cc-devflow 4.5.15 → 4.5.17

package/.claude/skills/cc-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: cc-review
-version: 2.2.1
+version: 2.2.3
 description: Use when a plan, bug fix, PR, or implementation diff needs review findings. Plan reviews write findings into task.md; implementation reviews ask the user to choose a repair option before fixing.
 triggers:
   - 深度 review 这个方案
@@ -41,6 +41,7 @@ entry_gate:
 exit_criteria:
   - Findings are listed first, ordered by severity and backed by concrete file/line, command, diff, UI, log, or missing-evidence proof.
   - Every finding has impact, recommendation, and route: cc-plan, cc-do, cc-check, cc-act, or stop.
+  - Findings include an ASCII Branch Chain when they involve plan scope, root cause, implementation behavior, PR diff risk, or code smell propagation; tree connector characters stay ASCII while node text follows the configured output language.
   - Plan or investigation review findings are written into the relevant `task.md` section before exit.
   - Implementation review findings are returned with concrete repair options and a blocking user choice; no repair happens until the user selects an option.
   - In-scope code smells are either findings, explicit defers, or clean with reason.
@@ -110,9 +111,10 @@ Review 的价值在于问题质量，不在于过程记录数量。没有证据
 3. Delta：用 Git、PR diff、`task.md` 和当前命令输出确定相对上次或 base 的真实变化。
 4. Facets：按风险选择 strategy / engineering / design / DX / TOC / contract / smell / test / runtime / docs。
 5. Nodes：把每个 selected facet 或 changed surface 当成一个 review node，在 scratch reasoning 中逐个检查；每个 node 只能 checked、skipped、blocked。
-6. Findings：每个 finding 必须有 evidence、impact、recommendation、route；没有证据的怀疑只能是 residual risk 或 blocked evidence。
-7. Aggregate：合并重复 finding，降级弱证据，拒收 out-of-scope、stale、speculative finding。
-8. Exit：计划问题写 `task.md`；实现问题回对话给修复选项；只差验证进 `cc-check`。
+6. Chain：对 plan / investigation / broad implementation / PR / smell finding 画 ASCII Branch Chain，向上追来源，向下追影响面。
+7. Findings：每个 finding 必须有 evidence、impact、recommendation、route；没有证据的怀疑只能是 residual risk 或 blocked evidence。
+8. Aggregate：合并重复 finding，降级弱证据，拒收 out-of-scope、stale、speculative finding。
+9. Exit：计划问题写 `task.md`；实现问题回对话给修复选项；只差验证进 `cc-check`。
 
 渐进加载只控制读多少上下文，不允许把该审的节点省掉。
 
@@ -144,9 +146,49 @@ Review 的价值在于问题质量，不在于过程记录数量。没有证据
 - impact: 它会导致什么错误、回归、维护成本或用户问题
 - recommendation: 最小修复动作
 - route: `cc-plan` / `cc-do` / `cc-check` / `cc-act` / `stop`
+- ASCII Branch Chain: 用 ASCII 分叉树展示 source -> faulty node -> downstream impact -> fix route；若涉及提示词或 provider contract，必须追到精确 prompt/provider 位置
 
 代码坏味道包括 rigidity、duplication、cycle、fragility、obscurity、data-clump、unnecessary complexity。范围内发现就报；不在范围内只作为 defer 或不提。
 
+## ASCII Branch Chain Shape
+
+Review 输出中的链路树必须使用 ASCII 连接符，不用 Unicode tree glyphs。
+
+Language rule:
+
+- Tree structure tokens must stay ASCII: `|--`, `` `-- ``, `|`, spaces, and plain punctuation.
+- Node labels, explanations, finding summaries, and route descriptions must follow the configured output language.
+- Language source order: `task.md` `Output language`, PR/task/handoff language fields, then current conversation language.
+- If no language source is available, record the assumption before the tree.
+- Do not hard-code English labels such as `Review Chain` when the configured output language is not English.
+- Use the Label table as the shared source for chain titles, node labels, and placeholder text.
+
+Label table:
+
+| Semantic slot | en | zh-CN |
+| --- | --- | --- |
+| reviewChain | Review Chain | 审查链 |
+| findingMarker | FINDING | 问题 |
+| source | Source | 来源 |
+| faultNode | Fault node | 错误节点 |
+| whyWrong | why wrong | 错误原因 |
+| firstAffectedSeam | first affected seam | 首个受影响边界 |
+| downstreamImpact | Downstream impact | 下游影响 |
+| fixRoute | Fix route | 修复路线 |
+
+```text
+<reviewChain>
+<findingMarker>: <severity + short name>
+|-- <source>: <task / diff / PR / log / prompt / provider contract>
+|-- <faultNode>: <file / section / behavior>
+|   |-- <whyWrong>: <violated contract or smell>
+|   `-- <firstAffectedSeam>: <public seam / caller / artifact>
+|-- <downstreamImpact>: <user / operator / release / maintenance>
+`-- <fixRoute>: <cc-plan / cc-investigate / cc-do / cc-check / cc-act / stop>
+```
+
+Plan / investigation review 的树写进 `task.md` 对应 finding 或 review gate。Implementation / PR review 的树写在当前回复或 GitHub review；不要为了树图创建本地 review 过程文件。
+
 ## Subagents
 
 可以使用只读 reviewer subagent，但输出只在主线程汇总，不写文件。主线程必须验证、去重、降级或拒收 subagent finding。
@@ -181,16 +223,18 @@ Plan / investigation review 的 decision question 写进 `task.md`。Implementat
 先写 `task.md`，再简短回复：
 
 1. Findings written: `task.md` path and sections changed.
-2. Required task changes: task IDs or contract sections updated.
-3. Route: `cc-plan` / `cc-investigate` / `cc-do` / `stop`.
+2. ASCII Branch Chains written: task sections updated with source -> fault -> impact -> route trees.
+3. Required task changes: task IDs or contract sections updated.
+4. Route: `cc-plan` / `cc-investigate` / `cc-do` / `stop`.
 
