@boyingliu01/xp-gate 0.18.5 → 0.19.1

package/plugins/dsh/skills/delphi-review/SKILL.md

@@ -0,0 +1,559 @@
+---
+name: delphi-review
+version: 1.1.0
+description: >
+  Performs multi-round anonymous expert consensus review using the Delphi method. Supports
+  design review (default), code-walkthrough (--mode code-walkthrough), and requirements
+  (lightweight, --mode requirements) modes. Uses exactly three experts with distinct executable
+  model IDs and a >=90% statistical consensus threshold.
+  Outputs structured verdict (APPROVED/PASS_WITH_CAVEATS/REQUEST_CHANGES/BLOCKED).
+
+  WHAT: Anonymous multi-expert review with iterative consensus building for designs, plans,
+  architecture, code changes, and PRs. NOT a single-reviewer pass, NOT a linter, NOT a test runner.
+  WHEN: User explicitly requests a review, design validation, multi-expert consensus, code walkthrough
+  before push, architecture evaluation, or "/delphi-review".
+  NOT WHEN: Asking HOW to review something (educational), mentioning "review" in passing without intent,
+  requesting a simple code check or lint, asking about the Delphi process itself, or mentioning
+  "review" as part of a different workflow (e.g., "code review" without multi-expert intent),
+  asking for review guidelines/checklists/formats, individual peer review, or casual review requests.
+
+  TRIGGERS: "/delphi-review", "review this design", "评审这个需求", "评审这个设计", "design review",
+  "多专家评审", "consensus review", "code walkthrough", "push review", "architecture review",
+  "delphi review", "run delphi", "start delphi", "评审这个架构", "review this architecture",
+  "评审PR", "review this PR with delphi", "delphi评审", "delphi 评审", "run delphi review",
+  "执行delphi", "启动delphi评审", "review the requirements", "评审需求", "requirements review",
+  "/requirements-review".
+  NEGATIVE TRIGGERS: "how does delphi work", "what is delphi review", "code review checklist",
+  "review my code quickly", "can you review this", "peer review", "I need a review",
+  "explain the review process", "review guidelines", "how to review a design",
+  "code review template", "review format", "PR review", "帮我review一下",
+  "just review this", "quick review", "review steps", "review my requirements document".
+maturity: beta
+auto_continue: true
+triggers:
+  - "/delphi-review"
+  - "review this design"
+  - "评审这个需求"
+  - "评审这个设计"
+  - "design review"
+  - "多专家评审"
+  - "consensus review"
+  - "code walkthrough"
+  - "push review"
+  - "architecture review"
+  - "delphi review"
+  - "run delphi"
+  - "start delphi"
+  - "评审这个架构"
+  - "review this architecture"
+  - "评审PR"
+  - "review this PR with delphi"
+  - "delphi评审"
+  - "delphi 评审"
+  - "run delphi review"
+  - "执行delphi"
+  - "启动delphi评审"
+  - "review the requirements"
+  - "评审需求"
+  - "requirements review"
+  - "/requirements-review"
+triggers_negative_examples:
+  - "how does delphi work"       # educational question about the process
+  - "what is delphi review"      # asking for explanation, not execution
+  - "code review checklist"      # asking for a checklist, not running review
+  - "review my code quickly"     # single-pass quick review, not Delphi multi-round
+  - "can you review this"        # ambiguous — could be casual peer review
+  - "peer review"                # different process from Delphi
+  - "I need a review"            # too vague, casual request
+  - "explain the review process" # educational, not executional
+  - "review guidelines"          # asking about guidelines, not executing
+  - "how to review a design"     # educational
+  - "PR review"                  # single-reviewer PR check, not multi-expert Delphi
+  - "review my PR"               # informal PR review request, not Delphi
+  - "帮我review一下"             # casual Chinese review request, no multi-expert intent
+  - "just review this"           # casual, single-pass review request
+  - "quick review"               # explicitly contradicts multi-round Delphi process
+  - "review steps"               # asking for review instructions, not running review
+  - "code review template"       # asking for a template, not executing review
+  - "review format"              # asking about format, not executing
+  - "show me how to review"      # educational request about reviewing
+  - "review checklist example"   # asking for examples, not running review
+  - "review my requirements document"  # educational discussion about requirements, not executing review
+triggers_negative_test_cases:
+  - input: "how does delphi work"
