joshua-zyy/academic-paper-writer / skills/academic-polishing
academic-polishing
VerifiedPolish academic prose, de-AI-ify text, control claim strength, or rewrite method sections for CS/AI/ML papers. Executes Prose Quality Gate, Claim Strength Audit, and de-AI pass. Use when: removing AI writing patterns from paper text, adjusting claim strength to match evidence level, rewriting method sections with proper narrative flow, improving academic writing quality, checking for overclaiming. Triggers on: 润色, polish, improve writing, 去AI, de-AI, claim strength, 改写, rewrite method, prose quality, 降级表述, remove AI patterns, academic writing polish, 学术润色, 去AI化, 降级结论, improve prose.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.3 KB |
| manifest.yaml | config | 1.4 KB |
| references/claim-strength.md | markdown | 4.8 KB |
| references/de-ai-patterns.md | markdown | 4.9 KB |
| references/method-narrative.md | markdown | 2.7 KB |
| references/phrasebank-playbook.md | markdown | 10.0 KB |
| references/section-moves.md | markdown | 14.4 KB |
| static/core/anti-patterns.md | markdown | 578 B |
| static/core/output-contract.md | markdown | 841 B |
| static/core/red-lines.md | markdown | 671 B |
| static/core/stance.md | markdown | 4.3 KB |
references/method-narrative.md
View on GitHub# Method 专项叙事强化
## 目标
将 Method section 从"公式罗列 + 模块说明"改写为"学术论证 prose",读起来像论文正文,而非代码讲解或提纲扩写。
## 核心叙事结构
对每个核心 / 非显然设计选择的模块,默认叙述顺序为:
```
1. 该模块在整体流水线中承担什么职责
2. 它为何需要存在,针对什么问题/瓶颈
3. 为什么采用这种具体设计,而不是更直接或更常见的替代方案
4. 核心机制、信息流、公式或算子定义
5. 该设计预期带来的收益
6. 该设计的边界、代价或未覆盖问题
```
简称:"问题 → 设计 → 机制 → 收益/边界"。
对标准 / 支撑性组件,可简写为:作用 + 输入输出 + 核心操作。不要对所有模块平均用力。
## 模块段首规范
正文中优先使用以下开头方式(直接落在"该模块解决什么问题"):
- "为缓解……问题,本文……"
- "考虑到……,本文采用……"
- "与……相比,该设计……"
- "为使……能够……,我们进一步……"
禁止使用:
- "在这一节中,我们将介绍……"(元评论)
- "该模块的代码实现如下……"(代码讲解)
- "该设计的合理性在于……"(审稿人对话口吻)
## 推断降级规则
若设计动机只能从问题缺口、模块输入输出或实现结构做有限推断,正文必须显式降级语气:
| 较差写法 | 推荐写法 |
|---------|---------|
| 从当前实现看,这一设置的意图是…… | 为缓解……,本文采用…… |
| 该设计的合理性在于…… | 这种设置使……,但同时…… |
| 一个合理解释是…… |(若证据不足,移入 sidecar 或改为 [RATIONALE_NEEDED: ...]) |
| 当前代码表明…… |(若证据不足,移入 sidecar 或改为 [RATIONALE_NEEDED: ...]) |
规则:若去掉"从实现看 / 一个合理解释是 / 当前代码表明"后某个动机无法成立 → 证据不足 → 不写进 Paper Body,改为 sidecar 或 [RATIONALE_NEEDED: ...]。
## Method Prose Rewrite 检查清单
- [ ] 每个核心模块段首是否直接落在"该模块解决什么问题"
- [ ] 是否形成"问题 → 设计 → 机制 → 收益/边界"叙事
- [ ] 是否清除了公式罗列(公式服务于论证,而非替代论证)
- [ ] 是否不存在"从实现看""一个合理解释是"等推断降级不充分的口吻
- [ ] 是否不存在元评论、代码讲解、审稿人对话口吻
- [ ] 强推断结论是否使用了论文句式("为缓解……,本文采用……")
- [ ] 弱推断结论是否移入 sidecar 或改为 [RATIONALE_NEEDED: ...]
全部通过 → `method_prose_debt: closed`;任一项失败 → 继续改写。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |