Back to Details

repo-orchestration

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

RepoSkillOpt — To-Be Design & Implementation Orchestration (Canonical Skill)

RepoSkillOpt — 目标状态设计与实现编排（标准Skill）

Purpose

目的

This skill consumes the as-is artifacts (Architecture View + Change-Impact Analysis) and a stated goal, and produces (a) a reviewable target-state design — ADRs + a concise Design Doc grounded in the as-is evidence — and (b) an implementation orchestration plan: a machine-readable Task Ledger decomposed into small, independent, individually acceptance-tested sub-tasks with declared dependencies and a topological order. The plan is an artifact, not an executor — any orchestrator can drive it; this skill never executes the implementation. Vendor-neutral: no dependency on any particular coding-agent runtime.
该Skill会接收现有状态工件（架构视图+变更影响分析）和明确的目标，生成(a)可评审的目标状态设计——基于现有状态证据的ADRs+简洁设计文档，以及(b)实现编排计划：一份机器可读的Task Ledger，分解为小型、独立、可单独验收测试的子任务，包含声明的依赖关系和拓扑顺序。该计划是一个工件，而非执行器——任何编排工具都可基于它执行；本Skill从不执行具体实现。厂商中立：不依赖任何特定编码Agent运行时。

Trigger Conditions

触发条件

Activate when the user asks to design a target state / to-be, plan the work / decompose into tasks, or produce an implementation plan for goal X — or recognizable equivalents. Do not activate for unrelated requests, and do not execute the resulting plan.
当用户要求设计目标状态/未来状态、规划工作/分解任务或为目标X生成实现计划——或类似表述时激活。请勿为无关请求激活，且请勿执行生成的计划。

Prerequisite

前置条件

The as-is artifacts (Architecture View, Change-Impact Analysis) and a stated goal. If the as-is is missing, point the user to the as-is architecture skill first; do not design against an ungrounded picture of the current system.
需具备现有状态工件（架构视图、变更影响分析）和明确的目标。若缺少现有状态工件，请先引导用户使用现有状态架构Skill；请勿基于当前系统的无依据描述进行设计。

Operating Principles

操作原则

  • Ground the design in the as-is. Every design claim is traceable to as-is evidence (
    file:line
    via the cited as-is artifacts). Mark inference as 
    **[inference]**
    , unknowns as 
    **[unknown]**
    .
  • Decide explicitly. Contested choices become ADRs that weigh ≥2 options — no silent defaults.
  • Plan, don't execute. The Task Ledger is a portable artifact; this skill writes it and stops.
  • Independent, acceptance-tested tasks. Each sub-task is small enough to be executed and reviewer-verified on its own, with declared dependencies; if a task isn't independently acceptance-testable, split it.
  • Repository facts stay repository-scoped. Only candidate-for-generic patterns enter convergence.
  • 基于现有状态进行设计。每个设计主张都可追溯到现有状态证据（通过引用的现有状态工件标注
    file:line
    ）。推断内容标记为
    **[inference]**
    ，未知内容标记为
    **[unknown]**
    。
  • 明确决策。有争议的选择需转化为ADRs，权衡至少2种选项——不得默认采用隐性选择。
  • 仅规划，不执行。Task Ledger是可移植的工件；本Skill仅负责生成它，之后停止操作。
  • 独立且可验收测试的任务。每个子任务需足够小，可单独执行并由评审人员验证，同时声明依赖关系；若任务无法独立验收测试，则拆分它。
  • 仓库信息仅限仓库范围内。只有可通用的候选模式才会进入收敛环节。

