@xulthekl/team-flow 0.23.0 → 0.24.0

package/skills/build-executor/references/execution-modes.md

@@ -7,14 +7,14 @@
 For `full`/`hotfix`, generate proposed waves from the approved contract, then use the recommendation as a decision aid:
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf execution recommend <change-dir> \
+npx --yes --package @xulthekl/team-flow@0.24.0 tf execution recommend <change-dir> \
   --wave <wave-id>:<parallel|serial>:<task,...>[:<depends-on,...>] --json
 # Show every available mode, the observed facts, and the recommendation to the user.
-npx --yes --package @xulthekl/team-flow@0.23.0 tf execution plan <change-dir> \
+npx --yes --package @xulthekl/team-flow@0.24.0 tf execution plan <change-dir> \
   --mode <selected-mode> --confirm --reason "user-selected execution mode" \
   --wave <wave-id>:<parallel|serial>:<task,...>[:<depends-on,...>]
 # Add --acknowledge-recommendation when the selection differs from the recommendation.
-npx --yes --package @xulthekl/team-flow@0.23.0 tf execution show <change-dir> --json
+npx --yes --package @xulthekl/team-flow@0.24.0 tf execution show <change-dir> --json
 ```
 
 The optional fourth `--wave` segment names prerequisite wave IDs. `execution show --json` reports `current`, plus each wave's `depends_on`, `receipt`, `blockers`, `retryable`, and `eligible` status.
@@ -37,7 +37,7 @@ Dispatch according to the persisted plan, review each planned wave, and run a fi
 3. A `serial` wave dispatches one task at a time in listed order.
 4. After every wave, write a review report, then record one receipt:
    ```bash
-   npx --yes --package @xulthekl/team-flow@0.23.0 tf execution review <change-dir> \
+   npx --yes --package @xulthekl/team-flow@0.24.0 tf execution review <change-dir> \
      --wave <wave-id> --base <sha> --head <sha> --report <review-report-path> --verdict <pass|fail>
    ```
 5. Critical/Important findings require a `fail` receipt, focused repair, re-review, then replacement `pass` receipt.
@@ -66,7 +66,7 @@ Per-task: extract brief → write failing test → confirm failure → implement
 ## Model Selection
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf runtime config --resolve-model <profile>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf runtime config --resolve-model <profile>
 ```
 
 | Profile | Role |
@@ -79,7 +79,7 @@ npx --yes --package @xulthekl/team-flow@0.23.0 tf runtime config --resolve-model
 ## Recovery Checkpoint
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf checkpoint save <change-dir> \
+npx --yes --package @xulthekl/team-flow@0.24.0 tf checkpoint save <change-dir> \
   --task <completed-task-id> --next "<next task>" --completed "<completed work>" \
   --verification "<verification report path>" --review "<review report path>" \
   --risk "<open risk or None>" --commit-start <base-sha> --commit-end <head-sha>

package/skills/build-executor/task-reviewer-prompt.md

@@ -146,7 +146,7 @@ Subagent (general-purpose):
     command for the controller:
 
     ```bash
-    npx --yes --package @xulthekl/team-flow@0.23.0 tf execution review <change-dir> --wave [WAVE_ID] --base [BASE_SHA] --head [HEAD_SHA] --report [REVIEW_REPORT_FILE] --verdict <pass|fail>
+    npx --yes --package @xulthekl/team-flow@0.24.0 tf execution review <change-dir> --wave [WAVE_ID] --base [BASE_SHA] --head [HEAD_SHA] --report [REVIEW_REPORT_FILE] --verdict <pass|fail>
     ```
 
     Use `fail` for any Critical/Important finding. A repair must be re-reviewed

package/skills/code-reviewer/SKILL.md

@@ -16,7 +16,7 @@ Two responsibilities: requesting review (dispatching a reviewer subagent) and re
 1. Get SHAs: `BASE_SHA=$(git rev-parse HEAD~1)` and `HEAD_SHA=$(git rev-parse HEAD)`
 2. Dispatch `general-purpose` subagent using template at `skills/code-reviewer/code-reviewer-prompt.md`
 3. Fill placeholders: `[DESCRIPTION]` (what was built), `[PLAN_OR_REQUIREMENTS]` (contract/spec reference), `[BASE_SHA]`, `[HEAD_SHA]`, `[WAVE_ID]`, and a distinct `[REVIEW_REPORT_FILE]`.
-4. Require the reviewer to write a non-empty persisted review report at `[REVIEW_REPORT_FILE]`, then record that exact path in the wave receipt: `npx --yes --package @xulthekl/team-flow@0.23.0 tf execution review <change-dir> --wave <id> --base <sha> --head <sha> --report <review-report-path> --verdict <pass|fail>`.
+4. Require the reviewer to write a non-empty persisted review report at `[REVIEW_REPORT_FILE]`, then record that exact path in the wave receipt: `npx --yes --package @xulthekl/team-flow@0.24.0 tf execution review <change-dir> --wave <id> --base <sha> --head <sha> --report <review-report-path> --verdict <pass|fail>`.
 5. Act on feedback: Critical/Important findings require a `fail` receipt, focused repair, re-review, and replacement `pass` receipt before a dependent wave or closing can proceed. Note Minor for later, push back with reasoning if reviewer is wrong.
 
