@fitlab-ai/agent-infra 0.9.13 → 0.9.15

package/templates/.agents/skills/init-labels/SKILL.en.md

@@ -19,17 +19,17 @@ Confirm that:
 
 If any prerequisite fails, stop and report the matching error.
 
-### 2. Run the bootstrap script
+### 2. Run the labels runtime intent
 
 Execute the complete label initialization flow with:
 
 ```bash
-bash .agents/skills/init-labels/scripts/init-labels.sh
+agent-infra-internal platform-metadata init-labels
 ```
 
-The script and `.agents/rules/label-milestone-setup.md` are responsible for:
+The runtime intent and `.agents/rules/label-milestone-setup.md` are responsible for:
 - Reading the configured `labels.in` mapping and preserving unrelated labels
-- Selecting the provider leaf or returning a clear no-op/degraded result
+- Selecting the platform capability or returning a clear no-op/degraded result
 - Creating or updating the standard label set and reporting the final summary
 - Printing the final execution summary
 
@@ -69,8 +69,8 @@ Show the current mapping and ask whether it should be updated.
 #### 4.3 Write the mapping and create labels
 
 1. Write the final mapping to `.agents/.airc.json` under `labels.in`.
-2. Run `bash .agents/skills/init-labels/scripts/init-labels.sh` to create or update one `in: {key}` label for each mapping key.
-3. After user confirmation, rerun the script with `--cleanup-stale-in` to delete stale `in:` labels that are no longer present in the final mapping.
+2. Run `agent-infra-internal platform-metadata init-labels` to create or update one `in: {key}` label for each mapping key.
+3. After user confirmation, rerun the intent with `--cleanup-stale-in` to delete stale `in:` labels that are no longer present in the final mapping.
 
 ### 5. Output and behavior guarantees
 
@@ -100,7 +100,7 @@ Next step - initialize milestones (optional):
 
 ## Error Handling
 
-- Provider capability unavailable: report the script's `degraded` or `no-op` result without claiming remote changes.
-- Provider authentication or repository access failure: report the script's non-zero exit status and diagnostic output; do not claim remote changes.
+- Platform capability unavailable: report the runtime's `degraded` or `no-op` result without claiming remote changes.
+- Platform authentication or repository access failure: report the runtime's non-zero exit status and diagnostic output; do not claim remote changes.
 - Permission error: prompt "No permission to manage labels in this repository"
 - API rate limit: prompt "platform API rate limit reached, please retry later"

package/templates/.agents/skills/init-labels/SKILL.zh-CN.md

@@ -19,17 +19,17 @@ description: >
 
 如果任一条件失败，停止并输出对应错误。
 
-### 2. 运行初始化脚本
+### 2. 运行 labels runtime intent
 
 执行以下命令，完成整套 label 初始化流程：
 
 ```bash
-bash .agents/skills/init-labels/scripts/init-labels.sh
+agent-infra-internal platform-metadata init-labels
 ```
 
-脚本与 `.agents/rules/label-milestone-setup.md` 共同负责：
+runtime intent 与 `.agents/rules/label-milestone-setup.md` 共同负责：
 - 读取配置的 `labels.in` 映射并保留无关 label
-- 选择 provider 叶子，或返回明确的 no-op/degraded 结果
+- 选择平台能力，或返回明确的 no-op/degraded 结果
 - 创建或更新标准 label 集合并输出最终摘要
 - 输出最终执行摘要
 
@@ -69,8 +69,8 @@ bash .agents/skills/init-labels/scripts/init-labels.sh
 #### 4.3 写入配置并创建 label
 
 1. 将最终映射写入 `.agents/.airc.json` 的 `labels.in` 字段。
-2. 执行 `bash .agents/skills/init-labels/scripts/init-labels.sh`，为每个映射 key 创建或更新 `in: {key}` label。
-3. 询问用户确认后，再使用 `--cleanup-stale-in` 重新执行脚本，清理不在最终映射中的旧 `in:` label。
+2. 执行 `agent-infra-internal platform-metadata init-labels`，为每个映射 key 创建或更新 `in: {key}` label。
+3. 询问用户确认后，再使用 `--cleanup-stale-in` 重新执行 intent，清理不在最终映射中的旧 `in:` label。
 