+    expect: "NOT triggered"
+  - input: "code review checklist"
+    expect: "NOT triggered"
+  - input: "review my code quickly"
+    expect: "NOT triggered"
+  - input: "can you review this"
+    expect: "NOT triggered"
+  - input: "peer review"
+    expect: "NOT triggered"
+  - input: "I need a review"
+    expect: "NOT triggered"
+  - input: "explain the review process"
+    expect: "NOT triggered"
+  - input: "review guidelines"
+    expect: "NOT triggered"
+  - input: "/delphi-review"
+    expect: "triggered"
+  - input: "review this design"
+    expect: "triggered"
+  - input: "评审这个需求"
+    expect: "triggered"
+  - input: "评审这个设计"
+    expect: "triggered"
+  - input: "design review"
+    expect: "triggered"
+  - input: "多专家评审"
+    expect: "triggered"
+  - input: "consensus review"
+    expect: "triggered"
+  - input: "code walkthrough"
+    expect: "triggered"
+  - input: "architecture review"
+    expect: "triggered"
+  - input: "delphi review"
+    expect: "triggered"
+  - input: "评审这个架构"
+    expect: "triggered"
+  - input: "delphi 评审"
+    expect: "triggered"
+  - input: "run delphi review"
+    expect: "triggered"
+  - input: "review my PR"
+    expect: "NOT triggered"
+  - input: "帮我review一下"
+    expect: "NOT triggered"
+  - input: "just review this"
+    expect: "NOT triggered"
+  - input: "quick review"
+    expect: "NOT triggered"
+  - input: "review steps"
+    expect: "NOT triggered"
+  - input: "code review template"
+    expect: "NOT triggered"
+  - input: "run delphi"
+    expect: "triggered"
+  - input: "review the requirements"
+    expect: "triggered"
+  - input: "评审需求"
+    expect: "triggered"
+  - input: "requirements review"
+    expect: "triggered"
+  - input: "/requirements-review"
+    expect: "triggered"
+  - input: "review my requirements document"
+    expect: "NOT triggered"
+workflow_steps:
+  - "Step 0: Input Validation → Output: [DelphiReview] or [DelphiReview:BLOCKED]"
+  - "Round 1: Anonymous Independent Review → Output: [DelphiReview Round 1] expert JSON verdicts"
+  - "Consensus Check → Output: consensus_ratio, verdict summary"
+  - "Round 2: Exchange Opinions (if needed) → Output: [DelphiReview Round 2] revised verdicts"
+  - "Round 3: Final Positions (if needed) → Output: [DelphiReview Round 3] final verdicts"
+  - "Fix & Re-Review (if REQUEST_CHANGES) → restart from Round 2"
+  - "Generate Output: consensus report + specification.yaml (design) or .code-walkthrough-result.json (walkthrough)"
+hooks:
+  security:
+    - "/careful": "Safety guardrails for destructive commands — ensure review is read-only"
+    - "/freeze": "Restrict edits to review scope — prevent accidental changes during review"
+    - "/guard": "Full safety mode combining careful + freeze for maximum protection"
+  operational:
+    - "/context-save": "Save review context before pause or handoff"
+    - "/context-restore": "Restore review context on resume"
+tools_allowed:
+  - "Read"                       # read design docs, code, configs, specification.yaml
+  - "Glob"                       # find files by pattern
+  - "Grep"                       # search code content
+  - "Bash"                       # read-only: git diff, git log, file stats
+  - "Task(subagent_type=oracle)" # dispatch oracle for deep analysis
+  - "Task(subagent_type=delphi-reviewer-architecture)"    # dispatch architecture expert
+  - "Task(subagent_type=delphi-reviewer-technical)"     # dispatch technical expert
+  - "Task(subagent_type=delphi-reviewer-feasibility)"   # dispatch feasibility expert
+  - "Write(specification.yaml, .code-walkthrough-result.json, delphi-reviewed.json)"  # write output artifacts only
+  - "Skill"                      # invoke related skills for context
+  - "Question"                   # ask user at decision points
+tools_denied:
+  - "Edit(source code)"           # NEVER edit implementation code during review
+  - "Write(source code)"          # NEVER write implementation code
+  - "Bash(git commit, git push)"  # NEVER commit or push during review
+  - "Task(category=*, subagent_type=build)"  # NEVER delegate build/implementation
+---
+
+# Delphi Consensus Review
+
+## Scope
+
+**In Scope:**
+- Multi-round anonymous expert consensus review (design + code-walkthrough modes)
+- Exactly three experts with distinct normalized executable model IDs and statistical consensus (>= 90%)
+- Structured verdict: APPROVED / PASS_WITH_CAVEATS / REQUEST_CHANGES
+- Model nationality, vendor, provider, and gateway are unrestricted.