 ### Minimality And Scope
@@ -76,7 +76,7 @@ Suggestion breaks existing functionality, reviewer lacks context, violates YAGNI
 | Performative agreement | State requirement or just act |
 | Blind implementation | Verify against codebase first |
 | Batch without testing | One at a time, test each |
-| Proceeding without a wave receipt | Record `pass`/`fail` via `npx --yes --package @xulthekl/team-flow@0.23.0 tf execution review` before the next dependent wave |
+| Proceeding without a wave receipt | Record `pass`/`fail` via `npx --yes --package @xulthekl/team-flow@0.24.0 tf execution review` before the next dependent wave |
 | Assuming reviewer is right | Check if breaks things |
 | Avoiding pushback | Technical correctness > comfort |
 | Partial implementation | Clarify all items first |

package/skills/code-reviewer/code-reviewer-prompt.md

@@ -93,7 +93,7 @@ Subagent (general-purpose):
     report path. End with the exact receipt command:
 
     ```bash
-    npx --yes --package @xulthekl/team-flow@0.23.0 tf execution review <change-dir> --wave [WAVE_ID] --base [BASE_SHA] --head [HEAD_SHA] --report [REVIEW_REPORT_FILE] --verdict <pass|fail>
+    npx --yes --package @xulthekl/team-flow@0.24.0 tf execution review <change-dir> --wave [WAVE_ID] --base [BASE_SHA] --head [HEAD_SHA] --report [REVIEW_REPORT_FILE] --verdict <pass|fail>
     ```
 
     Use `fail` when any Critical or Important finding remains. A repair needs

package/skills/contract-builder/SKILL.md

@@ -5,9 +5,9 @@ description: Convert approved planning artifacts into an execution contract. Inv
 
 # Contract Builder
 
-Converts planning artifacts into a single execution handshake: `execution-contract.md`. Load the baseline with `npx --yes --package @xulthekl/team-flow@0.23.0 tf runtime asset read templates/execution-contract.md`.
+Converts planning artifacts into a single execution handshake: `execution-contract.md`. Load the baseline with `npx --yes --package @xulthekl/team-flow@0.24.0 tf runtime asset read templates/execution-contract.md`.
 
-Read before generating: `proposal.md`, `specs/`, `design.md`, `tasks.md`, then load `docs/artifact-contract.md` with `npx --yes --package @xulthekl/team-flow@0.23.0 tf runtime asset read docs/artifact-contract.md`.
+Read before generating: `proposal.md`, `specs/`, `design.md`, `tasks.md`, then load `docs/artifact-contract.md` with `npx --yes --package @xulthekl/team-flow@0.24.0 tf runtime asset read docs/artifact-contract.md`.
 
 **Architecture Design Outputs (v0.9 §26)**: 若 `architecture/` 目录存在，同时读取 `architecture/architecture.md` / `database.md` / `api.md`，作为执行契约的架构约束补充输入——确保 execution-contract.md 的 Implementation Constraints 段包含架构设计的关键约束（聚合边界/CQRS 分流/API 契约/schema 变更）。`architecture/` 不存在时跳过。
 
@@ -38,8 +38,8 @@ Must make obvious: approved behavior, out-of-scope, constraints, batches, test o
 
 After drafting: summarize handoff rules, identify ambiguity, flag unmapped requirements, ask user to approve explicitly. After approval:
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_3_result "approved: <summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_3_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_3_result "approved: <summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_3_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 DP-3 is a hard gate — no implementation without this record.
 
@@ -60,9 +60,9 @@ Generate minimal contract: Intent Lock (one sentence), Task List (numbered), App
 
 ## Post-Generation
 
-Run `npx --yes --package @xulthekl/team-flow@0.23.0 tf state init <change-dir>` to create `.team-flow.yaml` with hashes.
+Run `npx --yes --package @xulthekl/team-flow@0.24.0 tf state init <change-dir>` to create `.team-flow.yaml` with hashes.
 