 ### 5. 输出与行为保证
 
@@ -100,7 +100,7 @@ bash .agents/skills/init-labels/scripts/init-labels.sh
 
 ## 错误处理
 
-- provider 能力不可用：如实报告脚本的 `degraded` 或 `no-op` 结果，不得声称远端已变更。
-- provider 认证或仓库访问失败：如实报告脚本的非零退出状态和诊断输出；不得声称远端已变更。
+- 平台能力不可用：如实报告 runtime 的 `degraded` 或 `no-op` 结果，不得声称远端已变更。
+- 平台认证或仓库访问失败：如实报告 runtime 的非零退出状态和诊断输出；不得声称远端已变更。
 - 权限不足：提示 "No permission to manage labels in this repository"
 - API 限流：提示 "platform API rate limit reached, please retry later"

package/templates/.agents/skills/init-milestones/SKILL.en.md

@@ -19,20 +19,18 @@ Confirm that:
 
 If any prerequisite fails, stop and report the matching error.
 
-### 2. Run the bootstrap script
+### 2. Run the milestones runtime intent
 
 Execute the complete milestone initialization flow with:
 
 ```bash
-bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
+agent-infra-internal platform-metadata init-milestones $ARGUMENTS
 ```
 
-The script and `.agents/rules/label-milestone-setup.md` are responsible for:
-- Creating and cleaning up a temporary workspace
-- Detecting whether `--history` was requested
-- Scanning all `v*` Git tags, selecting the highest valid version by SemVer precedence, and using compatibility default `0.1.0` when none is valid, without reading ecosystem manifests
-- Letting the provider leaf list and write current milestones
-- Building the desired milestone set and creating only the missing titles
+The runtime intent and `.agents/rules/label-milestone-setup.md` are responsible for:
+- Receiving the `--history` request and planning the desired milestones
+- Applying the established baseline, history, state, and title-idempotency contract
+- Letting runtime/provider code list and write current milestones
 - Printing the final execution summary
 
 ### 3. Standard milestone definitions
@@ -78,8 +76,8 @@ Next step - initialize labels (optional):
 
 ## Error Handling
 
-- Provider capability, authentication, or repository access failure: report the script's non-zero exit status and diagnostic output; do not claim remote changes.
-- Version detection failed: prompt "Unable to determine current version baseline"
-- No valid SemVer `v*` tags found in `--history` mode: prompt "No valid SemVer history tags found matching v*; only standard milestones will be created"
+- Platform capability, authentication, or repository access failure: report the runtime's non-zero exit status and diagnostic output; do not claim remote changes.
+- Version detection failed: report the runtime's version-baseline error
+- No valid SemVer `v*` tags found in `--history` mode: report the runtime's history diagnostic
 - Permission error: prompt "No permission to manage milestones in this repository"
 - API rate limit: prompt "platform API rate limit reached, please retry later"

package/templates/.agents/skills/init-milestones/SKILL.zh-CN.md

@@ -19,20 +19,18 @@ description: >
 
 如果任一条件失败，停止并输出对应错误。
 
-### 2. 运行初始化脚本
+### 2. 运行 milestones runtime intent
 
 执行以下命令，完成整套里程碑初始化流程：
 
 ```bash
-bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
+agent-infra-internal platform-metadata init-milestones $ARGUMENTS
 ```
 
-脚本与 `.agents/rules/label-milestone-setup.md` 共同负责：
-- 创建并清理临时工作目录
-- 检测是否传入 `--history`
-- 扫描所有 `v*` Git tag，按 SemVer precedence 选择最高合法版本；没有合法版本时使用兼容默认值 `0.1.0`，且不读取任何生态 manifest
-- 由 provider 叶子读取并写入当前里程碑
-- 构建目标里程碑集合，并且只创建缺失标题
+runtime intent 与 `.agents/rules/label-milestone-setup.md` 共同负责：
+- 接收 `--history` 请求并规划目标里程碑
+- 按既定基线、history、状态和标题幂等契约生成结果
+- 由 runtime/provider 读取并写入当前里程碑
 - 输出最终执行摘要
 
 ### 3. 标准里程碑定义
@@ -78,8 +76,8 @@ bash .agents/skills/init-milestones/scripts/init-milestones.sh "$ARGUMENTS"
 
 ## 错误处理
 
-- provider 能力、认证或仓库访问失败：如实报告脚本的非零退出状态和诊断输出；不得声称远端已变更。
-- 版本解析失败：提示 "Unable to determine current version baseline"
-- `--history` 模式下未找到合法 SemVer `v*` git tags：提示 "No valid SemVer history tags found matching v*; only standard milestones will be created"
+- 平台能力、认证或仓库访问失败：如实报告 runtime 的非零退出状态和诊断输出；不得声称远端已变更。
+- 版本解析失败：报告 runtime 返回的版本基线错误
+- `--history` 模式下未找到合法 SemVer `v*` git tags：报告 runtime 返回的 history 诊断
 - 权限不足：提示 "No permission to manage milestones in this repository"
 - API 限流：提示 "platform API rate limit reached, please retry later"

package/templates/.agents/skills/plan-task/SKILL.en.md

@@ -13,6 +13,11 @@ If the entry operands contain `--orchestrated`, bind `{execution-flag}` to `--or
 
 ## Boundary / Critical Rules
 
+### Persisted Report Evidence
+
+Before generating the plan report, read `.agents/rules/evidence-reporting.md`. Record the command, target scope, status or structured result, actual result, and uncovered parts for state checks and verification; include decisive raw excerpts only for failures, blocking conditions, or disputes.
+
+- When evaluating candidate qualification or `HD-N`, read `.agents/rules/decision-qualification.md`, audit normalized task constraints/candidates, and record the five qualification-audit tables in the plan artifact; unknown or unconfirmed constraints must not automatically exclude a candidate
 - This skill only outputs a technical plan document (`plan.md` or `plan-r{N}.md`) and does not modify any business code
 - This is a **mandatory human review checkpoint**; do not automatically proceed to implementation
 - Before generating task or lifecycle Markdown that will be synchronized to an Issue, read `.agents/rules/sync-content-generation.md` and apply its producer-side constraints; the sync path does not parse or rewrite the body
@@ -25,7 +30,7 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 
 After loading workflow / skill / rules instructions, and before any task-state judgment or user-visible conclusion, run the state check first. Reading instruction files does not count as an external-state action or conclusion.
 
-Run these commands and paste the raw output into this round's `## State Check` section:
+Run these commands and record the task/artifact scope, key result, and uncovered parts in this round's `## State Check` section; do not paste complete directory listings or task tails on normal success. Retain decisive raw lines only for failures, blocking conditions, identity mismatches, or disputes:
 
 ```bash
 agent-infra-internal task-snapshot {task-id} --format text
@@ -103,6 +108,14 @@ When this round introduces a new key design decision, first run `agent-infra-int
 
 ### 6. Output Plan Document
 
+Before writing this round's `{plan-artifact}`, create the controlled report skeleton:
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family plan --artifact {plan-artifact} --locale en
+```
+
+The skeleton contains identity metadata, stable section markers, and required headings only; real plan content is required before the completion gate can pass. If the finalizer returns one provably safe structural error, call `task-artifact {task-id} repair --family plan --artifact {plan-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`, then rerun the same finalizer.
+
 Create `.agents/workspace/active/{task-id}/{plan-artifact}`.
 
 ### 7. Update Task Status

package/templates/.agents/skills/plan-task/SKILL.zh-CN.md

@@ -13,6 +13,11 @@ description: >
 
 ## 行为边界 / 关键规则
 
+### 持久化报告证据
+
+生成方案报告时，先读取 `.agents/rules/evidence-reporting.md`。状态核对和验证记录命令、目标范围、状态/结构化结果、实际结果和未覆盖部分；失败、阻塞或争议才附决定性原文摘录。
+
+- 涉及候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，基于 task.md 规范化约束/候选完成资格审计，并在方案产物记录五张资格审计表；不得把来源不明或未确认约束自动升级为排除条件
 - 本技能仅产出技术方案文档（`plan.md` 或 `plan-r{N}.md`）—— 不修改任何业务代码
 - 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；同步端不解析或改写正文
 - 这是一个**强制性的人工审查检查点** —— 不要自动进入实现阶段
@@ -25,7 +30,7 @@ description: >
 
 在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
 
-运行以下命令，并把原文粘贴到本轮产物的 `## 状态核对` 段：
+运行以下命令，并在本轮产物的 `## 状态核对` 段记录任务/产物范围、关键结果和未覆盖部分；正常成功不粘贴完整目录清单或 `task.md` 尾部。失败、阻塞、身份不一致或争议时，附决定性原文行：
 
