Awesome Journal Skills is a collection of agent skill packs tailored to hundreds of academic journals across fields including economics, social science, medicine, science, and engineering. Researchers use the packs for tasks such as choosing topics, designing empirical strategies, preparing tables and figures, submitting papers, and responding to reviewers. The catalogue entries are the project's journal-specific skills and related plugins.
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 brycewang-stanford/Awesome-Journal-Skills --skill aejpol-referee-strategygit clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-SkillsWrote 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/brycewang-stanford/awesome-journal-skills/aejpol-referee-strategy)<a href="https://agentmods.dev/skills/brycewang-stanford/awesome-journal-skills/aejpol-referee-strategy"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/aejpol-referee-strategy/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/brycewang-stanford/awesome-journal-skills/aejpol-referee-strategy"><img src="https://agentmods.dev/badge/skills/brycewang-stanford/awesome-journal-skills/aejpol-referee-strategy.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 | $0.00079 | $0.01159 |
| Opus 5 | $0.00039 | $0.00580 |
| Sonnet 5 | $0.00016 | $0.00232 |
| Haiku 4.5 | $0.00008 | $0.00116 |
Grade A, and why
aejpol-referee-strategy 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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referee Strategy — Reading the Manuscript as an AEJ: Policy Referee (aejpol-referee-strategy)
When to trigger
- Before submitting: you want to find the objections a referee will raise first
- Deciding whether the paper is ready or needs another round of work
- Calibrating expectations about the AEA single-blind process and timeline
- Triaging which weaknesses to fix vs. disclose before submission
How AEJ: Policy referees read
AEJ: Policy reviews are single-blind through the AEA system (referees see the authors; authors do not see referees), refereed by economists who expect both credible causal evidence and a policy-relevant welfare reading. A referee typically tests four things in order; a paper dies at the first one it fails:
- Is it a policy paper of broad interest? (the
aejpol-topic-selectiontest) — a clean estimate with no policy lever or welfare reading invites a "better suited to a field journal / AEJ: Applied" rejection. - Is the causal claim credible? (the
aejpol-identificationtest) — staggered TWFE, asserted parallel trends, a weak instrument, or an over-generalized RDD are the usual kill shots. - Does the welfare/policy reading follow? (the
aejpol-theory-modeltest) — a hand-waved "this is welfare-improving" or a sufficient-statistic formula whose assumptions are violated. - Is it robust and reproducible? (the
aejpol-robustness/aejpol-replication-packagetests).
Pre-empting the predictable objections
| Likely referee objection | Pre-emption to build before submitting |
|---|---|
| "This isn't a policy paper / not broad-interest" | Lead with the policy question + welfare stake; state the cost-benefit reading in the abstract |
| "Staggered TWFE is biased here" | Heterogeneity-robust DID + Bacon decomposition + flat leads, in the main paper |
| "Parallel trends is assumed, not shown" | Event-study leads + honest-DID bounds |
| "Exclusion restriction is not credible" | Institutional + theoretical defense + falsification |
| "The welfare claim is hand-waved" | Explicit sufficient-statistic / MVPF / cost-benefit derivation |
| "External validity is unclear" | Heterogeneity by setting; explicit scope of the policy lesson |
| "Effect is significant but tiny / not policy-relevant" | Benchmark the magnitude against budget / status quo |
| "Not reproducible / data unavailable" | AEA-compliant package + restricted-data access path ready |
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.
- 7d ago First seen · 72 lines · 0 tokens per session scan A e85504dca5b3
aejpol-referee-strategy is a skill published in the GitHub repository brycewang-stanford/Awesome-Journal-Skills (1,142 stars, last pushed 7d ago), licensed MIT. It adds 79 tokens to every session and 1,159 once invoked, about $0.0004 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 2026-09-15.
Other skills, from other repositories
alterlab-qiime2-amplicon
Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 amplicon distribution (2026.1; renamed to "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier classify-sklearn against a…
alterlab-pyhealth
Develops, tests, and deploys clinical machine learning models with the PyHealth healthcare AI toolkit. Use when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare…
alterlab-phylogenetics
Build phylogenetic trees end-to-end from raw sequences — MAFFT multiple sequence alignment, optional TrimAl trimming, IQ-TREE 2 maximum-likelihood inference with model selection and bootstraps, FastTree for large datasets, then visualize with ETE3 or FigTree. Use when reconstructing trees from sequences (FASTA) for…
alterlab-pydicom
Reads, writes, and manipulates DICOM (Digital Imaging and Communications in Medicine) medical imaging files with the pydicom Python library. Use when reading/writing/modifying DICOM data, extracting pixel data from CT, MRI, X-ray, or ultrasound images, anonymizing DICOM files, working with DICOM metadata and tags…
alterlab-eda
Exploratory data analysis (EDA) on a scientific data file — auto-detects the format, runs structure/quality/statistics checks, and writes a markdown EDA report with downstream recommendations. Use when asked to "explore", "analyze", "summarize", "profile", or "QC" a data file, or to understand its…
alterlab-shap
Model interpretability and explainability with SHAP (SHapley Additive exPlanations) — feature importance and plots (waterfall, beeswarm, bar, scatter, force, heatmap). Use when explaining ML model predictions, computing feature importance, debugging models, analyzing bias or fairness, comparing models, or implementing…