-For hotfix, after writing the minimal contract, run `npx --yes --package @xulthekl/team-flow@0.23.0 tf state init <change-dir>` or `npx --yes --package @xulthekl/team-flow@0.23.0 tf state rebuild <change-dir>` so `contract_hash` is recorded. DP-3 remains mandatory before build.
+For hotfix, after writing the minimal contract, run `npx --yes --package @xulthekl/team-flow@0.24.0 tf state init <change-dir>` or `npx --yes --package @xulthekl/team-flow@0.24.0 tf state rebuild <change-dir>` so `contract_hash` is recorded. DP-3 remains mandatory before build.
 
 ## Exception Handling
 

package/skills/need-explorer/SKILL.md

@@ -41,8 +41,8 @@ Restate what you heard: "Here's what I'm hearing: [problem, scope, non-goals, su
 
 After user confirms the summary:
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_1_result "confirmed: <one-line summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_1_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_1_result "confirmed: <one-line summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_1_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 DP-1 confirms scope, non-goals, and success criteria before artifact creation.
 

package/skills/release-archivist/SKILL.md

@@ -72,12 +72,12 @@ If an `e2e/` suite exists for the change, fold its report into verification (see
 - Scope added without artifact updates?
 - Unresolved blockers or known risks?
 - Delta specs exist that need merging?
-- Run `npx --yes --package @xulthekl/team-flow@0.23.0 tf audit <change-dir>` — include `decision-point-audit.md` in archive
+- Run `npx --yes --package @xulthekl/team-flow@0.24.0 tf audit <change-dir>` — include `decision-point-audit.md` in archive
 
 ### DP-6 (Verification Outcome)
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_6_result "<pass|conditional|fail>: <summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_6_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_6_result "<pass|conditional|fail>: <summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_6_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 If FAIL, do NOT proceed to DP-7. Route back or ask about abandonment.
 
@@ -85,13 +85,13 @@ After recording a PASS outcome, also record it as the verification gate so the
 `executing → closing` transition is allowed (the guard accepts either
 `test_result: pass` or a `dp_6_result` starting with `pass`):
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> test_result pass
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> test_result pass
 ```
 
 ### DP-7 (Archive Confirmation)
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_7_result "confirmed: <archive summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_7_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_7_result "confirmed: <archive summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_7_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 Verify DP-0 through DP-6 are recorded before DP-7.
 
@@ -101,14 +101,14 @@ If implementation diverged from the contract, return to `bridging` before closur
 
 ## Post-Verification
 
-Run `npx --yes --package @xulthekl/team-flow@0.23.0 tf state transition <change-dir> closing`. If delta specs exist, route to `spec-merger`.
+Run `npx --yes --package @xulthekl/team-flow@0.24.0 tf state transition <change-dir> closing`. If delta specs exist, route to `spec-merger`.
 
 ### Architecture Merge (v0.10 §28-§31) — MUST run first
 
 Merge change-level architecture artifacts to the global `docs/architecture/` baseline **before** any other post-verification step:
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf arch-merge <change-dir>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf arch-merge <change-dir>
 ```
 
 This merges `architecture/{architecture,database,api}.md` and `architecture/sql/` into the global architecture docs. Skip silently when `architecture/` does not exist (architecture-design was `skipped`).
@@ -120,7 +120,7 @@ This merges `architecture/{architecture,database,api}.md` and `architecture/sql/
 After `arch-merge` completes, run prototype-sync to merge UX deltas back to the global prototype:
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf prototype-sync <change-dir>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf prototype-sync <change-dir>
 ```
 
 **Write-back order (mandatory)**: `arch-merge` → `prototype-sync` → `compound promotion` must be executed **sequentially** within the same change closing. Do not run them in parallel — the global `docs/architecture/` and `prototype/` must not be in a half-updated state when the next change grounds on them.
@@ -132,7 +132,7 @@ If `prototype-sync` reports conflicts, list them in the closing summary and flag
 During closing, promote change-level learnings to the global solutions library:
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf solutions promote <change-dir>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf solutions promote <change-dir>
 ```
 
 This checks `specs/<cap>/learnings.md` for entries meeting promotion criteria:
@@ -152,7 +152,7 @@ Before finalizing the closing, check if this change produced any learnable momen
 
