、引导/激活、降低流失、定价心理学、行为科学策略、功能纪律、定位/ICP、市场推广以及AI时代的差异化。在就产品设计、用户体验、转化、落地页、引导、试用、定价、留存/流失、增长或初创企业/SaaS的定位提供建议时使用。提炼自产品设计师Richard（@richardrx）。不适用于赌博、博彩或赌场产品。

heliocosta-dev

inspired-product

1.7Kdesign-ui

使用发现和交付双轨制，构建赋能型产品团队。当用户提及“产品发现”、“赋能团队”、“功能工厂”、“机会评估”、“产品愿景”、“产品战略”、“我们应该构建什么”或“我们的路线图只是一个功能列表”时触发。当团队从输出驱动模型重组，或基于成果决定下一步构建内容时也触发。涵盖发现技术、团队结构、机会评估、愿景/战略和持续交付。如需客户访谈，请参考 mom-test。如需持续发现系统，请参考 continuous-discovery。

wondelai

test-driven-development

229Ktesting-qa

在实现任何功能或修复缺陷之前使用，先编写测试代码

obra

lean-startup

1.7Kdesign-ui

基于“构建-衡量-学习”（Build-Measure-Learn）循环，设计 MVP、验证性学习实验，并指导“转型还是坚持”的决策。当用户提及“MVP 范围”、“验证性学习”、“转型或坚持”（pivot or persevere）、“虚荣指标”、“验证假设”、“创新核算”、“构建-衡量-学习”、“最小可行实验”、“我们是否该转型”、“低成本验证商业想法”或“先做最小版本”时使用。也可在决定首个版本功能范围、衡量创业/项目进展或评估产品方向是否需要调头时触发。涵盖创新核算与可执行指标。若需进行 5 天原型测试，请参阅 design-sprint；若需分析客户购买/使用动机，请参阅 jobs-to-be-done。

wondelai

domain-driven-design

1.7Kbackend-api

使用限界上下文、聚合和通用语言围绕业务领域建模软件。当用户提到“领域建模”、“限界上下文”、“聚合根”、“通用语言”、“防腐层”、“上下文映射”、“领域事件”、“战略设计”、“代码与业务不匹配”或“如何拆分这个大系统”时使用。在将单体拆分为服务、定义服务边界或使代码结构与业务流程对齐时也触发。涵盖实体与值对象、领域事件和上下文映射策略。有关架构层，请参见clean-architecture。有关复杂性，请参见software-design-philosophy。

wondelai

openspec-implementation

9testing-qa

Implements approved specification proposals by working through tasks sequentially with testing and validation. Use when implementing changes, applying proposals, executing spec tasks, or building from approved plans. Triggers include "openspec implement", "implement", "apply change", "execute spec", "work through tasks", "build feature", "start implementation".

forztf