 ### Implementation Review
 
 只在对话里组织结果并询问用户：
 
 1. Findings: severity, file/line, evidence, impact, fix.
-2. Repair options: smallest safe fix, broader cleanup, defer with risk.
-3. Recommendation: one option and why.
-4. User choice needed: ask which option to apply.
+2. ASCII Branch Chain: one tree per non-trivial finding or smell propagation.
+3. Repair options: smallest safe fix, broader cleanup, defer with risk.
+4. Recommendation: one option and why.
+5. User choice needed: ask which option to apply.
 
 没有问题时直接说 `No findings`，并说明还没验证的风险。

package/.claude/skills/cc-review/references/implementation-review-branch.md

@@ -106,6 +106,7 @@ Findings stay in the response. Ask which repair option to apply before editing c
 Return:
 
 - findings ordered by severity
+- ASCII Branch Chain per non-trivial finding or code smell propagation
 - smallest safe repair option
 - broader cleanup option when the smell is real
 - defer option with explicit risk

package/.claude/skills/cc-review/references/plan-review-branch.md

@@ -106,6 +106,7 @@ Each planning smell becomes a finding in `task.md` and routes to `cc-plan`.
 Write plan review findings directly into `task.md`:
 
 - scope or architecture finding
+- ASCII Branch Chain for each non-trivial scope, root-cause, or architecture finding
 - evidence and impact
 - required task or contract change
 - decision options when user judgment is needed

package/.claude/skills/cc-review/references/review-methods.md

@@ -19,6 +19,36 @@ Pick every method needed by the current risk. This is a routing map, not a findi
 
 Selected methods stay in scratch reasoning and final response/task updates. Do not write process files.
 
+## ASCII Branch Chains
+
+For any plan, investigation, PR, broad implementation, or code-smell finding, include a compact ASCII tree in the durable task update or review output. Keep `|--`, `` `-- ``, `|`, spaces, and punctuation ASCII; write labels, explanations, findings, and evidence summaries in the configured output language. Resolve language from `task.md` `Output language`, PR/task/handoff language fields, then the current conversation language.
+
+Label table:
+
+| Semantic slot | en | zh-CN |
+| --- | --- | --- |
+| reviewChain | Review Chain | 审查链 |
+| findingMarker | FINDING | 问题 |
+| source | Source | 来源 |
+| faultNode | Fault node | 错误节点 |
+| whyWrong | why wrong | 错误原因 |
+| firstAffectedSeam | first affected seam | 首个受影响边界 |
+| downstreamImpact | Downstream impact | 下游影响 |
+| fixRoute | Fix route | 修复路线 |
+
+```text
+<reviewChain>
+<findingMarker>: <severity + short name>
+|-- <source>: <task / diff / PR / log / prompt / provider contract>
+|-- <faultNode>: <file / section / behavior>
+|   |-- <whyWrong>: <violated contract or smell>
+|   `-- <firstAffectedSeam>: <public seam / caller / artifact>
+|-- <downstreamImpact>: <user / operator / release / maintenance>
+`-- <fixRoute>: <cc-plan / cc-investigate / cc-do / cc-check / cc-act / stop>
+```
+
+Trace upstream to the first supported source and downstream to the affected public seam. If prompt text, agent instructions, model/provider parameters, or generated artifacts are part of the chain, name the exact prompt/provider contract or write `unknown -> Evidence Request`.
+
 ## Review Nodes
 
 Before findings, mentally create ordered review nodes:

package/.claude/skills/cc-roadmap/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Roadmap Skill Changelog
 
+## v5.3.1 - 2026-05-17
+
+- make generated `ROADMAP.md` and deprecated `BACKLOG.md` projections render headings, labels, empty placeholders, and readiness booleans in Chinese when `outputPolicy.documentLanguage` is `zh-CN`
+- render `Output language` metadata in generated roadmap and backlog projections and keep v3 backlog metadata aligned with roadmap state metadata
+- preserve parsing for both English and Chinese projection labels so rerenders do not lose roadmap state after localization
+
 ## v5.3.0 - 2026-05-11
 
 - add the Roadmap Funnel Protocol with fixed F0-F9 rounds for direction mode, demand reality, status quo, specific human/sponsor, wedge/lake boundary, observation signal, future fit, premise challenge, alternatives, and route approval

package/.claude/skills/cc-roadmap/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: cc-roadmap
-version: 5.3.0
+version: 5.3.1
 description: "Use when defining, resetting, or narrowing project direction, stage order, or backlog priority before a concrete requirement enters the PDCA loop."
 triggers:
   - "帮我定路线图"