 If any of the above occurred, capture the learning:
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf solutions capture \
+npx --yes --package @xulthekl/team-flow@0.24.0 tf solutions capture \
   --phase cross-phase --domain <domain> --type pitfall \
   --severity medium --summary "<what happened and how to prevent it>"
 ```
@@ -174,6 +174,6 @@ Verify files exist and are non-empty, run `node --check` on code files, skip 5-s
 ## Exception Handling
 
 - **Parse failures**: Report exact file and section
-- **Missing files**: If audit can't generate, run `npx --yes --package @xulthekl/team-flow@0.23.0 tf audit` manually
+- **Missing files**: If audit can't generate, run `npx --yes --package @xulthekl/team-flow@0.24.0 tf audit` manually
 - **User interruption**: Re-run verification from the beginning on resume
 - **DP gaps**: Flag missing DPs during DP-6; ask user whether to proceed or return

package/skills/release-archivist/references/closing-procedures.md

@@ -7,7 +7,7 @@
 After `arch-merge` completes, run prototype-sync to merge UX deltas back to the global prototype:
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf prototype-sync <change-dir>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf prototype-sync <change-dir>
 ```
 
 **Write-back order (mandatory)**: `arch-merge` → `prototype-sync` must be executed **sequentially** within the same change closing. Do not run them in parallel.
@@ -19,7 +19,7 @@ If `prototype-sync` reports conflicts, list them in the closing summary and flag
 During closing, promote change-level learnings to the global solutions library:
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf solutions promote <change-dir>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf solutions promote <change-dir>
 ```
 
 Promotion criteria:
@@ -39,7 +39,7 @@ Before finalizing the closing, check if this change produced any learnable momen
 
 If any occurred, capture the learning:
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf solutions capture \
+npx --yes --package @xulthekl/team-flow@0.24.0 tf solutions capture \
   --phase cross-phase --domain <domain> --type pitfall \
   --severity medium --summary "<what happened and how to prevent it>"
 ```
@@ -49,22 +49,22 @@ Advisory — skip silently if no learnable moments detected.
 ## DP-6 (Verification Outcome)
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_6_result "<pass|conditional|fail>: <summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_6_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_6_result "<pass|conditional|fail>: <summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_6_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 
 If FAIL, do NOT proceed to DP-7. Route back or ask about abandonment.
 
 After PASS, also record the verification gate:
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> test_result pass
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> test_result pass
 ```
 
 ## DP-7 (Archive Confirmation)
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_7_result "confirmed: <archive summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_7_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_7_result "confirmed: <archive summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_7_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 
 Verify DP-0 through DP-6 are recorded before DP-7.

package/skills/spec-merger/SKILL.md

@@ -10,7 +10,7 @@ After a change completes, delta specs (ADDED/MODIFIED/REMOVED/RENAMED) must be m
 ## Pre-Flight Checks
 
 ### Conflict Detection
-Run `npx --yes --package @xulthekl/team-flow@0.23.0 tf sync <change-dir>`. If conflicts are detected (same requirement modified by multiple changes), present the conflict list to the user for resolution order.
+Run `npx --yes --package @xulthekl/team-flow@0.24.0 tf sync <change-dir>`. If conflicts are detected (same requirement modified by multiple changes), present the conflict list to the user for resolution order.
 
 ### Abandoned Change Guard
 Check if the change is `abandoned`. If so → STOP: "Abandoned changes cannot be synced. Delta specs are preserved for reference but must not be merged."
@@ -55,7 +55,7 @@ Output sync report table: Capability, ADDED/MODIFIED/REMOVED/RENAMED counts, Sta
 2. Change folder (including deltas) remains for traceability.
 3. Record that merging is complete so the `executing → closing` guard allows closure:
    ```bash
-   npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> spec_merged true
+   npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> spec_merged true
    ```
    (If the change had no delta sections, still set `spec_merged true` — there was nothing to merge.)
 

package/skills/spec-writer/SKILL.md

@@ -55,7 +55,7 @@ Read `docs/solutions/INDEX.md` if it exists. Filter entries where `phase = spec
 
 ## Config Check
 
-Run: `npx --yes --package @xulthekl/team-flow@0.23.0 tf runtime config --get artifacts.order` — generate in configured order (default: proposal → specs → design → tasks). Run with `artifacts.skip` — skip any listed artifacts.
+Run: `npx --yes --package @xulthekl/team-flow@0.24.0 tf runtime config --get artifacts.order` — generate in configured order (default: proposal → specs → design → tasks). Run with `artifacts.skip` — skip any listed artifacts.
 
 ## Artifact Roles
 
@@ -135,8 +135,8 @@ Generate one at a time. Confirm each before next. This prevents scope drift —
 
 Present summary of all 4 artifacts (2-3 sentences each). Ask user for adjustments. After approval:
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_2_result "approved: <summary>"
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state set <change-dir> dp_2_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_2_result "approved: <summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state set <change-dir> dp_2_timestamp $(date -u +%Y-%m-%dT%H:%M:%SZ)
 ```
 