 ```bash
 agent-infra-internal task-snapshot {task-id} --format text
@@ -83,6 +88,8 @@ agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-t
 
 ### 5. 设计技术方案
 
+方案必须按 `.agents/rules/decision-qualification.md` 复核规范化约束和候选，并在方案产物保留五张资格审计表及真实上游关系；来源不明或未人工确认的约束不得自动排除候选。
+
 遵循 `.agents/workflows/feature-development.yaml` 中的 `technical-design` 步骤：
 
 **必要任务**：
@@ -104,6 +111,14 @@ agent-infra-internal task-event {task-id} plan.started --agent {standard-agent-t
 
 ### 6. 输出计划文档
 
+在首次写入本轮 `{plan-artifact}` 前，先创建受控报告骨架：
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family plan --artifact {plan-artifact}
+```
+
+骨架只包含身份元数据、稳定 section marker 和必需标题；必须填入真实方案内容后才能通过完成门禁。finalizer 返回可证明的单个结构错误时，使用其 SHA 和 semantic digest 调用 `task-artifact {task-id} repair --family plan --artifact {plan-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`，然后完整重跑 finalizer。
+
 创建 `.agents/workspace/active/{task-id}/{plan-artifact}`。
 
 ### 7. 更新任务状态

package/templates/.agents/skills/plan-task/config/verify.en.json

@@ -17,25 +17,15 @@
     },
     "artifact": {
       "file_pattern": "plan.md|plan-r{N}.md",
-      "required_sections": [
-        "Problem Understanding",
-        "Constraints",
-        "Option Comparison",
-        "Technical Approach",
-        "Implementation Steps",
-        "File List",
-        "Verification Strategy",
-        "State Check"
-      ],
-      "required_patterns": [
-        "^\\$ "
-      ]
+      "schema": "plan"
     },
     "activity-log": {
       "expected_action_pattern": "(Plan Task|Technical Design) \\(Round \\d+\\)"
     },
     "review-ledger": {
-      "stage_scope": ["analysis"]
+      "stage_scope": [
+        "analysis"
+      ]
     },
     "platform-sync": {
       "when": "issue_number_exists",

package/templates/.agents/skills/plan-task/config/verify.zh-CN.json

@@ -17,25 +17,15 @@
     },
     "artifact": {
       "file_pattern": "plan.md|plan-r{N}.md",
-      "required_sections": [
-        "问题理解",
-        "约束条件",
-        "方案对比",
-        "技术方法",
-        "实施步骤",
-        "文件清单",
-        "验证策略",
-        "状态核对"
-      ],
-      "required_patterns": [
-        "^\\$ "
-      ]
+      "schema": "plan"
     },
     "activity-log": {
       "expected_action_pattern": "(Plan Task|Technical Design) \\(Round \\d+\\)"
     },
     "review-ledger": {
-      "stage_scope": ["analysis"]
+      "stage_scope": [
+        "analysis"
+      ]
     },
     "platform-sync": {
       "when": "issue_number_exists",

