pi-maestro-flow 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +124 -0
- package/agents/aggregator.md +27 -0
- package/agents/cli-explore-agent.md +188 -0
- package/agents/cross-role-reviewer.md +171 -0
- package/agents/delegate.md +19 -0
- package/agents/explorer.md +23 -0
- package/agents/impeccable-agent.md +99 -0
- package/agents/ralph-executor.md +81 -0
- package/agents/reference.md +24 -0
- package/agents/role-design-author.md +220 -0
- package/agents/team-supervisor.md +143 -0
- package/agents/team-worker.md +237 -0
- package/agents/ui-design-agent.md +270 -0
- package/agents/workflow-analyzer.md +116 -0
- package/agents/workflow-codebase-mapper.md +77 -0
- package/agents/workflow-collab-planner.md +147 -0
- package/agents/workflow-debugger.md +104 -0
- package/agents/workflow-executor.md +133 -0
- package/agents/workflow-external-researcher.md +86 -0
- package/agents/workflow-integration-checker.md +83 -0
- package/agents/workflow-nyquist-auditor.md +85 -0
- package/agents/workflow-phase-researcher.md +85 -0
- package/agents/workflow-plan-checker.md +100 -0
- package/agents/workflow-planner.md +200 -0
- package/agents/workflow-project-researcher.md +74 -0
- package/agents/workflow-research-synthesizer.md +70 -0
- package/agents/workflow-reviewer.md +82 -0
- package/agents/workflow-roadmapper.md +81 -0
- package/agents/workflow-verifier.md +120 -0
- package/package.json +58 -0
- package/skills/codify-to-knowhow/SKILL.md +167 -0
- package/skills/delegation-check/SKILL.md +297 -0
- package/skills/domain-add/SKILL.md +75 -0
- package/skills/insight-challenge/SKILL.md +226 -0
- package/skills/learn-decompose/SKILL.md +124 -0
- package/skills/learn-follow/SKILL.md +163 -0
- package/skills/learn-investigate/SKILL.md +160 -0
- package/skills/learn-second-opinion/SKILL.md +128 -0
- package/skills/maestro/SKILL.md +239 -0
- package/skills/maestro-amend/SKILL.md +169 -0
- package/skills/maestro-analyze/SKILL.md +173 -0
- package/skills/maestro-blueprint/SKILL.md +159 -0
- package/skills/maestro-brainstorm/SKILL.md +193 -0
- package/skills/maestro-collab/SKILL.md +181 -0
- package/skills/maestro-companion/SKILL.md +536 -0
- package/skills/maestro-composer/SKILL.md +192 -0
- package/skills/maestro-execute/SKILL.md +193 -0
- package/skills/maestro-fork/SKILL.md +104 -0
- package/skills/maestro-grill/SKILL.md +151 -0
- package/skills/maestro-guard/SKILL.md +124 -0
- package/skills/maestro-help/SKILL.md +328 -0
- package/skills/maestro-impeccable/SKILL.md +302 -0
- package/skills/maestro-init/SKILL.md +151 -0
- package/skills/maestro-merge/SKILL.md +90 -0
- package/skills/maestro-milestone-audit/SKILL.md +117 -0
- package/skills/maestro-milestone-complete/SKILL.md +133 -0
- package/skills/maestro-milestone-release/SKILL.md +131 -0
- package/skills/maestro-next/SKILL.md +269 -0
- package/skills/maestro-overlay/SKILL.md +203 -0
- package/skills/maestro-plan/SKILL.md +194 -0
- package/skills/maestro-player/SKILL.md +184 -0
- package/skills/maestro-quick/SKILL.md +117 -0
- package/skills/maestro-ralph/SKILL.md +905 -0
- package/skills/maestro-ralph-cli/SKILL.md +976 -0
- package/skills/maestro-ralph-cli-execute/SKILL.md +229 -0
- package/skills/maestro-ralph-execute/SKILL.md +409 -0
- package/skills/maestro-ralph-v2/SKILL.md +1198 -0
- package/skills/maestro-roadmap/SKILL.md +157 -0
- package/skills/maestro-swarm-workflow/SKILL.md +272 -0
- package/skills/maestro-tools-execute/SKILL.md +143 -0
- package/skills/maestro-tools-register/SKILL.md +192 -0
- package/skills/maestro-ui-codify/SKILL.md +127 -0
- package/skills/maestro-universal-workflow/SKILL.md +622 -0
- package/skills/maestro-update/SKILL.md +156 -0
- package/skills/manage-codebase-rebuild/SKILL.md +111 -0
- package/skills/manage-drift-realign/SKILL.md +159 -0
- package/skills/manage-harvest/SKILL.md +121 -0
- package/skills/manage-issue/SKILL.md +88 -0
- package/skills/manage-issue-discover/SKILL.md +104 -0
- package/skills/manage-kg-extractors/SKILL.md +147 -0
- package/skills/manage-knowhow/SKILL.md +102 -0
- package/skills/manage-knowhow-capture/SKILL.md +109 -0
- package/skills/manage-knowledge-audit/SKILL.md +147 -0
- package/skills/manage-status/SKILL.md +80 -0
- package/skills/manage-wiki/SKILL.md +104 -0
- package/skills/odyssey-debug/SKILL.md +344 -0
- package/skills/odyssey-improve/SKILL.md +423 -0
- package/skills/odyssey-planex/SKILL.md +542 -0
- package/skills/odyssey-review-test-fix/SKILL.md +392 -0
- package/skills/odyssey-ui/SKILL.md +388 -0
- package/skills/prompt-generator/SKILL.md +470 -0
- package/skills/quality-auto-test/SKILL.md +168 -0
- package/skills/quality-debug/SKILL.md +176 -0
- package/skills/quality-refactor/SKILL.md +108 -0
- package/skills/quality-retrospective/SKILL.md +134 -0
- package/skills/quality-review/SKILL.md +169 -0
- package/skills/quality-sync/SKILL.md +90 -0
- package/skills/quality-test/SKILL.md +183 -0
- package/skills/scholar-anti-ai-writing/SKILL.md +173 -0
- package/skills/scholar-anti-ai-writing/references/patterns-chinese.md +242 -0
- package/skills/scholar-anti-ai-writing/references/patterns-english.md +242 -0
- package/skills/scholar-citation-verify/SKILL.md +166 -0
- package/skills/scholar-citation-verify/references/api-usage.md +372 -0
- package/skills/scholar-citation-verify/references/common-errors.md +384 -0
- package/skills/scholar-citation-verify/references/verification-rules.md +399 -0
- package/skills/scholar-experiment/SKILL.md +321 -0
- package/skills/scholar-ideation/SKILL.md +288 -0
- package/skills/scholar-latex-organizer/SKILL.md +186 -0