 ## Handoff Rule

package/skills/workflow-bootstrap/SKILL.md

@@ -66,9 +66,19 @@ Do NOT invoke for:
 
 **条件**：如果 B1 侦察发现项目有一定复杂度（≥5 个模块或 ≥10 个源文件），执行此阶段。否则跳过。
 
-**B2 成果物导入（v0.23.0 新增）**：
+**B2 成果物导入（v0.23.0 新增，v0.24.0 模板初始化补强）**：
 
 ```
+Step 0: 目录+模板初始化（v0.24.0 新增）
+  ├── mkdir -p docs/architecture/
+  ├── 从 ${CLAUDE_PLUGIN_ROOT}/skills/architecture-design/templates/ 复制模板：
+  │     architecture.md → docs/architecture/ARCHITECTURE.md
+  │     database.md     → docs/architecture/DATABASE.md
+  │     physical-model.md → docs/architecture/PHYSICAL-MODEL.md
+  │     api.md          → docs/architecture/API-INDEX.md
+  │     index.md        → docs/architecture/INDEX.md
+  └── 已存在的文件不覆盖（只补缺失）
+
 Step 1: 询问用户是否有既有成果物
   ├── 有 SQL DDL 脚本 → 导入到 docs/architecture/schema-baseline.sql
   ├── 有物理模型文档 → 转换为 docs/architecture/PHYSICAL-MODEL.md（对齐标准格式）
@@ -76,7 +86,8 @@ Step 1: 询问用户是否有既有成果物
   └── 无既有成果物 → Step 2 兜底
 
 Step 2: 确定性提取（兜底）
-  ├── recon-probe.sh 增加 DDL 提取能力（解析 Entity 类 / SHOW CREATE TABLE）
+  ├── recon-probe.sh DDL 提取能力（v0.24.0 已实现：SQL 文件 / Java Entity / 占位）
+  │   bash scripts/recon-probe.sh --root <根> --ddl-out docs/architecture/schema-baseline.sql
   ├── 从 schema-baseline.sql 反向生成 PHYSICAL-MODEL.md
   └── 扫描 Controller/Router 类 → 生成 API-INDEX.md
 

package/skills/workflow-bootstrap/references/b1-reconnaissance.md

@@ -15,16 +15,22 @@ bash scripts/recon-probe.sh --root <项目根> --out /tmp/recon-<slug>.json
 
 固定采集（不依赖 LLM，两次接入结果一致）：目录树（限深 4 层）、依赖清单（pom/package.json/requirements/go.mod/build.gradle）、LOC 与文件类型分布、测试文件计数（含 `.test.mjs`/`.spec.mjs`）、DB 迁移文件清单、README/docs 探测。输出结构化 JSON 供子代理消费。脚本只做确定性机械采集（§17.8 第四类载体），语义判断交给子代理 LLM。
 
-## B1.1a DDL 提取能力（v0.23.0 新增）
+## B1.1a DDL 提取能力（v0.23.0 设计，v0.24.0 已实现）
 
-`recon-probe.sh` 需增加 DDL 提取能力，用于 B2 成果物导入阶段的兜底提取：
+`recon-probe.sh` 已实现 DDL 提取能力（v0.24.0），用于 B2 成果物导入阶段的兜底提取：
 
-- **Entity 类解析**：扫描 `@Entity`、`@Table` 注解的 Java 类，或 ORM 模型定义文件，提取表名、字段名、字段类型、索引信息
-- **SHOW CREATE TABLE**：当项目配置了数据库连接时，执行 `SHOW CREATE TABLE` 导出各表 DDL
-- **迁移文件解析**：解析 Flyway / Liquibase / Alembic 等迁移脚本，提取最终态 schema
-- **输出**：将提取结果写入 `docs/architecture/schema-baseline.sql`，格式为标准 DDL（CREATE TABLE 语句）
+- **策略 1：SQL 文件提取**（优先级最高）：扫描 `*.sql` 文件中的 `CREATE TABLE` 语句，直接提取完整 DDL
+- **策略 2：Java Entity 类解析**：扫描 `@Entity`、`@Table` 注解的 Java 类，提取表名、字段名、字段类型（正则映射：String→varchar(255)、Long/int→bigint、Boolean→tinyint(1)、LocalDateTime→datetime、BigDecimal→decimal(15,4)）
+- **策略 3：占位兜底**：以上均无时生成带注释的空 `schema-baseline.sql`，提示用户手动补充
 
-此能力为 B2 Step 2 兜底提取的前置依赖。当用户无既有 DDL 脚本时，由 recon-probe.sh 自动从代码/数据库中提取 schema 基线。
+**用法**：
+```bash
+bash scripts/recon-probe.sh --root <根> --ddl-out docs/architecture/schema-baseline.sql --out /tmp/recon-<slug>.json
+```
+
+**JSON 输出字段**：`ddl_extraction.source`（sql_files / java_entity / none）、`ddl_extraction.table_count`、`ddl_extraction.tables[]`、`ddl_extraction.ddl_statements`
+
+**未实现**：SHOW CREATE TABLE（需数据库连接，留待用户手动配置）、Flyway/Liquibase 迁移脚本解析（需语义判断，由侦察子代理处理）。
 