+
+**Out of Scope:**
+- Does NOT implement code changes (review only, implementation is separate)
+- Does NOT replace testing or CI/CD verification
+- Does NOT handle deployment or release decisions
+
+## Triggers
+
+- /delphi-review
+- review this design
+- 评审这个需求
+- 评审这个设计
+- design review
+- 多专家评审
+- consensus review
+- code walkthrough
+- push review
+- architecture review
+- delphi review
+- run delphi
+- start delphi
+- 评审这个架构
+- review this architecture
+- 评审PR
+- review this PR with delphi
+- delphi评审
+- delphi 评审
+- run delphi review
+- 执行delphi
+- 启动delphi评审
+- review the requirements
+- 评审需求
+- requirements review
+- /requirements-review
+
+**NOT triggered by:**
+- "how does delphi work" (educational)
+- "code review checklist" (asking for a list)
+- "review my code quickly" (single-pass, not multi-expert)
+- "can you review this" (ambiguous casual review)
+- "peer review" (different process)
+- "I need a review" (too vague)
+- "explain the review process" (educational)
+- "review guidelines" (asking about guidelines)
+- "PR review" (single-reviewer PR check)
+- "review my PR" (informal PR review)
+- "帮我review一下" (casual Chinese request)
+- "just review this" (casual single-pass)
+- "quick review" (contradicts multi-round process)
+- "review steps" (asking for instructions)
+- "code review template" (asking for template)
+- "review format" (asking about format)
+- "show me how to review" (educational)
+- "review my requirements document" (educational discussion, not execution)
+
+## Workflow
+
+1. **Step 0: Input Validation** — Check input contains reviewable content (design doc/code/spec/diff). Empty input → `[DelphiReview:BLOCKED]`.
+2. **Round 1: Anonymous Independent Review** — Invoke architecture, technical, and feasibility independently without exposing their opinions to one another. Every successful result must use `result_type=delphi_expert_result`.
+3. **Execution Verification** — Verify that all three results succeeded and that their `requested_model` values are three distinct trimmed IDs. A local fallback (`provider: local`) is not an executed expert and cannot satisfy this check; a local hosted endpoint configured as an ordinary callable provider can.
+4. **Consensus Check** — Aggregate all three successful expert results. Consensus >=90% AND all APPROVED → complete. One expert result is never global approval.
+5. **Rounds 2-5: Exchange and Final Positions** — If needed, expose prior aggregate evidence, re-evaluate, and stop at the first approved consensus or after five rounds.
+6. **Failure Handling** — Any expert failure, missing result, duplicate model ID, or unverifiable execution blocks the review. Do not substitute a local fallback or silently reduce the expert count.
+7. **Generate Output** — Write the consensus report and mode-specific evidence only after aggregation. For code walkthrough, bind the exact-HEAD result after aggregation.