- package/skills/scholar-publish/SKILL.md +220 -0
- package/skills/scholar-rebuttal-pro/README.md +313 -0
- package/skills/scholar-rebuttal-pro/SKILL.md +511 -0
- package/skills/scholar-review/SKILL.md +227 -0
- package/skills/scholar-thesis-docx/README.md +111 -0
- package/skills/scholar-thesis-docx/README_EN.md +108 -0
- package/skills/scholar-thesis-docx/SKILL.md +212 -0
- package/skills/scholar-thesis-docx/references/failure-patterns-and-quality-gates.md +178 -0
- package/skills/scholar-thesis-docx/references/figure-and-code-rules.md +33 -0
- package/skills/scholar-thesis-docx/references/paper-format-workflow.md +68 -0
- package/skills/scholar-thesis-docx/references/script-usage.md +157 -0
- package/skills/scholar-thesis-docx/scripts/audit_docx_ooxml.py +429 -0
- package/skills/scholar-thesis-docx/scripts/check_word_com.ps1 +50 -0
- package/skills/scholar-thesis-docx/scripts/export_word_pdf.ps1 +62 -0
- package/skills/scholar-thesis-docx/scripts/normalize_word_styles.ps1 +498 -0
- package/skills/scholar-thesis-docx/scripts/render_mermaid_figure.ps1 +148 -0
- package/skills/scholar-writing/SKILL.md +296 -0
- package/skills/security-audit/SKILL.md +244 -0
- package/skills/skill-generator/SKILL.md +472 -0
- package/skills/skill-iter-tune/SKILL.md +382 -0
- package/skills/skill-simplify/SKILL.md +63 -0
- package/skills/skill-tuning/SKILL.md +174 -0
- package/skills/spec-add/SKILL.md +105 -0
- package/skills/spec-load/SKILL.md +98 -0
- package/skills/spec-remove/SKILL.md +74 -0
- package/skills/spec-setup/SKILL.md +75 -0
- package/skills/team-adversarial-swarm/SKILL.md +233 -0
- package/skills/team-adversarial-swarm/scripts/__pycache__/pheromone.cpython-313.pyc +0 -0
- package/skills/team-adversarial-swarm/scripts/__pycache__/scoring.cpython-313.pyc +0 -0
- package/skills/team-adversarial-swarm/scripts/aco.py +473 -0
- package/skills/team-adversarial-swarm/scripts/pheromone.py +144 -0
- package/skills/team-adversarial-swarm/scripts/scoring.py +92 -0
- package/skills/team-adversarial-swarm/scripts/test_aco.py +475 -0
- package/skills/team-arch-opt/SKILL.md +158 -0
- package/skills/team-brainstorm/SKILL.md +171 -0
- package/skills/team-coordinate/SKILL.md +266 -0
- package/skills/team-designer/SKILL.md +160 -0
- package/skills/team-executor/SKILL.md +189 -0
- package/skills/team-frontend/SKILL.md +136 -0
- package/skills/team-frontend-debug/SKILL.md +198 -0
- package/skills/team-interactive-craft/SKILL.md +141 -0
- package/skills/team-issue/SKILL.md +171 -0
- package/skills/team-lifecycle-v4/SKILL.md +209 -0
- package/skills/team-motion-design/SKILL.md +142 -0
- package/skills/team-perf-opt/SKILL.md +175 -0
- package/skills/team-planex/SKILL.md +137 -0
- package/skills/team-quality-assurance/SKILL.md +147 -0
- package/skills/team-review/SKILL.md +147 -0