 ## B1.2 并行派发侦察子代理（语义增强）
 

package/skills/workflow-bootstrap/scripts/recon-probe.sh

@@ -36,6 +36,7 @@ set -u  # 未定义变量报错；不用 -e（单条采集失败不应中断整
 # ----------------------------------------------------------------------------
 ROOT="."
 OUT=""
+DDL_OUT=""           # v0.24.0: DDL 输出文件路径（默认不写，仅含在 JSON 中）
 MAX_FILES=50000     # LOC 统计文件数上限（保护超大仓库）
 TREE_DEPTH=4        # 目录树限深
 
@@ -51,6 +52,8 @@ while [ $# -gt 0 ]; do
     --root=*) ROOT="${1#*=}"; shift ;;
     --out)    OUT="${2:-}"; shift 2 ;;
     --out=*)  OUT="${1#*=}"; shift ;;
+    --ddl-out) DDL_OUT="${2:-}"; shift 2 ;;
+    --ddl-out=*) DDL_OUT="${1#*=}"; shift ;;
     -h|--help) print_help; exit 0 ;;
     *) echo "[recon-probe] warn: unknown arg '$1' (ignored)" >&2; shift ;;
   esac
@@ -260,6 +263,111 @@ pruned_find -maxdepth 2 -type f \
   -print 2>/dev/null | sed "s#^$ROOT_ABS/##" | sort > "$TMP/doc_files.txt"
 if [ -d "$ROOT_ABS/docs" ]; then DOCS_DIR=true; else DOCS_DIR=false; fi
 
+# ============================================================================
+# ⑦ DDL 提取（v0.24.0：schema-baseline 兜底采集）
+# ----------------------------------------------------------------------------
+# 策略（优先级）：
+#   1. 既有 .sql 中的 CREATE TABLE 语句 → 直接提取
+#   2. Java Entity 类（@Entity / @Table 注解）→ 正则提取表名+字段
+#   3. 以上均无 → 输出空 schema-baseline.sql + 提示手动补充
+# 设计契约：只做确定性机械采集（regex），语义推断交给侦察子代理。
+# ============================================================================
+
+: > "$TMP/ddl_statements.sql"
+: > "$TMP/ddl_tables.txt"
+DDL_SOURCE="none"
+DDL_TABLE_COUNT=0
+
+# --- 策略 1：从既有 .sql 文件提取 CREATE TABLE ----------------------------------
+if [ -s "$TMP/sql_files.txt" ]; then
+  while IFS= read -r sql_rel; do
+    sql_abs="$ROOT_ABS/$sql_rel"
+    [ -f "$sql_abs" ] || continue
+    # 提取 CREATE TABLE 语句（多行匹配，到第一个 ; 结束）
+    # 兼容：CREATE TABLE / CREATE TABLE IF NOT EXISTS / 大小写不敏感
+    awk '
+      BEGIN { IGNORECASE=1; in_stmt=0; stmt="" }
+      /CREATE[[:space:]]+TABLE/ { in_stmt=1; stmt="" }
+      in_stmt {
+        stmt = stmt $0 "\n"
+        if (/;/) {
+          printf "%s-- Source: %s\n\n", stmt, sql_file
+          in_stmt=0; stmt=""
+        }
+      }
+    ' sql_file="$sql_rel" "$sql_abs" 2>/dev/null >> "$TMP/ddl_statements.sql" || true
+  done < "$TMP/sql_files.txt"
+  if [ -s "$TMP/ddl_statements.sql" ]; then
+    DDL_SOURCE="sql_files"
+    # 提取表名（用于计数和 JSON）
+    grep -ioE 'CREATE[[:space:]]+TABLE[[:space:]]+(IF[[:space:]]+NOT[[:space:]]+EXISTS[[:space:]]+)?[`"]?([a-zA-Z_][a-zA-Z0-9_.]*)[`"]?' \
+      "$TMP/ddl_statements.sql" 2>/dev/null \
+      | grep -ioE '[`"]?[a-zA-Z_][a-zA-Z0-9_]*\.[a-zA-Z_][a-zA-Z0-9_]*[`"]?|[a-zA-Z_][a-zA-Z0-9_]*[`"]?$' \
+      | sed -E 's/[`"]//g' | sort -u > "$TMP/ddl_tables.txt" || true
+    DDL_TABLE_COUNT=$(wc -l < "$TMP/ddl_tables.txt" | tr -d ' ')
+  fi
+fi
+
+# --- 策略 2：从 Java Entity 类提取（@Entity / @Table 注解）-----------------------
