team-ai-skills

创建、审阅和优化团队自有项目 README.md，以准确事实和自上而下的信息层级呈现定位、快速开始、使用与维护入口。Create, review, and improve README.md for team-owned projects using verified facts and a progressive top-to-bottom reading flow.

将代码库事实转化为面向业务、产品和管理者的能力说明、场景材料和影响分析。Turn codebase evidence into business-facing capability briefs, scenario narratives, and impact analysis.

从已有代码仓库提取可追溯的功能清单、架构说明和 AI 接手上下文。Extract traceable feature inventory, architecture notes, and AI onboarding context from an existing codebase.

基于 onboarding 产物和源码，围绕功能清单做代码库走读、问答和证据追踪。Guide developers through codebase features with walkthroughs, Q&A, and source-backed explanations.

为已完成的单个 issue 分支推送代码并创建关联 issue 的 GitLab Merge Request。Push a completed issue branch and create an issue-linked GitLab Merge Request.

为已完成的单个 issue 分支推送代码并创建关联 issue 的 GitHub Pull Request。Push a completed issue branch and create an issue-linked GitHub Pull Request.

为具体代码项目维护 Codex 运行时检索层、入口约束、失败记忆和验证 harness。Maintain a Codex runtime retrieval layer, entry constraints, failure memory, and verification harness for a concrete code project.

根据真实反馈、失败案例和执行日志复盘团队技能库，并提出可审核的技能进化建议。Review real feedback, failures, and execution logs to propose auditable improvements to the team skill library.

按依赖顺序批量编排多个工程 issue 的实现与验证，并保留失败即停和可恢复续跑边界。Batch orchestrate multiple engineering issues in dependency order with verification, fail-fast behavior, and resumable boundaries.

实现单个工程 issue，优先使用行为测试、TDD、现有代码复用和最小实现模式。Implement one engineering issue with behavior-focused tests, TDD, existing-code reuse, and lean implementation.

将本地工程 issue 草稿发布到 GitHub Issues，并回写发布结果。Publish local engineering issue drafts to GitHub Issues and write back publication status.

将本地工程 issue 草稿发布到 GitLab Issues，并回写发布结果。Publish local engineering issue drafts to GitLab Issues and write back publication status.

独立验证单个 issue 实现是否满足验收、PRD、风险和最小实现要求。Verify a single issue implementation against acceptance criteria, PRD, risks, and lean implementation expectations.

将结构化 PRD 转换为适合需求、研发和项目管理评审的对齐材料。Turn structured PRDs into alignment materials for product, engineering, and project management review.

将 PRD 拆解为可独立领取、可验证、按依赖排序的端到端工程 issue。Break PRDs into independently grabbable, verifiable, dependency-ordered engineering issues.

将已完成、废弃或暂停的单个需求工作区从 active 归档到 archive。Archive one completed, abandoned, or paused requirement workspace from active to archive.

通过用户确认细化需求规格，澄清术语、边界、业务规则和验收口径。Refine product specs through user confirmation of terminology, scope, business rules, and acceptance criteria.

评审已细化的需求规格，输出风险、阻塞项、补救动作和 ready 结论。Review refined product specs and produce risks, blockers, mitigations, and readiness findings.

将已细化并通过评审的规格固化为结构化 PRD，形成需求到工程的交接边界。Turn refined and reviewed specs into a structured PRD as the product-to-engineering handoff boundary.

通过用户确认细化技术债需求，明确证据、影响范围、风险等级和验收口径。Refine technical debt requests through user confirmation of evidence, scope, risk, and acceptance criteria.

将已评审的技术债规格拆解为可独立领取、可验证、按依赖排序的工程 issue。Break reviewed technical debt specs into independently grabbable, verifiable, dependency-ordered engineering issues.

对项目或模块进行只读技术债分析，输出有证据的维护性、稳定性、测试、架构和交付风险报告。Analyze technical debt through read-only inspection and produce evidence-backed maintainability, stability, testing, architecture, and delivery risk findings.

评审技术债规格的风险、优先级、阻塞项和工程拆解 ready 状态。Review technical debt specs for risk, priority, blockers, and readiness for issue breakdown.

在产品规划阶段澄清产品定位、价值与能力边界，并编写可评审的产品概念白皮书。Create a reviewable product concept white paper by clarifying its positioning, value, and capability boundaries.