- package/skills/team-roadmap-dev/SKILL.md +169 -0
- package/skills/team-swarm/SKILL.md +178 -0
- package/skills/team-swarm/scripts/aco.py +473 -0
- package/skills/team-swarm/scripts/pheromone.py +144 -0
- package/skills/team-swarm/scripts/scoring.py +92 -0
- package/skills/team-swarm/scripts/test_aco.py +475 -0
- package/skills/team-tech-debt/SKILL.md +128 -0
- package/skills/team-testing/SKILL.md +143 -0
- package/skills/team-ui-polish/SKILL.md +141 -0
- package/skills/team-uidesign/SKILL.md +144 -0
- package/skills/team-ultra-analyze/SKILL.md +173 -0
- package/skills/team-ux-improve/SKILL.md +151 -0
- package/skills/team-visual-a11y/SKILL.md +156 -0
- package/skills/workflow-skill-designer/SKILL.md +496 -0
- package/src/extension/index.ts +222 -0
- package/src/extension/schemas.ts +131 -0
- package/src/providers/cli-tools-loader.ts +74 -0
- package/src/providers/provider-registry.ts +130 -0
- package/src/tools/delegate.ts +85 -0
- package/src/tools/explore.ts +134 -0
- package/src/tools/moa.ts +213 -0
- package/src/tools/status.ts +99 -0
- package/src/tools/wait.ts +166 -0
|
@@ -0,0 +1,313 @@
|
|
|
1
|
+
# Scholar Rebuttal Pro - 使用指南
|
|
2
|
+
|
|
3
|
+
## 概述
|
|
4
|
+
|
|
5
|
+
**scholar-rebuttal-pro** 是一个增强版的学术论文审稿意见回复 skill,整合了 Agy/CLI 协作分析和多视角讨论机制,用于生成结构化、证据支撑的 rebuttal 文档。
|
|
6
|
+
|
|
7
|
+
## 核心特性
|
|
8
|
+
|
|
9
|
+
### 1. 五阶段工作流
|
|
10
|
+
|
|
11
|
+
```
|
|
12
|
+
Phase 1: 审稿意见解析与分类
|
|
13
|
+
↓ (使用 Agy CLI 语义分析)
|
|
14
|
+
Phase 2: 多视角讨论
|
|
15
|
+
↓ (作者/审稿人/专家三方视角)
|
|
16
|
+
Phase 3: 策略制定
|
|
17
|
+
↓ (Accept/Defend/Clarify/Experiment)
|
|
18
|
+
Phase 4: Rebuttal 撰写
|
|
19
|
+
↓ (会议特定模板 + 专业语气优化)
|
|
20
|
+
Phase 5: 质量验证
|
|
21
|
+
↓ (完整性/专业性/说服力评估)
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
### 2. CLI 协作分析
|
|
25
|
+
|
|
26
|
+
- **Phase 1**: Agy CLI 语义分析,自动分类审稿意见
|
|
27
|
+
- **Phase 2**: 多视角讨论(可选 team-ultra-analyze)
|
|
28
|
+
- **Phase 3**: CLI 搜索论文内容,提取支撑证据
|
|
29
|
+
- **Phase 5**: CLI 质量验证,生成改进建议
|
|
30
|
+
|
|
31
|
+
### 3. 多视角讨论
|
|
32
|
+
|
|
33
|
+
模拟三方视角进行讨论:
|
|
34
|
+
- **作者视角**: 如何最有效回应
|
|
35
|
+
- **审稿人视角**: 什么样的回复最有说服力
|
|
36
|
+
- **领域专家视角**: 技术准确性和学术规范
|
|
37
|
+
|
|
38
|
+
### 4. 会议特定策略
|
|
39
|
+
|
|
40
|
+
支持主流会议模板:
|
|
41
|
+
- **ML Conferences**: NeurIPS/ICML/ICLR
|
|
42
|
+
- **CV Conferences**: CVPR/ECCV/ICCV
|
|
43
|
+
- **NLP Conferences**: ACL/EMNLP
|
|
44
|
+
- **Generic**: 通用模板
|
|
45
|
+
|
|
46
|
+
## 使用方法
|
|
47
|
+
|
|
48
|
+
### 基本调用
|
|
49
|
+
|
|
50
|
+
```bash
|
|
51
|
+
# 方式 1: 直接调用 skill
|
|
52
|
+
scholar-rebuttal-pro
|
|
53
|
+
|
|
54
|
+
# 方式 2: 通过触发词
|
|
55
|
+
"帮我回复审稿意见"
|
|
56
|
+
"respond to reviewers"
|
|
57
|
+
"rebuttal"
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
### 输入格式
|
|
61
|
+
|
|
62
|
+
支持三种输入方式:
|
|
63
|
+
|
|
64
|
+
1. **文件路径**:
|
|
65
|
+
```
|
|
66
|
+
reviews.txt