+if [ "$DDL_TABLE_COUNT" -eq 0 ]; then
+  : > "$TMP/entity_files.txt"
+  pruned_find -type f -name '*.java' -print 2>/dev/null \
+    | while IFS= read -r jf; do
+        if grep -qlE '@(Entity|Table|Document|TableName)' "$jf" 2>/dev/null; then
+          echo "$jf"
+        fi
+      done | sort > "$TMP/entity_files.txt"
+
+  ENTITY_COUNT=$(wc -l < "$TMP/entity_files.txt" | tr -d ' ')
+  if [ "$ENTITY_COUNT" -gt 0 ]; then
+    DDL_SOURCE="java_entity"
+    while IFS= read -r ef; do
+      ef_rel="${ef#"$ROOT_ABS"/}"
+      # 提取 @Table(name="xxx") 或类名作为表名
+      table_name=""
+      tn="$(grep -oE '@Table\([^)]*name[[:space:]]*=[[:space:]]*"[^"]+"' "$ef" 2>/dev/null | head -1 \
+        | grep -oE '"[^"]+"' | tr -d '"')" || true
+      if [ -n "$tn" ]; then
+        table_name="$tn"
+      else
+        # 降级：用类名转 snake_case 作为表名
+        table_name="$(grep -oE 'class[[:space:]]+[A-Z][a-zA-Z0-9]*' "$ef" 2>/dev/null | head -1 \
+          | sed -E 's/class[[:space:]]+//' \
+          | sed -E 's/([A-Z])/_\1/g' | tr '[:upper:]' '[:lower:]' | sed 's/^_//')" || true
+      fi
+      [ -z "$table_name" ] && continue
+
+      # 攒完整 DDL 到临时文件再一次性追加（避免多次 >> 缓冲问题）
+      : > "$TMP/_entity_ddl.tmp"
+      echo "-- Entity: $ef_rel" >> "$TMP/_entity_ddl.tmp"
+      echo "CREATE TABLE $table_name (" >> "$TMP/_entity_ddl.tmp"
+      # 机械提取 private 字段声明：private Type fieldName;
+      grep -E '^[[:space:]]*private[[:space:]]+' "$ef" 2>/dev/null \
+        | grep -vE 'static[[:space:]]|final[[:space:]]|Logger|log|serialVersionUID' \
+        | sed -E 's/^[[:space:]]*private[[:space:]]+([A-Za-z0-9_<>, ]+)[[:space:]]+([a-zA-Z_][a-zA-Z0-9_]*)[[:space:]]*(=|;).*/  \2 \1,/' \
+        | sed -E 's/String|varchar|text/varchar(255)/g; s/Long|Integer|int|long/bigint/g; s/Boolean|boolean/tinyint(1)/g; s/Date|LocalDateTime|Timestamp/datetime/g; s/BigDecimal|Double|Float/decimal(15,4)/g' \
+        >> "$TMP/_entity_ddl.tmp" 2>/dev/null || true
+      echo "  create_time datetime," >> "$TMP/_entity_ddl.tmp"
+      echo "  update_time datetime," >> "$TMP/_entity_ddl.tmp"
+      echo "  del_flag tinyint(1) DEFAULT 0" >> "$TMP/_entity_ddl.tmp"
+      echo ");" >> "$TMP/_entity_ddl.tmp"
+      echo "" >> "$TMP/_entity_ddl.tmp"
+      cat "$TMP/_entity_ddl.tmp" >> "$TMP/ddl_statements.sql"
+      echo "$table_name" >> "$TMP/ddl_tables.txt"
+    done < "$TMP/entity_files.txt"
+    sort -u "$TMP/ddl_tables.txt" -o "$TMP/ddl_tables.txt"
+    DDL_TABLE_COUNT=$(wc -l < "$TMP/ddl_tables.txt" | tr -d ' ')
+  fi
+fi
+
+# --- 策略 3：生成占位 schema-baseline.sql ---------------------------------------
+if [ "$DDL_TABLE_COUNT" -eq 0 ]; then
+  DDL_SOURCE="none"
+  printf -- '-- schema-baseline.sql (auto-generated placeholder)\n' > "$TMP/ddl_statements.sql"
+  printf -- '-- No CREATE TABLE statements or Java Entity classes detected.\n' >> "$TMP/ddl_statements.sql"
+  printf -- '-- Please populate manually with your database schema.\n\n' >> "$TMP/ddl_statements.sql"