+
+## Activation (MANDATORY for L1 Trigger Detection)
+
+Every delphi-review response MUST begin with an activation marker as the first line:
+
+| Marker | Meaning |
+|--------|---------|
+| `[DelphiReview]` | Standard entry — review proceeding |
+| `[DelphiReview:BLOCKED]` | Step 0 input validation failure |
+| `[DelphiReview:WARNING]` | Red flag detected (reserved) |
+
+## Round Markers (MANDATORY for L3 Step Adherence)
+
+Each round MUST output a structured round marker:
+
+```
+[DelphiReview Round 1] Anonymous Independent Review
+[DelphiReview Round 2] Exchange Opinions
+[DelphiReview Round 3] Final Positions
+```
+
+**Rules**:
+- Every round marker MUST appear as a separate, identifiable line
+- Round numbering MUST be sequential (1 through at most 5)
+- After each round, output consensus summary: `consensus_ratio=N/N`, `verdict_status: converging | stable | diverging`
+- Final round MUST output verdict: `APPROVED | PASS_WITH_CAVEATS | REQUEST_CHANGES | PROCESS_BLOCK`
+
+## 核心原则
+
+**Delphi 方法只有一个目的：得到所有专家一致认可的可行方案。**
+
+| 特性 | 说明 |
+|------|------|
+| **匿名性** | Round 1 专家互不知道对方意见 |
+| **迭代** | 多轮直到共识，不是固定轮数 |
+| **受控反馈** | 每轮看到其他专家意见 |
+| **统计共识** | >=90% 一致才算共识 |
+| **Token 是投资** | 相比后期修复成本，评审消耗微不足道 |
+| **零容忍** | Critical/Major 全部必须处理，不可跳过 |
+
+---
+
+## 评审模式
+
+| 模式 | 触发 | 用途 | 输出 |
+|------|------|------|------|
+| `design`（默认） | `/delphi-review` | 需求/设计/架构/PR 评审 | 共识报告 + specification.yaml |
+| `code-walkthrough` | `--mode code-walkthrough` | git push 前代码走查 | `.code-walkthrough-result.json` |
+| `requirements` | `--mode requirements` | Phase 2 THINK 阶段需求评审 | `.sprint-state/phase-outputs/requirements-reviewed.json` |
+
+**Code Walkthrough 模式**的完整规范 → 详见 `references/code-walkthrough.md`
+
+**Requirements 模式**的完整规范 → 详见 `references/requirements.md`
+
+---
+
+## 参数配置
+
+### 专家配置
+
+| 配置 | 专家 | 适用场景 |
+|------|------|---------|
+| 3 专家（固定） | A(架构) + B(实现) + C(可行性) | 所有评审模式 |
+
+### 模型选择策略（强制 — 平台适配）
+
+**关键原则**：
+- ✅ 必须配置 architecture、technical、feasibility 三个专家角色
+- ✅ 三个角色必须使用三个不同的 trimmed、可执行模型 ID
+- ✅ 模型国籍、厂商、provider 和 gateway 不受限制
+- ✅ 三个角色可以共享一个 provider 和 token 计划
+- ❌ `provider: local` 的特殊 fallback 不能计为一次成功执行
+
+#### Qoder 平台（推荐 — Custom Agent 模式）
+
+Qoder 环境下使用 **Custom Agent** 机制，每个专家是一个独立的 custom agent，配置不同的 Qoder 内置模型：
+
+| 专家 | Agent 文件 | 模型 | Credits 费率 |
+|------|-----------|------|-------------|
+| Architecture (A) | `.qoder/agents/delphi-architecture.md` | Qwen3.7-Max | 0.5× |
+| Technical (B) | `.qoder/agents/delphi-technical.md` | GLM-5.2 | 0.6× |
+| Feasibility (C) | `.qoder/agents/delphi-feasibility.md` | DeepSeek-V4-Pro | 0.5× |
+
+**执行方式**：通过 Agent tool 并行启动 3 个 subagent（type=GeneralPurpose），每个 agent 使用自己配置的模型独立评审，主 orchestrator 收集结果后计算共识。
+
+**优势**：无需外部 API key，直接使用 Qoder Credits，模型由平台统一管理。
+
+#### OpenCode 平台（External API 模式）
+
+OpenCode 环境下通过 `opencode.json` 的 agent 配置 + `.delphi-config.json` 调用外部 API：
+- **MUST 从 `opencode.json` 的 agent 配置中读取模型**
+- 通过 `scripts/delphi-external-review.cjs` 调用各 provider 的兼容 API
+- 需要用户自行配置 API key（环境变量注入）
+
+### 共识阈值
+
+| 阈值 | 说明 |
+|------|------|
+| **>=90%** | 推荐默认 |
+| 100% | 完全一致（更严格） |
+
+---
+
+## 评审执行过程
+
+```
+Phase 0: 准备 → Round 1: 匿名独立评审 → 共识检查
+    │
+    ├─ 一致 + >=90% + APPROVED → ✅ 完成
+    │
+    └─ 不一致 或 <90% 或 REQUEST_CHANGES
+          │
+          ▼
+       Round 2: 交换意见 → 共识检查
+          │
+          ├─ 一致 + >=90% + APPROVED → ✅ 完成
+          │
+          └─ 仍分歧 或 REQUEST_CHANGES
+                │
+                ▼
+             Round 3: 最终立场 → 共识检查
+                │
+                ├─ APPROVED → ✅ 完成
+                │
+                └─ REQUEST_CHANGES → 修复方案 → 回到 Round 2 重新评审
+```
+
+### Step 0: Input Validation (MANDATORY — 必须在任何评审前执行)
+
+检查用户 prompt 中是否包含可评审内容（设计文档、代码、specification.yaml、PR diff）：
+
+1. **有完整输入** → 直接进入 Phase 0（准备阶段），开始 Round 1
+2. **有部分输入**（占位符、描述性文本）→ 按输入内容执行评审，标注 `[INPUT: PARTIAL]`，但继续执行
+3. **无输入**（仅触发词，无文档/代码）→ 输出阻断响应
+
+**Detection heuristics**:
+- **Complete**: >=1 structural element (##, requirement, AC-, function, class, interface, YAML frontmatter, code block) AND >=50 non-whitespace chars.