package/templates/.agents/skills/release/SKILL.en.md

@@ -19,15 +19,19 @@ Require one canonical SemVer `{version}` and a satisfied entropy checkpoint.
 agent-infra-internal release-workflow inspect {version}
 ```
 
-Run prepare and inspect again only when the snapshot is not prepared. Reuse prepared or partially published facts. Unknown state is blocked.
+Preserve and present the complete non-empty stdout. Run prepare and inspect again only when the snapshot is not prepared. Reuse prepared or partially published facts. Unknown state is blocked.
 
 ```bash
 agent-infra-internal release-workflow prepare {version} --entropy-report {path}
 ```
 
+Present the prepare `status`, `error`, and `operations`, including milestone closure and creation of the next planning milestones. Stop on `failed` or `blocked`; do not request publish authorization. Continue only after a successful prepare and a fresh inspect.
+
+Inspect again after prepare.
+
 ## 3. Present and Confirm
 
-Present the latest snapshot. Only an unambiguous affirmative reply for that snapshot in the current session authorizes publishing. A denial, adjustment, question, ambiguity, interruption, or changed snapshot stops the write and requires a new preview.
+Present the complete latest snapshot JSON, including every channel state. Only an unambiguous affirmative reply for that snapshot in the current session authorizes publishing. A denial, adjustment, question, ambiguity, interruption, or changed snapshot stops the write and requires a new preview.
 
 ## 4. Publish and Reinspect
 
@@ -35,7 +39,7 @@ Present the latest snapshot. Only an unambiguous affirmative reply for that snap
 agent-infra-internal release-workflow publish {version}
 ```
 
-Push refs normally, preserve partial success for replay, never force push, and inspect again after the operation.
+Push refs normally, preserve partial success for replay, never force push, and inspect again after the operation. Explicitly list any incomplete platform release, npm, Homebrew, or smoke state; a successful Git ref push is not a complete release.
 
 ## 5. Report Facts
 

package/templates/.agents/skills/release/SKILL.zh-CN.md

@@ -19,15 +19,19 @@ description: >
 agent-infra-internal release-workflow inspect {version}
 ```
 
-未 prepared 时执行 prepare 并重新 inspect；已准备或部分发布时复用当前事实。unknown 必须 blocked。
+保留并展示该命令的完整非空 stdout。未 prepared 时执行 prepare 并重新 inspect；已准备或部分发布时复用当前事实。unknown 必须 blocked。
 
 ```bash
 agent-infra-internal release-workflow prepare {version} --entropy-report {path}
 ```
 
+展示 prepare 的 `status`、`error` 和 `operations`，包括里程碑关闭与后续里程碑创建结果。`failed` 或 `blocked` 时停止，不得请求发布授权；只有 prepare 成功且重新 inspect 得到的最新快照才可继续。
+
+prepare 后必须重新 inspect。
+
 ## 3. 展示快照并确认
 
-展示最新 snapshot。只有当前会话中针对该快照的无歧义明确肯定答复才授权发布；否定、调整、疑问、歧义或中断均停止。快照变化后重新确认。
+展示最新 snapshot 的完整 JSON，包括所有渠道状态。只有当前会话中针对该快照的无歧义明确肯定答复才授权发布；否定、调整、疑问、歧义或中断均停止。快照变化后重新确认。
 
 ## 4. 发布并复核
 
@@ -35,7 +39,7 @@ agent-infra-internal release-workflow prepare {version} --entropy-report {path}
 agent-infra-internal release-workflow publish {version}
 ```
 
-逐 ref 普通 push；部分成功可重放，禁止 force push。操作后重新 inspect。
+逐 ref 普通 push；部分成功可重放，禁止 force push。操作后重新 inspect，并明确列出仍未完成的平台 Release、npm、Homebrew 或 smoke 项。
 