+fi
+
 # ============================================================================
 # 组装 JSON
 # ============================================================================
@@ -288,8 +396,13 @@ if [ -d "$ROOT_ABS/docs" ]; then DOCS_DIR=true; else DOCS_DIR=false; fi
     "$(json_array_from_file "$TMP/migration_dirs.txt")" \
     "$(json_array_from_file "$TMP/sql_samples.txt")"
   # ⑥ docs
-  printf '  "docs": {"docs_dir": %s, "doc_files": %s}\n' \
+  printf '  "docs": {"docs_dir": %s, "doc_files": %s},\n' \
     "$DOCS_DIR" "$(json_array_from_file "$TMP/doc_files.txt")"
+  # ⑦ DDL 提取（v0.24.0）
+  printf '  "ddl_extraction": {"source": "%s", "table_count": %s, "tables": %s, "ddl_statements": "%s"}\n' \
+    "$(json_escape "$DDL_SOURCE")" "$DDL_TABLE_COUNT" \
+    "$(json_array_from_file "$TMP/ddl_tables.txt")" \
+    "$(json_escape "$(cat "$TMP/ddl_statements.sql" 2>/dev/null)")"
   printf '}\n'
 } > "$TMP/out.json"
 
@@ -311,6 +424,13 @@ else
   emit_json
 fi
 
+# v0.24.0: DDL 独立输出文件（--ddl-out）
+if [ -n "$DDL_OUT" ] && [ -s "$TMP/ddl_statements.sql" ]; then
+  mkdir -p "$(dirname "$DDL_OUT")" 2>/dev/null || true
+  cp "$TMP/ddl_statements.sql" "$DDL_OUT" 2>/dev/null || true
+  echo "[recon-probe] DDL baseline written to: $DDL_OUT" >&2
+fi
+
 # 人类可读摘要 → stderr
 {
   echo "================ recon-probe 摘要 ================"
@@ -322,6 +442,7 @@ fi
   echo "SQL 迁移     : $SQL_COUNT 个"
   echo "docs/ 目录   : $DOCS_DIR"
   echo "README 等    : $(wc -l < "$TMP/doc_files.txt" | tr -d ' ') 个"
+  echo "DDL 提取     : source=$DDL_SOURCE, tables=$DDL_TABLE_COUNT"
   echo "================================================="
 } >&2
 

package/skills/workflow-orchestrator/references/s2-prd-prototype-loop.md

@@ -54,7 +54,7 @@
 检测可复利时刻（需求矛盾、原型返工、自动评审发现不一致并修正等）。每次自动评审发现不一致并修正后触发：
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf solutions capture --phase prd --domain <domain> --type pitfall --severity <sev> --summary "<summary>"
+npx --yes --package @xulthekl/team-flow@0.24.0 tf solutions capture --phase prd --domain <domain> --type pitfall --severity <sev> --summary "<summary>"
 ```
 
 ### 6. 反馈环路检查点

package/skills/workflow-orchestrator/references/s4-split-validate.md

@@ -38,7 +38,7 @@ verdict = FAIL → 必须回退 S3 调整拆分后重新审计，不可绕过直
 
 ```bash
 mkdir -p changes/<change-name>
-npx --yes --package @xulthekl/team-flow@0.23.0 tf state init changes/<change-name>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf state init changes/<change-name>
 ```
 
 > ⚠️ **路径约束**：change 脚手架目录固定为项目根 `changes/<change-name>/`。

package/skills/workflow-orchestrator/references/s5-monitoring.md

@@ -34,7 +34,7 @@
 change closing 时检查经验晋升（change 内经验 → 产品级经验）：
 
 ```bash
-npx --yes --package @xulthekl/team-flow@0.23.0 tf solutions promote <change-dir>
+npx --yes --package @xulthekl/team-flow@0.24.0 tf solutions promote <change-dir>
 ```
 
 ### 4. 动态重规划触发