VerifiedGit
v1.0.0

/forge-ship:发布上线

by @yike-gunshi0 pulls
URLopenbooklet.com/s/forge-ship
Pinnedopenbooklet.com/s/forge-ship@1.0.0
APIGET /api/v1/skills/forge-ship

14 skills from this repoyike-gunshi/forge-skills
/forge-ship:发布上线viewing
/forge-bugfix:系统性 Bug 调查与修复 v2.1skills/forge-bugfix/SKILL.md
/forge-deliver v2:端到端交付编排层skills/forge-deliver/SKILL.md

一句话描述你的想法,拿到完整交付。

/forge-doc-policy:文档落地治理规范skills/forge-doc-policy/SKILL.md

> 这是一个**规范型 skill**,不主动产出代码或文档,作为其他 forge-* skill 和 LLM 自觉行为的**单一真相源(SSoT)**。 > > 全程中文。

/forge-doc-release:发布后文档更新skills/forge-doc-release/SKILL.md
/forge-qa:QA 验收与测试报告 v3.0skills/forge-qa/SKILL.md

**纯验收模式:测试 + 报告,不修代码。** 发现的问题生成修复清单,回 `/forge-eng` 修复。

/forge-review:代码审查skills/forge-review/SKILL.md
/forge-status:并行会话巡检 + 清理skills/forge-status/SKILL.md
forge-brainstormskills/forge-brainstorm/SKILL.md

通用头脑风暴。任何时候、任何话题都能用。4种模式:产品·内容·构建·探索。6阶段:上下文感知→深度提问→景观感知→前提挑战→方案生成→思考文档。融合 superpowers:brainstorming + office-hours + plan-ceo-review 的精华。反谄媚·Pushback·对抗性审查。触发方式:用户说"头脑风暴"、"brainstorm"、"讨论一下"、"我有个想法"、"帮我想想"、任何需要发散讨论的场景。

forge-designskills/forge-design/SKILL.md

全栈设计规划与文档管理。分级门控体系下,管理项目的 DESIGN.md 和 DESIGN-CHANGELOG。涵盖竞品调研、美学方向探索、配色/字体/风格搜索、三层Token架构、99条UX规则审计、反AI模板检测、0-10交互评分。自闭环——所有设计知识内嵌,不依赖外部Skill。触发方式:用户说"设计"、"forge-design"、forge-dev 调度器调用、需要创建或更新设计文档时使用。

forge-design-implskills/forge-design-impl/SKILL.md

设计实现:将 DESIGN.md 转化为代码。反AI模板编码、shadcn/ui组件推荐、Token驱动样式、CSS优先修改、原子提交。从 forge-design 接力,或 forge-eng 调用。触发方式:用户说"实现设计"、"forge-design-impl"、设计文档确认后需要写代码时使用。

forge-devskills/forge-dev/SKILL.md

开发调度器。接力 forge-prd 产出的 PRD 变更,半自动调度设计(forge-design)、工程(forge-eng)、QA(forge-qa) 子技能。读取 PRD 迭代摘要,并行调研技术方案,判断需要调用哪些子技能,列出建议顺序供用户确认后以独立上下文执行。触发方式:用户说"开始开发"、"实现需求"、"forge-dev"、PRD 更新后需要进入开发阶段时使用。

forge-engskills/forge-eng/SKILL.md

工程文档管理与代码实现。管理项目的 ENGINEERING.md 和 ENGINEERING-CHANGELOG,涵盖前端和后端。支持完整模式(文档+审查+实现)和轻量模式(跳过文档直接实现)。集成 Worktree 会话级隔离、分级 TDD(严格/轻量/验证驱动)、Verification Gate(证据先于断言)。基于 PRD 和 DESIGN.md 产出架构设计、数据流、API 设计、实现清单、测试矩阵,与用户确认关键技术决策后将实现拆分为原子任务、Wave 并行执行、每个任务独立 git commit。触发方式:用户说"工程"、"实现"、"forge-eng"、forge-dev 调度器调用、需要实现代码变更时使用。

forge-prdskills/forge-prd/SKILL.md

产品诊断与 PRD 迭代管理器。用户描述遇到的问题或需求,skill 诊断根因(产品设计缺陷/实现偏离/PRD遗漏)、审查模块健康度、设计方案、挑战假设、必要时反驳需求,最终更新 PRD 和 CHANGELOG。支持从零创建 PRD(深度阅读代码+多轮交互)和迭代已有 PRD。触发方式:用户说"更新PRD"、"调整需求"、"迭代PRD"、"forge-prd"、描述产品问题、需要修改项目产品需求时使用。

Auto-indexed from yike-gunshi/forge-skills

Are you the author? Claim this skill to take ownership and manage it.

Related Skills

@openbooklet

graceful-error-recovery

Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.

1.1K0
@openbooklet

audience-aware-communication

Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.

1.1K0
@openbooklet

Refactoring Expert

Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.

600
@openbooklet

Research Expert

Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.

600
@openbooklet

clarify-ambiguous-requests

Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.

1.1K0
@openbooklet

structured-step-by-step-reasoning

Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.

1.1K0