design-readiness-check
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDesign Readiness Check
设计就绪检查
Overview
概述
This skill is the quality gate between design work and implementation planning.
Its job is to answer one question clearly: is the current design complete enough to move into ?
writing-plansIt is not a replacement for . That skill audits standalone design or plan documents. This skill checks the readiness of an in-progress design workflow before planning.
design-decision-audit此skill是设计工作与实施规划之间的质量关卡。
它的职责是清晰回答一个问题:当前设计是否足够完备,可以进入阶段?
writing-plans它不能替代。该skill用于审核独立的设计或规划文档,而本skill则是在规划前检查进行中设计工作流的就绪状态。
design-decision-auditWhen to Use
使用场景
Use this skill when:
- the design looks mostly complete
- the next possible step is
writing-plans - the user asks whether the design is ready to implement
- the remaining concern is completeness, not discovery
Do not use this skill when:
- the design tree is still missing
- major branches remain vague
- core decisions are still unresolved
- the user is asking for a general audit of an external design document
- is missing from the design state
design_target_type
在以下场景中使用本skill:
- 设计看起来基本完成
- 下一步可能是
writing-plans - 用户询问设计是否已准备好实施
- 剩余关注点是完备性,而非探索
在以下场景中请勿使用本skill:
- 设计树仍缺失
- 主要分支仍模糊不清
- 核心决策仍未解决
- 用户要求对外部设计文档进行通用审核
- 设计状态中缺少
design_target_type
Workflow
工作流程
Phase A: Context Preparation
A阶段:上下文准备
Goal: Load design state and assemble context for parallel checks.
- Load the current from the conversation context.
design_state - Read the design tree content and all related context (open branches, decision nodes, risks, validation state).
- If does not exist or the design tree is empty, return NOT READY immediately with a handoff to
design_state.design-structure - If is missing, return NOT READY immediately with a blocking issue for missing required state.
design_target_type - Assemble a context package containing: design tree text, open branches, decision nodes, existing risks, validation entries, and .
design_target_type - Perform a lightweight structural integrity check using the shared rules in :
../design-tree-core/REFERENCE.md- mixed responsibilities inside one tree
- parent/child ownership confusion
- duplicated parent/child logic on the same branch
- branches that likely should have been derived but were kept inline
目标:加载设计状态并组装上下文以进行并行检查。
- 从对话上下文中加载当前的。
design_state - 读取设计树内容及所有相关上下文(未闭合分支、决策节点、风险、验证状态)。
- 如果不存在或设计树为空,立即返回NOT READY,并转交至
design_state。design-structure - 如果缺少,立即返回NOT READY,并标记缺失必要状态的阻塞问题。
design_target_type - 组装上下文包,包含:设计树文本、未闭合分支、决策节点、已存在的风险、验证条目以及。
design_target_type - 使用中的共享规则执行轻量级结构完整性检查:
../design-tree-core/REFERENCE.md- 单个树中混合了不同职责
- 父/子所有权混淆
- 同一分支上存在重复的父/子逻辑
- 本应派生但仍内联保留的分支
Phase B: Parallel Readiness Checks
B阶段:并行就绪检查
Goal: Run four independent checks in parallel using specialized subagents.
-
Launch four parallel Sonnet subagents, each using one of the checker agent templates:
- branch-checker: reads . Fill
skills/design-readiness-check/agents/branch-checker.mdand{{DESIGN_TREE}}.{{CONTEXT}} - assumption-checker: reads . Fill
skills/design-readiness-check/agents/assumption-checker.mdand{{DESIGN_TREE}}.{{CONTEXT}} - failure-checker: reads . Fill
skills/design-readiness-check/agents/failure-checker.mdand{{DESIGN_TREE}}.{{CONTEXT}} - risk-checker: reads . Fill
skills/design-readiness-check/agents/risk-checker.mdand{{DESIGN_TREE}}.{{CONTEXT}}
- branch-checker: reads
-
Collect results from all four subagents.
Fallback: If any subagent fails or times out, the main agent performs that check inline using the same rubric from the agent template.
目标:使用专用子agent并行运行四项独立检查。
-
启动四个并行的Sonnet子agent,每个子agent使用一个检查器agent模板:
- branch-checker:读取,填充
skills/design-readiness-check/agents/branch-checker.md和{{DESIGN_TREE}}。{{CONTEXT}} - assumption-checker:读取,填充
skills/design-readiness-check/agents/assumption-checker.md和{{DESIGN_TREE}}。{{CONTEXT}} - failure-checker:读取,填充
skills/design-readiness-check/agents/failure-checker.md和{{DESIGN_TREE}}。{{CONTEXT}} - risk-checker:读取,填充
skills/design-readiness-check/agents/risk-checker.md和{{DESIGN_TREE}}。{{CONTEXT}}
- branch-checker:读取
-
收集所有四个子agent的结果。
回退方案:如果任何子agent失败或超时,主agent将使用agent模板中的相同标准内联执行该检查。
Phase C: Verdict Synthesis
C阶段:结论综合
Goal: Combine check results into a clear readiness judgment.