|
|
67
|
+
reviewer-comments.md
|
|
68
|
+
reviews.pdf
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
2. **内联文本**: 直接粘贴审稿意见
|
|
72
|
+
|
|
73
|
+
3. **结构化 JSON**: 预解析的审稿结构
|
|
74
|
+
|
|
75
|
+
### 交互式配置
|
|
76
|
+
|
|
77
|
+
Skill 启动时会询问三个配置:
|
|
78
|
+
|
|
79
|
+
#### 1. 自动模式
|
|
80
|
+
- **交互模式 (推荐)**: 每阶段后确认,可调整策略
|
|
81
|
+
- **自动模式**: 一次性执行所有阶段
|
|
82
|
+
|
|
83
|
+
#### 2. 论文来源
|
|
84
|
+
- **提供路径**: 指定论文 PDF/LaTeX 路径
|
|
85
|
+
- **当前目录**: 自动搜索当前目录
|
|
86
|
+
- **仅审稿意见**: 不分析论文内容
|
|
87
|
+
|
|
88
|
+
#### 3. 会议类型
|
|
89
|
+
- **ML Conferences**: NeurIPS/ICML/ICLR 策略
|
|
90
|
+
- **CV Conferences**: CVPR/ECCV/ICCV 策略
|
|
91
|
+
- **NLP Conferences**: ACL/EMNLP 策略
|
|
92
|
+
- **Generic**: 通用模板
|
|
93
|
+
|
|
94
|
+
## 输出产物
|
|
95
|
+
|
|
96
|
+
### Phase 1 输出
|
|
97
|
+
- `review-analysis.json` - 结构化分类结果
|
|
98
|
+
- `comment-classification.md` - 人类可读的分类报告
|
|
99
|
+
|
|
100
|
+
### Phase 2 输出
|
|
101
|
+
- `discussion-log.md` - 完整讨论记录
|
|
102
|
+
- `consensus-strategies.json` - 共识策略
|
|
103
|
+
|
|
104
|
+
### Phase 3 输出
|
|
105
|
+
- `strategy-matrix.md` - 策略矩阵
|
|
106
|
+
- `evidence-references.json` - 证据引用
|
|
107
|
+
|
|
108
|
+
### Phase 4 输出
|
|
109
|
+
- `rebuttal.md` - 最终 rebuttal 文档
|
|
110
|
+
- `rebuttal-draft-v1-{timestamp}.md` - 版本化草稿
|
|
111
|
+
|
|
112
|
+
### Phase 5 输出
|
|
113
|
+
- `quality-report.md` - 质量评估报告
|
|
114
|
+
- `improvement-suggestions.json` - 改进建议
|
|
115
|
+
|
|
116
|
+
所有输出文件位于: `.workflow/.scratchpad/`
|
|
117
|
+
|
|
118
|
+
## 架构设计
|
|
119
|
+
|
|
120
|
+
### Orchestrator + Phases 模式
|
|
121
|
+
|
|
122
|
+
```
|
|
123
|
+
scholar-rebuttal-pro/
|
|
124
|
+
├── SKILL.md # 协调器(纯协调逻辑)
|
|
125
|
+
└── phases/
|
|
126
|
+
├── 01-review-parsing.md # Phase 1 完整执行协议
|
|
127
|
+
├── 02-multi-perspective-discussion.md # Phase 2 + Compact Sentinel
|
|
128
|
+
├── 03-strategy-formulation.md # Phase 3 + Compact Sentinel
|
|
129
|
+
├── 04-rebuttal-writing.md # Phase 4 + Compact Sentinel
|
|
130
|
+
└── 05-quality-validation.md # Phase 5 完整执行协议
|
|
131
|
+
```
|
|
132
|
+
|
|
133
|
+
### 渐进式加载
|
|
134
|
+
|
|
135
|
+
- **SKILL.md**: 仅包含协调逻辑和 `Ref:` 标记
|
|
136
|
+
- **Phase 文件**: 按需加载,包含完整执行细节
|
|
137
|
+
- **Compact Recovery**: Phase 2/3/4 包含 sentinel 机制
|
|
138
|
+
|
|
139
|
+
### TodoWrite 模式
|
|
140
|
+
|
|
141
|
+
```json
|
|
142
|
+
// Phase 执行中(任务展开)
|
|
143
|
+
[
|
|
144
|
+
{"content": "Phase 1: Review Parsing", "status": "completed"},
|
|
145
|
+
{"content": "Phase 2: Multi-Perspective Discussion", "status": "in_progress"},
|
|
146
|
+
{"content": " → Author perspective", "status": "in_progress"},
|
|
147
|
+
{"content": " → Reviewer perspective", "status": "pending"},
|
|
148
|
+
{"content": " → Expert perspective", "status": "pending"},
|
|
149
|
+
{"content": "Phase 3: Strategy Formulation", "status": "pending"}
