Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AkaliKong/PaperClaw --skill paper-human-reviewgit clone --depth 1 https://github.com/AkaliKong/PaperClawWrote 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/akalikong/paperclaw/paper-human-review)<a href="https://agentmods.dev/skills/akalikong/paperclaw/paper-human-review"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-human-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/akalikong/paperclaw/paper-human-review"><img src="https://agentmods.dev/badge/skills/akalikong/paperclaw/paper-human-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 | $0.00061 | $0.01317 |
| Opus 5 | $0.00030 | $0.00659 |
| Sonnet 5 | $0.00012 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00132 |
Grade A, and why
paper-human-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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Human Review — 对话式交互 + 异步状态机
概述
本 Skill 拦截边缘分数(4-6 分)论文,生成信息卡片供人工审阅。支持两种交互模式:
- 对话式实时交互(Agent 编排模式首选):Agent 在对话中展示卡片 → 用户回复 accept/reject → Agent 调用
--chat-decide - 异步状态机(cron 场景兜底):脚本生成卡片后挂起 → 用户异步编辑 JSON →
--merge恢复
⚠️ 关键规则
- 对话式交互优先:在对话中,Agent 应展示审阅卡片并收集用户决策,不挂起 Pipeline。
- 异步不阻塞:cron 场景下脚本生成卡片、写入等待状态后立即 Exit 0 退出。
- 三模式脚本:
--init(生成卡片)、--chat-decide(对话式决策)、--merge(文件式决策)。 - 无边缘论文时跳过:如果没有边缘论文,直接复制高分论文到输出。
工作流程
对话式交互流程(Agent 编排模式首选)
Step 1: 初始化审阅
python $PAPER_AGENT_ROOT/scripts/human_review.py --init --run-id {run_id}
脚本返回 JSON,其中 compact_cards 字段包含适合对话展示的精简卡片。
Step 2: Agent 展示卡片
在对话中将 compact_cards 内容展示给用户,示例:
发现 3 篇边缘论文需要您判断:
📄 [1] (5pts) Semantic ID Generation for Recommendation
ID: 2603.01234 [generative_rec, semantic_id]
This paper proposes a novel approach to generate semantic...
📄 [2] (4pts) Collaborative Filtering with Transformers
ID: 2603.05678 [collaborative_filtering]
We present a transformer-based collaborative filtering...
请回复 accept/reject 决定,例如:
"accept 1, reject 2"
或 "accept all" / "reject all"
Step 3: 收集用户决策
等待用户回复。用户可能以多种方式回复:
- "accept 1, reject 2, accept 3"
- "accept 论文A, reject 论文B"
- "accept all"
- "reject all"
Step 4: Agent 解析决策并调用脚本
将用户回复解析为标准 JSON 格式,调用:
python $PAPER_AGENT_ROOT/scripts/human_review.py --chat-decide '[{"arxiv_id":"2603.01234","decision":"accept"},{"arxiv_id":"2603.05678","decision":"reject"}]' --run-id {run_id}
脚本将合并高分论文与捞回论文,输出 skill3_final_selection.json。
异步状态机流程(cron 场景兜底)
默认模式 — 生成卡片并挂起
python $PAPER_AGENT_ROOT/scripts/human_review.py --init --run-id {run_id}
脚本将:
- 从
skill2_scored_results.json读取边缘区论文 - 生成信息卡片(Markdown 文件 + stdout 精简格式)
- 输出
skill3_review_pending.json - 如果在 cron 模式,更新
pipeline_state.json为waiting_for_human - 尝试通过 webhook 通知用户
- Exit 0 退出,不阻塞
用户异步审阅
用户创建 skill3_human_decisions.json:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 143 lines · 61 tokens per session scan A 498e71cc6f88
paper-human-review is a skill published in the GitHub repository AkaliKong/PaperClaw (22 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 1,317 once invoked, about $0.0003 per session on Opus 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…