Workflow

工作流程

(a) Read the as-is artifacts + the goal. Identify constraints and the affected blast-radius.
(b) ADRs (
.reposkillopt/decisions/ADR-NNN-<slug>.md
, per 
templates/adr.md
): one decision each — Context, Options considered (≥2, pros/cons), Decision, Consequences. A goal that conflicts with an as-is constraint is recorded as an ADR trade-off, not papered over.
(c) Design Doc (
.reposkillopt/design/design-doc.md
, per 
templates/design-doc.md
): Goal, Target-state overview, How it maps onto the as-is (each change tied to the current component/flow it touches, cited), Risks & trade-offs (link the ADRs), Out of scope.
(d) Task Ledger (
.reposkillopt/plan/task-ledger.md
, per 
templates/task-ledger.md
): the work as a table — 
id | goal | acceptance | depends_on
— each task independent + individually acceptance-tested, dependencies declared, the dependency graph acyclic, and the front-matter 
topological_order
listing every id with each dependency before its dependent.
(e) Deterministic gate. The artifacts MUST pass the deterministic checks (
check_adr
, 
check_task_ledger
): ≥2 options per ADR; every task has a goal + acceptance; deps exist; graph acyclic; topological order valid.
(a) 读取现有状态工件+目标。识别约束条件和受影响的范围。
(b) ADRs（路径为
.reposkillopt/decisions/ADR-NNN-<slug>.md
，遵循
templates/adr.md
模板）：每个决策对应一份ADR——包含背景、考虑的选项（≥2个，含优缺点）、决策结果、影响。若目标与现有状态约束冲突，需记录为ADR中的权衡项，不得掩盖。
(c) 设计文档（路径为
.reposkillopt/design/design-doc.md
，遵循
templates/design-doc.md
模板）：包含目标、目标状态概述、与现有状态的映射关系（每个变更关联到它所影响的当前组件/流程，并标注引用）、风险与权衡（链接至对应ADRs）、范围外内容。
(d) Task Ledger（路径为
.reposkillopt/plan/task-ledger.md
，遵循
templates/task-ledger.md
模板）：以表格形式呈现工作内容——
id | 目标 | 验收标准 | 依赖项
——每个任务独立且可单独验收测试，声明依赖关系，依赖图无环，且前置部分的
topological_order
列出所有任务ID，确保每个依赖项排在其依赖任务之前。
(e) 确定性校验门。生成的工件必须通过确定性检查（
check_adr
、
check_task_ledger
）：每份ADR包含至少2个选项；每个任务有明确目标和验收标准；依赖项存在；依赖图无环；拓扑顺序有效。

Output Discipline

输出规范

Same R10 labels and citation forms as the as-is skill; design claims cite the as-is artifacts they rest on. Trivial recitations need no label.
与现有状态Skill使用相同的R10标签和引用格式；设计主张需引用其依据的现有状态工件。无需对琐碎表述添加标签。

Human Feedback Loop

人工反馈循环

Corrections to a decision or to the task decomposition are recorded as Feedback Items (
templates/human-feedback.md
) under 
.reposkillopt/feedback/
and applied to the artifact in place.
对决策或任务分解的修正需记录为反馈项（遵循
templates/human-feedback.md
模板），存储在
.reposkillopt/feedback/
目录下，并直接应用到对应工件中。

Skill Convergence Loop

Skill收敛循环

Recurrent candidate-for-generic feedback (≥3 related items) becomes a Skill Edit Proposal (
templates/skill-edit-proposal.md
), accepted only after the validation gate (
rubric/validation-gate.md
): regenerate artifacts for a disjoint held-out set with no per-dimension rubric regression (see 
rubric/tobe-orchestration-rubric.md
) and deterministic checks still passing. Nothing is silently promoted; acceptance bumps the version + CHANGELOG and is mirrored into the four adapters.
重复出现的可通用候选反馈（≥3个相关项）需转化为Skill编辑提案（遵循
templates/skill-edit-proposal.md
模板），仅在通过验证门（
rubric/validation-gate.md
）后才可接受：针对独立的预留数据集重新生成工件，确保各维度评分无退化（详见
rubric/tobe-orchestration-rubric.md
）且仍通过确定性检查。所有内容均需明确确认；通过验收后需更新版本号+CHANGELOG，并同步到四个适配器中。