|
|
150
|
+
]
|
|
151
|
+
|
|
152
|
+
// Phase 完成后(任务折叠)
|
|
153
|
+
[
|
|
154
|
+
{"content": "Phase 1: Review Parsing", "status": "completed"},
|
|
155
|
+
{"content": "Phase 2: Multi-Perspective Discussion", "status": "completed"},
|
|
156
|
+
{"content": "Phase 3: Strategy Formulation", "status": "pending"}
|
|
157
|
+
]
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
## CLI 集成示例
|
|
161
|
+
|
|
162
|
+
### Phase 1 - 审稿意见分类
|
|
163
|
+
|
|
164
|
+
```bash
|
|
165
|
+
ccw cli -p "PURPOSE: Parse and classify reviewer comments by type and severity
|
|
166
|
+
TASK: • Parse comment structure • Classify by severity • Extract key concerns
|
|
167
|
+
MODE: analysis
|
|
168
|
+
CONTEXT: @reviews.txt
|
|
169
|
+
EXPECTED: JSON with classification results" \
|
|
170
|
+
--tool agy --mode analysis --rule analysis-analyze-technical-document
|
|
171
|
+
```
|
|
172
|
+
|
|
173
|
+
### Phase 3 - 证据搜索
|
|
174
|
+
|
|
175
|
+
```bash
|
|
176
|
+
ccw cli -p "PURPOSE: Search paper content for evidence supporting response strategies
|
|
177
|
+
TASK: • Locate relevant sections • Extract supporting data • Identify evidence gaps
|
|
178
|
+
MODE: analysis
|
|
179
|
+
CONTEXT: @paper.pdf
|
|
180
|
+
EXPECTED: Evidence map with file:line references" \
|
|
181
|
+
--tool agy --mode analysis
|
|
182
|
+
```
|
|
183
|
+
|
|
184
|
+
### Phase 5 - 质量验证
|
|
185
|
+
|
|
186
|
+
```bash
|
|
187
|
+
ccw cli -p "PURPOSE: Validate rebuttal quality (completeness, professionalism, persuasiveness)
|
|
188
|
+
TASK: • Check all comments addressed • Assess tone • Evaluate evidence strength
|
|
189
|
+
MODE: analysis
|
|
190
|
+
CONTEXT: @rebuttal.md
|
|
191
|
+
EXPECTED: Quality report with improvement suggestions" \
|
|
192
|
+
--tool agy --mode analysis
|
|
193
|
+
```
|
|
194
|
+
|
|
195
|
+
## 会议特定策略
|
|
196
|
+
|
|
197
|
+
### NeurIPS/ICML/ICLR (ML Conferences)
|
|
198
|
+
- 强调概念新颖性和 broader impact
|
|
199
|
+
- 理论严谨性和方法论贡献
|
|
200
|
+
- 实验彻底性和局限性讨论
|
|
201
|
+
|
|
202
|
+
### CVPR/ECCV/ICCV (CV Conferences)
|
|
203
|
+
- 严格一页限制
|
|
204
|
+
- 禁止外部链接
|
|
205
|
+
- Champion 审稿人策略
|
|
206
|
+
|
|
207
|
+
### ACL/EMNLP (NLP Conferences)
|
|
208
|
+
- 语言学意义和适当性
|
|
209
|
+
- 伦理考量和数据来源
|
|
210
|
+
- 实用性和可扩展性
|
|
211
|
+
|
|
212
|
+
### Generic Template
|
|
213
|
+
- 适用于所有会议的通用策略
|
|
214
|
+
- 四大响应策略: Accept/Defend/Clarify/Experiment
|
|
215
|
+
- 五大成功模式(基于 ICLR Spotlight 论文分析)
|
|
216
|
+
|
|
217
|
+
## 最佳实践
|
|
218
|
+
|
|
219
|
+
### 1. 准备工作
|
|
220
|
+
- 准备审稿意见文件(txt/md/pdf)
|
|
221
|
+
- 准备论文源文件(PDF/LaTeX)
|
|
222
|
+
- 了解目标会议的特定要求
|
|
223
|
+
|
|
224
|
+
### 2. 执行流程
|
|
225
|
+
- 使用交互模式(推荐)以便在每阶段后调整
|
|
226
|
+
- 仔细审查 Phase 2 的多视角讨论结果
|
|
227
|
+
- 在 Phase 3 验证证据引用的准确性
|
|
228
|
+
- Phase 4 后人工审查 rebuttal 草稿
|
|
229
|
+
- 根据 Phase 5 的改进建议优化
|