+- **Partial**: Descriptive text referencing a design/code artifact BUT lacks structure, OR contains placeholders.
+- **None**: Only trigger words with zero additional content, OR questions about the review process itself.
+
+**Partial input constraint**: Cap review to 1 round with `confidence=low` annotation.
+
+---
+
+## 修复与重新评审
+
+如果最终裁决是 REQUEST_CHANGES 或 REJECTED：
+1. 修复所有 Critical Issues + 处理所有 Major Concerns
+2. 重新评审（从 Round 2 起步，不是 Round 1）
+3. 迭代直到 APPROVED
+
+---
+
+## 终止条件
+
+| 参数 | 默认值 | 说明 |
+|------|--------|------|
+| `max_review_rounds` | 5 | 超过后生成"未达成共识报告"，交人决策 |
+| `timeout` | 60min | 单次评审超时 |
+
+---
+
+## Output Format (MANDATORY for L3)
+
+Every Delphi mode MUST use the full JSON schema below. Architecture, technical, and feasibility each output independently; the orchestrator verifies all three executions before aggregating `consensus_report`. There is no single-reviewer Delphi approval path.
+
+```json
+{
+  "expert_id": "A|B|C",
+  "round": 1,
+  "mode": "design",
+  "verdict": "APPROVED|REQUEST_CHANGES|REJECTED",
+  "confidence": 9,
+  "critical_issues": ["..."],
+  "major_concerns": ["..."],
+  "minor_concerns": ["..."],
+  "consensus_report": {
+    "agreed_items": ["..."],
+    "disagreed_items": ["..."],
+    "final_verdict": "APPROVED|REQUEST_CHANGES",
+    "consensus_ratio": 0.95
+  }
+}
+```
+
+**For code-walkthrough mode**, output follows `.code-walkthrough-result.json` schema (see `references/code-walkthrough.md`).
+
+**For requirements mode**, output follows `requirements-reviewed.json` schema (see `references/requirements.md`):
+
+```json
+{
+  "mode": "requirements",
+  "verdict": "APPROVED|GAPS_FOUND",
+  "timestamp": "2026-07-25T10:30:00Z",
+  "consensus_ratio": 1.0,
+  "requirements_hash": "<SHA-256 hex digest>",
+  "head_commit": "<git rev-parse HEAD>",
+  "context_file_used": "CONTEXT.md",
+  "round": 1,
+  "expert_verdicts": [
+    { "role": "architecture", "verdict": "APPROVED", "confidence": 9, "result_type": "delphi_expert_result", "requested_model": "provider/model-a" },
+    { "role": "technical", "verdict": "APPROVED", "confidence": 8, "result_type": "delphi_expert_result", "requested_model": "provider/model-b" },
+    { "role": "feasibility", "verdict": "APPROVED", "confidence": 8, "result_type": "delphi_expert_result", "requested_model": "provider/model-c" }
+  ],
+  "requirements_statement": "<short summary of what was reviewed>",
+  "gaps_found": [],
+  "rounds_used": 1,
+  "escalation_needed": false
+}
+```
+
+Schema-v2 Phase 2 requires `requirements_statement`, `timestamp`, `consensus_ratio`, `expert_verdicts`, `head_commit`, and `requirements_hash`. The hash is SHA-256 of the exact concatenation `requirements_statement + project-relative context file UTF-8 content if used + timestamp YYYY-MM-DD`; context paths must remain inside the project after realpath resolution.