 ## 5. 输出事实摘要
 

package/templates/.agents/skills/review-analysis/SKILL.en.md

@@ -15,6 +15,11 @@ Review the latest analysis artifact and produce `review-analysis.md` or `review-
 
 ## Boundary / Critical Rules
 
+### Persisted Report Evidence
+
+Before generating the review report, read `.agents/rules/evidence-reporting.md`. Normal inspection records the command, scope, structured result, actual conclusion, and uncovered parts; findings, blocking conditions, or disputes retain reproducible locations and decisive excerpts, while identity fields remain exact.
+
+- When reviewing candidate qualification or `HD-N`, read `.agents/rules/decision-qualification.md` and check the five qualification-audit tables, digests, QCR, and upstream relations; do not treat a process label as identity authentication
 - This skill only reviews analysis artifacts and writes a report; it does not modify product code.
 - Before generating task or lifecycle Markdown that will be synchronized to an Issue, read `.agents/rules/sync-content-generation.md` and apply its producer-side constraints; the sync path does not parse or rewrite the body
 - After executing this skill, you **must** immediately update task.md.
@@ -25,7 +30,7 @@ Version stamp rule: when creating or updating `task.md` frontmatter, read `.agen
 
 After loading workflow / skill / rules instructions, and before any task-state judgment or user-visible conclusion, run the state check first.
 
-Run these commands and paste the raw output into this round's `## State Check` section:
+Run these commands and record the task/artifact scope, key result, and uncovered parts in this round's `## State Check` section; do not paste complete directory listings or task tails on normal success. Retain decisive raw lines only for failures, blocking conditions, identity mismatches, or disputes:
 
 ```bash
 agent-infra-internal task-snapshot {task-id} --format text
@@ -64,6 +69,14 @@ Check requirement completeness, risks, affected scope, open questions, and effor
 
 ### 5. Write Review Report
 
+Before writing this round's `{review-artifact}`, create the controlled review skeleton:
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family review-analysis --artifact {review-artifact} --locale en
+```
+
+The skeleton contains identity metadata, stable section markers, and required headings only; complete review content is required before summary finalization. If structural finalization returns one provably safe error, call `task-artifact {task-id} repair --family review-analysis --artifact {review-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`, then rerun the original finalizer.
+
 Create `.agents/workspace/active/{task-id}/{review-artifact}`.
 
 > Read `reference/report-template.md` before writing the report.

package/templates/.agents/skills/review-analysis/SKILL.zh-CN.md

@@ -15,6 +15,11 @@ description: >
 
 ## 行为边界 / 关键规则
 
+### 持久化报告证据
+
+生成审查报告时，先读取 `.agents/rules/evidence-reporting.md`。正常检视记录命令、范围、结构化结果、实际结论和未覆盖部分；finding、阻塞或争议保留可复现位置与决定性摘录，身份字段必须精确保留。
+
+- 审查候选资格或 `HD-N` 判断时，先读取 `.agents/rules/decision-qualification.md`，逐项复核产物中的五张资格审计表、digest、QCR 和上游关系；不得把流程标签当作身份认证
 - 本技能只审查分析产物并写报告，不修改业务代码
 - 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取 `.agents/rules/sync-content-generation.md` 并遵循其中的生成端约束；同步端不解析或改写正文
 - 执行本技能后，你**必须**立即更新 task.md
@@ -25,7 +30,7 @@ description: >
 
 在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
 
-运行以下命令，并把原文粘贴到本轮产物的 `## 状态核对` 段：
+运行以下命令，并在本轮产物的 `## 状态核对` 段记录任务/产物范围、关键结果和未覆盖部分；正常成功不粘贴完整目录清单或 `task.md` 尾部。失败、阻塞、身份不一致或争议时，附决定性原文行：
 
 ```bash
 agent-infra-internal task-snapshot {task-id} --format text
@@ -67,6 +72,14 @@ agent-infra-internal task-snapshot {task-id} --format text
 
