Borrowing it
Nothing to install: this file belongs to dengls24/annota. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dengls24/annota/master/.claude/skills/annota-review/SKILL.mdgit clone --depth 1 https://github.com/dengls24/annotaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dengls24/annota/annota-review)<a href="https://agentmods.dev/skills/dengls24/annota/annota-review"><img src="https://agentmods.dev/badge/skills/dengls24/annota/annota-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dengls24/annota/annota-review"><img src="https://agentmods.dev/badge/skills/dengls24/annota/annota-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.00997 |
| Opus 5.5 | $0.00034 | $0.00399 |
| Sonnet 5.5 | $0.00017 | $0.00199 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
annota-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
论文审阅
以顶会审稿人视角审阅一篇学术论文，输出结构化评审报告。
输入解析
用户输入：$ARGUMENTS
提取：
- 目标论文：PDF 路径或标题
- 目标会议（可选）：如 MICRO、ISCA、HPCA、ASPLOS、DAC 等。默认按通用学术标准。
工作流程
Step 1：获取论文
用 search_zotero_items 或直接路径定位 PDF。
用 get_item_metadata 获取元数据。
Step 2：提取全文
调用 get_pdf_text_bulk(item_id, skip_refs=True) 提取正文。
Step 3：深度审阅
仔细阅读全文，从以下维度评估：
评分维度（1-5 分）
| 维度 | 评估标准 |
|---|---|
| Novelty (新颖性) | 研究问题和解决方案的原创性 |
| Technical Quality (技术质量) | 方法的正确性、严谨性、完整性 |
| Significance (重要性) | 对领域的潜在影响和实用价值 |
| Clarity (表达清晰度) | 写作质量、图表质量、逻辑连贯性 |
| Experimental Evaluation (实验评估) | 实验设计、baseline 选择、结果可信度 |
Step 4：生成审阅报告
按以下格式输出：
## 审阅报告
### 论文信息
- 标题：{title}
- 作者：{authors}
- 目标会议：{venue}
### 总体评价
Overall Score: X/5
Recommendation: [Strong Accept / Accept / Weak Accept / Borderline / Weak Reject / Reject]
一段话总结论文核心贡献和主要问题。
### 分维度评分
- Novelty: X/5 — 简要说明
- Technical Quality: X/5 — 简要说明
- Significance: X/5 — 简要说明
- Clarity: X/5 — 简要说明
- Experimental Evaluation: X/5 — 简要说明
### 优点 (Strengths)
1. [S1] ...
2. [S2] ...
3. [S3] ...
### 缺点 (Weaknesses)
1. [W1] ...
2. [W2] ...
3. [W3] ...
### 详细意见 (Detailed Comments)
逐节给出具体修改建议，包括：
- 引言部分：motivation 是否清晰？
- 方法部分：技术方案是否完整？有无漏洞？
- 实验部分：baseline 是否充分？实验设计是否合理？
- 写作：是否有语法错误、表述不清的地方？
### 小问题 (Minor Issues)
- 具体页码和行的小问题列表
### 给作者的建议
如果要修改重投，最应该改进的 3 个方面。
Step 5：可选 — 保存为笔记
询问用户是否要将审阅报告保存为 Zotero 子笔记。
如果是，用 add_child_note 保存（HTML 格式）。
Step 6：可选 — 标注关键问题
询问用户是否要在 PDF 中标注发现的问题：
- 技术问题标红色
#ff6666 - 写作问题标黄色
#ffd400 - 亮点标绿色
#28CA42
如果是，执行 /annota-annotate 的两阶段流程。
审阅原则
- 建设性：指出问题的同时给出改进方向
- 具体：不说"实验不够充分"，而说"缺少与 XXX 的对比"
- 公正：不因写作风格或语言问题过度扣分
- 专业：评价基于技术内容，不涉及个人偏好
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 123 lines · 85 tokens per session scan A 62d2953c2d6b
annota-review is a skill published in the GitHub repository dengls24/annota (20 stars, last pushed 6mo ago), licensed MIT. It adds 85 tokens to every session and 997 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review-response
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
debug
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing…
paper-writing
Use when the user wants to write, structure, or revise academic paper sections, improve notation consistency, or refine figures and tables. Triggers on phrases like "write the abstract", "structure the methods", "improve this section", "notation consistency", "figure refinement", or "paper structure".
reproduce
End-to-end paper reproduction from arxiv URL through smoke runs to replication experiments. Handles missing or partial official code, missing training scripts, missing hyperparameters, and private datasets via similar-public-dataset substitution. Use when the user asks to reproduce, implement, replicate, or re-run a…
research-publishing
Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".
academic-research
Use when drafting citation-bearing academic writing or revising empirical claims. Nested swiss-knife reference for source verification and keeping manuscript claims anchored to data, not reviewer consensus.