+
+**Anti-patterns mapping:**
+- `Round 1 → "评审完成"` → MUST NOT have `verdict: APPROVED` if `critical_issues` exist
+- `只处理 Critical，忽略 Major` → MUST include `major_concerns` array
+- `用户说"时间紧急"就跳过` → MUST include `round` field proving multi-round process
+
+---
+
+## Terminal State Checklist
+
+- [ ] Phase 0 完成（文档验证 + 专家分配）
+- [ ] 已完成所需轮次（最多 5 轮，每轮三位专家均执行）
+- [ ] 问题共识比例 >=90%
+- [ ] 所有 Critical Issues 已解决，Major Concerns 已处理
+- [ ] 最终裁决是 **APPROVED** 或 **APPROVED_WITH_MINOR**
+- [ ] 共识报告生成并保存
+- [ ] IF REQUEST_CHANGES → 已修复 → 已重新评审 → APPROVED
+- [ ] ⭐ **IF APPROVED (design mode): 生成 specification.yaml**
+- [ ] ⭐ **状态文件**: 写入 `.sprint-state/delphi-reviewed.json`
+
+**IF REQUEST_CHANGES/REJECTED → CANNOT claim complete**
+
+### 状态文件格式
+
+**Design mode APPROVED** → `.sprint-state/delphi-reviewed.json`:
+```json
+{"mode":"design","timestamp":"...","verdict":"APPROVED","consensus_ratio":1.0,"specification_path":".sprint-state/phase-outputs/specification.yaml"}
+```
+
+**Code-walkthrough mode APPROVED** → `.sprint-state/delphi-reviewed.json`:
+```json
+{"mode":"code-walkthrough","commit":"abc123...","timestamp":"...","verdict":"APPROVED","consensus_ratio":1.0}
+```
+
+**Requirements mode APPROVED** → `.sprint-state/delphi-reviewed.json`:
+```json
+{"mode":"requirements","timestamp":"...","verdict":"APPROVED","consensus_ratio":1.0}
+```
+
+---
+
+## Anti-Patterns
+
+| ❌ 错误 | ✅ 正确 |
+|---------|---------|
+| Round 1 未 APPROVED 就"评审完成" | 迭代直到 APPROVED，修复后重新评审 |
+| 只处理 Critical，忽略 Major | 零容忍：Critical/Major 全部必须处理 |
+| 单专家自评 | 必须运行 architecture、technical、feasibility 三位专家，并聚合三份成功结果 |
+| 用户说"时间紧急"就跳过 | 评审是投资不是开销 |
+| "专家几乎一致"就通过 | "几乎" = 不一致，继续到 >=90% |
+| 使用任何国籍或厂商的模型 | 模型国籍和厂商均不受限制，仍必须满足三个 distinct executable model IDs |
+| 三个专家同一 provider | 允许共享 provider，只要三个 requested_model IDs distinct 且每个调用成功 |
+
+**Code-walkthrough 专属 Anti-Patterns** → 详见 `references/code-walkthrough.md`
+
+**Requirements 专属 Anti-Patterns** → 详见 `references/requirements.md`
+
+---
+
+## Red Flags
+
+| 用户输入模式 | 触发词 | 响应动作 |
+|-------------|--------|---------|
+| 要求跳过评审 | "skip review", "不用评审", "跳过评审" | → 提醒评审是投资而非开销 |
+| 时间压力 | "来不及", "时间紧", "emergency" | → 提醒时间紧迫正是需要评审的时刻 |
+| 提前终止 | Round 1 后用户说 "可以了", "够了" | → BLOCK: 评审未达终止条件 |
+| 单专家自评 | 用户仅指定 1 个专家 | → BLOCK：Delphi 必须执行 architecture、technical、feasibility 三位专家 |
+| 无文档输入 | 仅触发词，无设计/代码内容 | → `[DelphiReview:BLOCKED]` |
+
+---
+
+## 成功标准
+
+1. ✅ 所有专家裁决 APPROVED
+2. ✅ 问题共识 >=90%
+3. ✅ 所有 Critical Issues 已修复验证 + Major Concerns 已处理
+4. ✅ 共识报告已生成，用户已确认
+5. ✅ 状态文件已写入
+
+**缺少任何一项 = 未完成**
+
+## References
+
+> **Path convention**: `@references/` resolves relative to the skill directory (`skills/delphi-review/`).
+
+| File | Content |
+|------|---------|
+| `@references/code-walkthrough.md` | Code-walkthrough mode specification |
+| `@references/requirements.md` | Requirements mode specification |
+| `@references/orchestrator-dispatch.md` | Orchestrator auto-dispatch rules (#218 subagent multi-round loop) |
+| `@references/round-templates.md` | Round templates (anonymous/exchange/final/fix report formats) |

package/plugins/dsh/skills/delphi-review/hooks.md

@@ -0,0 +1,19 @@
+# Hooks — Delphi Review
+
+Delphi Review integrates with safety and operational hooks to ensure review integrity
+and context preservation.
+
+## Security Hooks
+
+| Hook | Purpose | Activation |
+|------|---------|------------|
+| `/careful` | Safety guardrails for destructive commands | Ensure review is read-only — block any destructive operations |
+| `/freeze` | Restrict edits to review scope | Prevent accidental changes during review |
+| `/guard` | Full safety mode (careful + freeze) | Maximum protection — read-only review with no accidental edits |
+
+## Operational Hooks
+
+| Hook | Purpose | Activation |
+|------|---------|------------|
+| `/context-save` | Save review context before pause or handoff | Before pausing review or switching tasks |
+| `/context-restore` | Restore review context on resume | When resuming review from pause or handoff |

package/plugins/dsh/skills/delphi-review/opencode.json.delphi.example

@@ -0,0 +1,52 @@
+{
+  "$comment": [
+    "Delphi Review Agent Configuration Template",
+    "===========================================",
+    "Copy the relevant 'agent' block below into your opencode.json.",
+    "Replace the example model IDs with three callable IDs available through your configured provider.",
+    "The three model fields must be different after trimming; providers may be shared."
+  ],
+
+  "$example_providers": {
+    "SharedProviderExample": "bailian-tp/qwen-plus"
+  },
+
+  "agent": {
+    "delphi-reviewer-architecture": {
+      "description": "Delphi expert reviewer for architecture perspective. Focuses on requirements alignment, system design, and high-level coherence.",
+      "mode": "subagent",
+      "model": "bailian-tp/qwen-plus",
+      "prompt": "You are a Delphi expert reviewer specializing in architecture and requirements alignment. Review the input for: 1) Alignment with stated goals 2) Architectural coherence 3) System-level implications 4) Trade-offs and alternatives. Output structured review with verdict (APPROVED/REQUEST_CHANGES/REJECTED) and confidence level.",
+      "tools": {
+        "read": true,
+        "bash": true,
+        "write": false,
+        "edit": false
+      }
+    },
+    "delphi-reviewer-technical": {
+      "description": "Delphi expert reviewer for technical depth. Focuses on implementation details, code correctness, and edge cases. Used in delphi-review.",
+      "mode": "subagent",
+      "model": "bailian-tp/deepseek-v3",
+      "prompt": "You are a Delphi expert reviewer specializing in technical implementation. Review the input for: 1) Implementation correctness 2) Code quality and patterns 3) Edge cases and error handling 4) Performance implications. Output structured review with verdict (APPROVED/REQUEST_CHANGES/REJECTED) and confidence level.",
+      "tools": {
+        "read": true,
+        "bash": true,
+        "write": false,
+        "edit": false
+      }
+    },
+    "delphi-reviewer-feasibility": {
+      "description": "Delphi expert reviewer for feasibility analysis. Focuses on practical constraints, risks, and execution viability. Used in delphi-review.",
+      "mode": "subagent",
+      "model": "bailian-tp/glm-4.5",
+      "prompt": "You are a Delphi expert reviewer specializing in feasibility and risk analysis. Review the input for: 1) Practical constraints (time, resources, dependencies) 2) Risk identification and mitigation 3) Execution complexity 4) Alternative approaches. Output structured review with verdict (APPROVED/REQUEST_CHANGES/REJECTED) and confidence level.",
+      "tools": {
+        "read": true,
+        "bash": true,
+        "write": false,
+        "edit": false
+      }
+    }
+  }
+}