 ### 5. 编写审查报告
 
+在首次写入本轮 `{review-artifact}` 前，先创建受控审查骨架：
+
+```bash
+agent-infra-internal task-artifact {task-id} init --family review-analysis --artifact {review-artifact}
+```
+
+骨架不生成审查结论、发现或计数；完成审查内容后才能进入 summary finalizer。结构 finalizer 返回可证明的单个错误时，使用其 SHA 和 semantic digest 调用 `task-artifact {task-id} repair --family review-analysis --artifact {review-artifact} --expected-sha256 {artifact-sha256} --expected-semantic-digest {semantic-digest}`，再重跑原 finalizer。
+
 创建 `.agents/workspace/active/{task-id}/{review-artifact}`。
 
 > 报告格式见 `reference/report-template.md`。写报告前先读取 `reference/report-template.md`。

package/templates/.agents/skills/review-analysis/config/verify.en.json

@@ -17,24 +17,7 @@
     },
     "artifact": {
       "file_pattern": "review-analysis.md|review-analysis-r{N}.md",
-      "required_sections": [
-        "Review Summary",
-        "Review Coverage Declaration",
-        "Requirement Analysis Coverage",
-        "Traceability Matrix",
-        "Findings",
-        "Non-blocking Advisories",
-        "Manual Validation Items",
-        "Conclusion and Recommendations",
-        "State Check",
-        "Evidence",
-        "Self-Doubt",
-        "Review Disagreement Ledger Writeback"
-      ],
-      "required_patterns": [
-        "^### Approval Decision$",
-        "^\\$ "
-      ]
+      "schema": "review-analysis"
     },
     "decision-details": {},
     "review-summary": {

package/templates/.agents/skills/review-analysis/config/verify.zh-CN.json

@@ -17,24 +17,7 @@
     },
     "artifact": {
       "file_pattern": "review-analysis.md|review-analysis-r{N}.md",
-      "required_sections": [
-        "审查摘要",
-        "检视覆盖声明",
-        "需求分析专项覆盖",
-        "追踪矩阵",
-        "问题清单",
-        "非阻塞建议",
-        "人工校验项",
-        "结论与建议",
-        "状态核对",
-        "证据原文",
-        "自我质疑",
-        "审查分歧账本回写"
-      ],
-      "required_patterns": [
-        "^### 审查决定$",
-        "^\\$ "
-      ]
+      "schema": "review-analysis"
     },
     "decision-details": {},
     "review-summary": {

package/templates/.agents/skills/review-analysis/reference/report-template.en.md

@@ -1,5 +1,7 @@
 # Review Report Template
 
+> Before writing this report, use `task-artifact init --family review-analysis` to create the skeleton and preserve every `artifact-section` marker; the skeleton contains no review conclusion.
+
 Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`.
 
 ## Output Template
@@ -12,11 +14,31 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 - **Review Input**:
   - `{analysis-artifact}` (the highest-round requirement-analysis artifact actually reviewed, e.g. `analysis-r2.md`; leave blank if it cannot be reliably determined)
 
-## State Check
+## Review Summary
 
-> Paste the raw state-check command output; each command starts with `$ `.
+## Qualification Audit Review
 
-## Review Summary
+> Use `.agents/rules/decision-qualification.md` to review the five tables: constraint dependencies, candidate qualification, classification results, upstream relations, and dependency snapshot.
+
+### Constraint Dependencies
+| constraint_id | constraint_digest | role | evidence |
+| --- | --- | --- | --- |
+
+### Candidate Qualification
+| candidate_id | status | impact | constraint_ids | evidence |
+| --- | --- | --- | --- | --- |
+
+### Classification Results
+| decision_id | classification | evidence |
+| --- | --- | --- |
+
+### Upstream Relations
+| upstream_family | upstream_artifact | upstream_round | upstream_sha256 | relation |
+| --- | --- | --- | --- | --- |
+
+### Dependency Snapshot
+| task_input_digest | non_constraint_input_digest | upstream_artifact_digest |
+| --- | --- | --- |
 
 - **Reviewer**: {reviewer-name}
 - **Review Time**: {timestamp}
@@ -24,7 +46,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 - **Overall Verdict**: {Approved / Changes Requested / Rejected}
 - **Findings (AI-actionable)**: {unresolved-blockers} blockers, {unresolved-major} majors, {unresolved-minor} minors / **Manual validation**: 0
 
-## Review Coverage Declaration
+## Inspection Coverage
 
 | pass_id | scope | evidence | result | gaps_or_assumptions |
 |---------|-------|----------|--------|---------------------|
@@ -34,7 +56,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 |---------|------------------|--------|--------|
 | {registry token} | {trigger or non-trigger evidence} | {yes / no / not-applicable} | {lens result} |
 
-## Requirement Analysis Coverage
+## Requirements Analysis Coverage
 
 | perspective_id | applicability | reviewed_scope | evidence | result_or_gap |
 |----------------|---------------|----------------|----------|---------------|
@@ -92,7 +114,7 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 **File**: `{file-path}:{line-number}`
 **Suggestion**: {improvement suggestion}
 
-## Non-blocking Advisories
+## Non-blocking Suggestions
 
 > Record only future optimizations that do not affect the current artifact's completeness, correctness, or acceptance. Advisories do not enter the disagreement ledger, finding counts, or verdict.
 
@@ -111,27 +133,42 @@ Use this template when writing `review-analysis.md` or `review-analysis-r{N}.md`
 > If this round has no Manual validation items, keep the section heading and write "None".
 
 
-## Review Disagreement Ledger Writeback
+## Conclusion and Recommendation
 
-> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `AN-N` and validates transitions; do not edit task.md table rows.
-> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
+### Approval Decision
+- [ ] Approved
+- [ ] Changes Requested
+- [ ] Rejected
+
+### Next Steps
+{recommended next step}
+
+## State Check
 
-## Evidence
+> Record the state-check command, review scope, key result, and uncovered parts; each command starts with `$ `.
+> Follow `.agents/rules/evidence-reporting.md`: record review scope, key result, and uncovered parts; do not paste complete successful stdout.
 
-> Pair each "I verified X" claim with the corresponding raw tool output; the gate only checks that this section exists and at least one `$ ` line is present. Every Blocker must be backed by a reproducible command (rg/grep/sed/nl) and its raw output; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
+## Raw Evidence
+
+> Follow `.agents/rules/evidence-reporting.md`: pair each claim with a `$ ` command and proportionate result summary; Blockers, failures, blocking conditions, or disputes require a reproducible command, exact location, and decisive excerpt; a judgment that cannot be reproduced must be downgraded or moved to Self-Doubt.
 
 - Claim: {verified claim}
 ```text
 $ {command}
-{raw output}
+{result summary or decisive excerpt}
 ```
 
-## Self-Doubt
+## Self-critique
 
 > Explicitly declare conclusions, inferences, and assumptions in this review that were **not directly verified**; downstream can rebut them on this basis. Write "None" if there are none.
 
 - {an unverified conclusion or inference; note why it was not verified and the impact if it is overturned}
 
+## Review Disagreement Ledger Write-back
+
+> Record the structured intents to submit: use `task-ledger finding-upsert` for new findings and `finding-review` for prior responses. The core allocates `AN-N` and validates transitions; do not edit task.md table rows.
+> Every finding escalated to `needs-human-decision` must include a self-contained detail block per `.agents/rules/human-decision-context.md`, with evidence pointing to that stable anchor.
+
 ## Highlights
 
 - {what went well}
@@ -140,14 +177,4 @@ $ {command}
 
 - [ ] Implementation matches the technical plan
 - [ ] No unintended scope expansion
-
-## Conclusion and Recommendation
-
-### Approval Decision
-- [ ] Approved
-- [ ] Changes Requested
-- [ ] Rejected
-
-### Next Steps
-{recommended next step}
 ```