Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/yipng05-max/-skills/top-journals-methods-scout)<a href="https://agentmods.dev/skills/yipng05-max/-skills/top-journals-methods-scout"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/top-journals-methods-scout/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/yipng05-max/-skills/top-journals-methods-scout"><img src="https://agentmods.dev/badge/skills/yipng05-max/-skills/top-journals-methods-scout.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 | $0.00335 | $0.03468 |
| Opus 5 | $0.00168 | $0.01734 |
| Sonnet 5 | $0.00067 | $0.00694 |
| Haiku 4.5 | $0.00034 | $0.00347 |
Grade A, and why
top-journals-methods-scout 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 11d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
顶刊研究方法扫描工具（Top Journals Methods Scout）
面向课程策划与方法教学的顶刊方法扫描工具。默认输入：什么都不说—— 本 skill 会自动用 14 大学科分区顶刊清单 + 近 24 个月 + AI 单独成章。
设计现实（先读这段）
第一次试跑时低估了数据规模——14 个学科分区近 24 个月的顶刊发文约 10,000 篇（AHR/Q&Q 等刊发文量大是主因）。对 10k 篇做逐篇 LLM 深度编码既不经济也不必要。因此本 skill 的实际主路径是：
- 启发式规则编码（
heuristic_classify.py）——对全库打 L1 家族标签 + AI 识别，覆盖快 - Python 生成统计骨架（
generate_outputs.py）——Excel 矩阵 + Markdown 自动统计章节 - 主 agent 写分析层（补一份
methods_report_analysis.md）——用启发式统计做依据，写摘要、新兴方法、AI 专章、教学模块建议
LLM 深度编码只用于特定子集（如用户聚焦某学科、或对某 50 篇做教学候选精选）。
依赖
pip install openpyxl
OpenAlex API 免费、无需 key；脚本已内置重试限速。
第一步：需求确认（≤ 3 问）
用简明清单向用户确认（不要开放问卷式追问）：
- 学科范围：默认全部 14 类；是否只要其中几类？
- 时间窗口：默认近 24 个月；是否调整为 12/36/48 个月？
- AI 聚焦度：默认 AI 单独成章 + 常规方法并行；是否纯 AI 方法扫描？
用户回"默认"就直接下一步。
向用户坦诚成本：全学科 24 个月扫约 10k 篇，抓取 5-10 分钟、启发式编码 1 分钟、统计生成 10 秒、分析写作由主 agent 完成。总耗时约 15-20 分钟。
第二步：OpenAlex 抓取
mkdir -p /tmp/methods_scout
python3 /Users/songyiping/.claude/skills/top-journals-methods-scout/scripts/fetch_journal_papers.py \
--journals-file /Users/songyiping/.claude/skills/top-journals-methods-scout/references/journals.json \
--months 24 \
--out /tmp/methods_scout/papers.json
只要某几个学科追加 --disciplines sociology ai_social_intersection ...。
脚本已内置指数退避重试（5 次），网络抖动不会中断。单次抓取 5-10 分钟。完成后报告总数与分学科分布。
第三步：启发式方法编码（主路径）
python3 /Users/songyiping/.claude/skills/top-journals-methods-scout/scripts/heuristic_classify.py \
--papers /tmp/methods_scout/papers.json \
--out /tmp/methods_scout/classifications.json
内置规则（详见 scripts/heuristic_classify.py 里的 METHOD_RULES 与 AI_OBJECT_RULES）：
- 扫 title + abstract + keywords + concepts + topics 的拼接文本
- 按规则优先级匹配 L1 标签（AI 方法先于普通方法以保证 LLM 辅助定性研究正确识别）
- AI 识别：tool（用 AI）/ object（研究 AI）/ hybrid / n/a
- 输出包含规则命中证据片段（在
notes列）
编码结果典型特征：
- 未匹配率 60-75%（人文历史论文摘要通常不写方法）——正常
- AI 识别率通常 5-10%
- L1 分布最常见：qual.ethnography / qual.interview / ai.llm / quant.experiment / quant.survey
不需要 LLM 逐篇编码。如果用户后续要求对某子集做深度编码，再调 LLM（见 §补充路径）。
What ships with it
8 files 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.
- references/ai_method_taxonomy.md 4.7 KB
- references/excel_schema.md 3.3 KB
- references/journals.json 6.0 KB
- references/method_taxonomy.md 3.7 KB
- references/report_template.md 4.4 KB
- scripts/fetch_journal_papers.py 6.8 KB runs code
- scripts/generate_outputs.py 16 KB runs code
- scripts/heuristic_classify.py 15 KB runs code
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.
- 11d ago First seen · 256 lines · 335 tokens per session scan A bd36813e5e8b
top-journals-methods-scout is a skill published in the GitHub repository yipng05-max/-skills (285 stars, last pushed 4mo ago), licensed MIT. It adds 335 tokens to every session and 3,468 once invoked, about $0.0017 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…
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…
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.
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…