|
230
|
+
|
|
231
|
+
### 3. 质量保证
|
|
232
|
+
- 确保所有审稿意见都有回应
|
|
233
|
+
- 每个回应都有充分的证据支撑
|
|
234
|
+
- 保持专业、尊重的语气
|
|
235
|
+
- 避免过度承诺(只承诺可行的改进)
|
|
236
|
+
|
|
237
|
+
### 4. 会议特定注意事项
|
|
238
|
+
- **NeurIPS**: 强调 broader impact 和伦理考量
|
|
239
|
+
- **ICML**: 突出理论贡献和数学证明
|
|
240
|
+
- **ICLR**: 详细讨论局限性,披露 LLM 使用
|
|
241
|
+
- **CVPR**: 严格遵守一页限制,不使用外部链接
|
|
242
|
+
- **ACL**: 强调语言学意义和伦理声明
|
|
243
|
+
|
|
244
|
+
## 故障排除
|
|
245
|
+
|
|
246
|
+
### 问题 1: CLI 执行失败
|
|
247
|
+
**解决方案**: 检查 `~/.claude/cli-tools.json` 配置,确保 agy 工具已启用
|
|
248
|
+
|
|
249
|
+
### 问题 2: 论文路径无效
|
|
250
|
+
**解决方案**: 使用"仅审稿意见"模式,手动提供证据
|
|
251
|
+
|
|
252
|
+
### 问题 3: 会议模板未找到
|
|
253
|
+
**解决方案**: 使用 Generic 模板,手动调整会议特定要求
|
|
254
|
+
|
|
255
|
+
### 问题 4: Phase 执行中断
|
|
256
|
+
**解决方案**: Skill 支持断点恢复,重新调用会从中断处继续
|
|
257
|
+
|
|
258
|
+
## 扩展性
|
|
259
|
+
|
|
260
|
+
### 添加新会议模板
|
|
261
|
+
|
|
262
|
+
1. 在 `G:\github_lib\claude-scholar\skills\review-response\references\` 添加模板
|
|
263
|
+
2. 或在 `d:\ccws\.workflow\参考文档1\` 添加自定义模板
|
|
264
|
+
3. Phase 4 会自动搜索并加载
|
|
265
|
+
|
|
266
|
+
### 自定义响应策略
|
|
267
|
+
|
|
268
|
+
编辑 Phase 3 的策略映射规则,添加新的响应类型。
|
|
269
|
+
|
|
270
|
+
### 集成其他 CLI 工具
|
|
271
|
+
|
|
272
|
+
修改 Phase 1/3/5 的 CLI 调用,替换 `--tool agy` 为其他工具(qwen/codex)。
|
|
273
|
+
|
|
274
|
+
## 相关 Skills
|
|
275
|
+
|
|
276
|
+
- **scholar-review**: 论文自审和审稿流程
|
|
277
|
+
- **scholar-writing**: 端到端论文撰写
|
|
278
|
+
- **scholar-publish**: 会后准备(演讲/海报)
|
|
279
|
+
|
|
280
|
+
## 技术细节
|
|
281
|
+
|
|
282
|
+
### Compact Recovery 机制
|
|
283
|
+
|
|
284
|
+
Phase 2/3/4 包含 compact sentinel,防止长上下文压缩导致协议丢失:
|
|
285
|
+
|
|
286
|
+
```markdown
|
|
287
|
+
> **📌 COMPACT SENTINEL [Phase 2: multi-perspective-discussion]**
|
|
288
|
+
> This phase contains 4 execution steps (Step 2.1 — 2.4).
|
|
289
|
+
> If you can read this sentinel but cannot find the full Step protocol below, context has been compressed.
|
|
290
|
+
> Recovery: `Read("phases/02-multi-perspective-discussion.md")`
|
|
291
|
+
```
|
|
292
|
+
|
|
293
|
+
### Checkpoint 验证
|
|
294
|
+
|
|
295
|
+
关键执行步骤前包含 checkpoint:
|
|
296
|
+
|
|
297
|
+
```markdown
|
|
298
|
+
> **⚠️ CHECKPOINT**: Before proceeding, verify:
|
|
299
|
+
> 1. This phase is TodoWrite `in_progress` (active phase protection)
|
|
300
|
+
> 2. Full protocol (Step N.X — N.M) is in active memory, not just sentinel
|
|
301
|
+
> If only sentinel remains → `Read("phases/0N-xxx.md")` now.
|
|
302
|
+
```
|
|
303
|
+
|
|
304
|
+
## 版本信息
|
|
305
|
+
|
|
306
|
+
- **Skill Version**: 1.0.0
|
|
307
|
+
- **Created**: 2026-03-02
|
|
308
|
+
- **Based on**: claude-scholar review-response skill
|
|
309
|
+
- **Enhancements**: CLI integration, multi-perspective discussion, conference templates
|
|
310
|
+
|
|
311
|
+
## 贡献与反馈
|
|
312
|
+
|
|
313
|
+
如需改进或报告问题,请联系项目维护者。
|