-
Map each subagent'sto a pass/fail entry in the readiness checklist:
status- required-state check → "Design target type present"
- branch-checker → "Design tree present" and "Key branches refined"
- assumption-checker → "Decisions resolved" (if assumptions are unresolved)
- failure-checker → "Failure paths documented" and "Validation strategy defined"
- risk-checker → "Blocking risks mitigated"
- structural integrity check → "Structural integrity preserved"
-
Build the ✓/✗ checklist diagram following Diagram Conventions.
-
Determine verdict:
- READY: required state is present, all four checks return , and no structural integrity issue is blocking
pass - NOT READY: required state is missing, any check returns , or structural integrity issues are blocking
fail
-
If NOT READY, determine the handoff target based on which check failed:
- required-state fails → hand off to
design-structure - branch-checker fails → hand off to (branches missing) or
design-structure(branches weak)design-refinement - assumption-checker fails → hand off to (assumptions need expansion)
design-refinement - failure-checker fails → hand off to (failure paths need adding)
design-refinement - risk-checker fails → hand off to (unresolved risk decision) or
decision-evaluation(risk documentation weak)design-refinement - structural integrity fails → hand off to (re-route ownership),
design-orchestrator(derive a child tree), ordesign-structure(shrink duplicated inline logic)design-refinement
- required-state fails → hand off to
-
Updatewith:
design_state- : true or false
status.ready_for_planning - : list from failed checks
status.blocking_issues - Updated ,
open_branches,risksif new information emergedvalidation - If a persisted design artifact exists, keep its document status aligned with the verdict: for NOT READY,
draftfor READYready-for-planning
-
Return the explicit verdict with checklist diagram. Never give a "probably ready" answer.
目标:将检查结果合并为清晰的就绪判断。
-
将每个子agent的映射到就绪检查清单中的通过/未通过条目:
status- 必要状态检查 → "设计目标类型已存在"
- branch-checker → "设计树已存在"和"关键分支已细化"
- assumption-checker → "决策已解决"(若假设未解决)
- failure-checker → "故障路径已记录"和"验证策略已定义"
- risk-checker → "阻塞风险已缓解"
- 结构完整性检查 → "结构完整性已保持"
-
遵循图表规范构建✓/✗检查清单图表。
-
确定结论:
- READY:必要状态已存在,四项检查均返回,且无阻塞性结构完整性问题
pass - NOT READY:必要状态缺失,任何一项检查返回,或存在阻塞性结构完整性问题
fail
- READY:必要状态已存在,四项检查均返回
-
如果为NOT READY,根据哪项检查失败确定转交目标:
- 必要状态检查失败 → 转交至
design-structure - branch-checker失败 → 转交至(分支缺失)或
design-structure(分支薄弱)design-refinement - assumption-checker失败 → 转交至(假设需要扩展)
design-refinement - failure-checker失败 → 转交至(需要添加故障路径)
design-refinement - risk-checker失败 → 转交至(未解决的风险决策)或
decision-evaluation(风险文档薄弱)design-refinement - 结构完整性检查失败 → 转交至(重新分配所有权)、
design-orchestrator(派生子树)或design-structure(缩减重复的内联逻辑)design-refinement
- 必要状态检查失败 → 转交至
-
更新,包含:
design_state- :true或false
status.ready_for_planning - :来自失败检查的问题列表
status.blocking_issues - 若出现新信息,更新、
open_branches、risksvalidation - 若存在持久化设计工件,使其文档状态与结论保持一致:NOT READY时为,READY时为
draftready-for-planning
-
返回明确结论及检查清单图表。绝不能给出“可能就绪”的答案。
Readiness Standard
就绪标准
A design is ready for planning only when:
- is present
design_target_type - the main design tree is present
- key branches are refined enough to guide implementation for the current target type
- major decision nodes are resolved or explicitly deferred with acceptable rationale
- failure paths and validation strategy are not missing
- blocking risks are either mitigated or clearly acknowledged
- tree responsibilities are not mixed in a way that breaks routing clarity
设计只有满足以下条件时才具备规划就绪状态:
- 存在
design_target_type - 主设计树已存在
- 关键分支已细化到足以指导当前目标类型的实施
- 主要决策节点已解决,或有可接受的理由明确推迟
- 故障路径和验证策略无缺失
- 阻塞风险已缓解或已明确确认
- 树的职责未混合到破坏路由清晰度的程度
Expected Outputs
预期输出
Produce or update a that includes:
design_statedesign_target_typeopen_branchesrisksvalidationstatus.ready_for_planningstatus.blocking_issues
Always return an explicit result:
- ready for planning
- not ready for planning
If a persisted design file is part of the workflow, its document status should also be explicit:
- while the design is not ready
draft - after the readiness gate passes
ready-for-planning
生成或更新包含以下内容的:
design_statedesign_target_typeopen_branchesrisksvalidationstatus.ready_for_planningstatus.blocking_issues
始终返回明确结果:
- 已准备好进入规划阶段
- 未准备好进入规划阶段
如果工作流中包含持久化设计文件,其文档状态也应明确:
- 设计未就绪时为
draft - 通过就绪关卡后为
ready-for-planning
Diagram Conventions
图表规范
Present the readiness verdict as a status checklist inside a code block (no language tag):
Readiness Check
├── Design target type present ✓
├── Design tree present ✓
├── Key branches refined ✓
├── Decisions resolved ✗ (storage choice pending)
├── Failure paths documented ✓
├── Validation strategy defined ✓
├── Blocking risks mitigated ✗ (migration cutover risk)
└── Structural integrity preserved ✓
Verdict: NOT READY — 2 blocking issuesRules:
- Use (pass) and
✓(fail) markers with inline reason for failures✗ - Max width: 78 characters
- Always include this checklist in the readiness verdict
在代码块中(无语言标签)以状态检查清单的形式呈现就绪结论:
Readiness Check
├── Design target type present ✓
├── Design tree present ✓
├── Key branches refined ✓
├── Decisions resolved ✗ (storage choice pending)
├── Failure paths documented ✓
├── Validation strategy defined ✓
├── Blocking risks mitigated ✗ (migration cutover risk)
└── Structural integrity preserved ✓
Verdict: NOT READY — 2 blocking issues规则:
- 使用(通过)和
✓(未通过)标记,并为未通过项添加内联原因✗ - 最大宽度:78字符
- 就绪结论中必须包含此检查清单
Entry and Exit Criteria
进入与退出标准
Enter when:
- the design is near completion
- the next meaningful step may be implementation planning
Exit when:
- you have issued a clear readiness decision
- you have identified the next route if the design is not ready
进入条件:
- 设计接近完成
- 下一步可能是实施规划
退出条件:
- 已发布明确的就绪决策
- 已确定设计未就绪时的下一步路径
Handoff Rules
转交规则
- Hand off to only when the design is clearly ready.
writing-plans - Hand off to when foundational branches are still missing.
design-structure - Hand off to when important branches exist but are still weak.
design-refinement - Hand off to when the real blocker is an unresolved decision node.
decision-evaluation - Hand off to when the real blocker is tree ownership or routing drift rather than branch weakness.
design-orchestrator - Treat missing as an immediate blocker, not as a soft warning.
design_target_type - Never give a "probably ready" answer. The result must be explicit.
- 仅当设计明确就绪时,才转交至。
writing-plans - 当基础分支仍缺失时,转交至。
design-structure - 当重要分支存在但仍薄弱时,转交至。
design-refinement - 当真正的阻塞因素是未解决的决策节点时,转交至。
decision-evaluation - 当真正的阻塞因素是树所有权或路由偏移而非分支薄弱时,转交至。
design-orchestrator - 将缺失视为立即阻塞因素,而非软警告。
design_target_type - 绝不能给出“可能就绪”的答案。结果必须明确。
Journal Integration
日志集成
When operating on a task tracked under , append a journal entry at this skill's milestone.
.agents/tasks/<task-id>/- Trigger: after readiness verdict is produced
- Reserved key(s): (value must be
readinessorready)not-ready - Entry shape:
## <ISO8601-timestamp> — design-readiness-check readiness: ready [optional ≤ 15-line body; longer content goes to artifacts/]
Resolve the task id from the explicit caller argument or . If neither resolves, skip the append; do not guess.
.agents/tasks/.currentSee for the full convention.
task-journal当在下跟踪的任务上操作时,在此skill的里程碑处追加日志条目。
.agents/tasks/<task-id>/- 触发时机: 就绪结论生成后
- 保留键: (值必须为
readiness或ready)not-ready - 条目格式:
## <ISO8601-timestamp> — design-readiness-check readiness: ready [可选≤15行正文;更长内容放入artifacts/]
从显式调用者参数或解析任务ID。如果两者都无法解析,则跳过追加操作;请勿猜测。
.agents/tasks/.current有关完整规范,请参见。
task-journal