New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Jimf Empirical Design

by brycewang-stanford in brycewang-stanford/Awesome-Journal-Skills

A skill your agent uses when the cross-country/time-series data construction, sample, frequency, or measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck.

MITAuto-check passedData & Analytics

Install Jimf Empirical Design

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jimf-empirical-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills jimf-empirical-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Journal-of-International-Money-and-Finance-Skills/skills/jimf-empirical-design .claude/skills/jimf-empirical-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jimf-empirical-design
GitHub stars
1.2k
Token cost
~2.4k tokens
SKILL.md length
1,215 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the cross-country/time-series data construction, sample, frequency, or measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck.

  • Works in 5 steps: Declare the country set and the split.… → Anchor the sample period to the… → Resolve the frequency mismatch… → …
  • The cross-country/time-series data construction
  • SKILL.md covers When to trigger, The JIMF data-design bar, Design moves that read as… and Execution bridge (StatsPAI /…, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Jimf Empirical Design is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when the cross-country/time-series data construction, sample, frequency, or measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck. Builds the international dataset and measurement; it does not establish causality (jimf-identification) or run robustness (jimf-robustness).

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Forecasting and time series. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.

When your agent uses it

  • The cross-country/time-series data construction
  • Measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck

Example prompts

  • “/jimf-empirical-design”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Declare the country set and the split. State advanced vs. emerging, why each country is in, and report results separately if the mechanism…
  2. Anchor the sample period to the institutional history. Bretton-Woods break, euro introduction, GFC, ZLB, taper tantrum, COVID — say which…
  3. Resolve the frequency mismatch explicitly. If the shock is daily and the outcome quarterly, state the aggregation; if you use mixed…
  4. Defend the exchange-rate convention. Distinguish a dollar effect from a general exchange-rate effect; report NEER/REER alongside USD when…
  5. Document sources to the series level. BIS, IMF IFS/BoP, IMF AREAER (capital-account openness), EPFR, Datastream/Bloomberg…

What it can do on your machine

Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jimf Empirical Design loads about 2.4k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 1,215 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 1,215 words, ~2,440 tokens.

Download SKILL.mdSave it as .claude/skills/jimf-empirical-design/SKILL.md (or your agent's skills folder).
name
jimf-empirical-design
description
Use when the cross-country/time-series data construction, sample, frequency, or measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck. Builds the international dataset and measurement; it does not establish causality (jimf-identification) or run robustness (jimf-robustness).

Empirical Design (jimf-empirical-design)

When to trigger

  • A cross-country panel is unbalanced, mixes incompatible series, or pools regimes that should be separated
  • Frequency and alignment are unclear (daily FX vs. monthly flows vs. quarterly macro) and the design glosses the mismatch
  • Key variables (exchange rate, capital flows, sovereign spread, pass-through) are measured in a way a referee will dispute
  • Country coverage, the advanced-vs-emerging split, or sample period drives the result and is not justified
  • Standard data quirks (USD vs. trade-weighted FX, gross vs. net flows, BoP vs. EPFR, nominal vs. real) are not pinned down

The JIMF data-design bar

International-finance referees scrutinize measurement and comparability as hard as identification, because cross-country data are heterogeneous and easy to mis-align. Three recurring fault lines: (1) which series — there are several defensible measures of every JIMF object, and the choice matters; (2) which countries and period — advanced vs. emerging, pre- vs. post-GFC, in-vs-out of a crisis window; (3) what frequency and alignment — mixing frequencies without saying how. Make each explicit and defend it before the result.

JIMF objectMeasurement choices to declareCommon referee objection
Exchange ratebilateral USD vs. NEER/REER; nominal vs. real; end-of-period vs. average"Your result is a dollar effect, not an exchange-rate effect"
Capital flowsgross vs. net; BoP (quarterly) vs. EPFR (high-frequency fund flows); by instrument (debt/equity/bank)"EPFR is fund flows, not balance-of-payments flows"
Pass-throughimport prices vs. CPI; aggregate vs. invoicing-currency level; horizon of pass-through"Aggregate ERPT hides the dominant-currency margin"
Sovereign riskCDS vs. EMBI/bond spread vs. rating; local- vs. foreign-currency debt"LC and FC sovereign risk are different objects"
Global financial cycleVIX vs. a factor (Miranda-Agrippino–Rey) vs. US shadow rate"VIX is a proxy, not the GFCy"
Monetary stancepolicy rate vs. shadow rate vs. surprise; domestic vs. foreign"The ZLB period breaks your policy-rate measure"

Design moves that read as JIMF-competent

  1. Declare the country set and the split. State advanced vs. emerging, why each country is in, and report results separately if the mechanism differs — pooling AE and EM without a test invites rejection.
  2. Anchor the sample period to the institutional history. Bretton-Woods break, euro introduction, GFC, ZLB, taper tantrum, COVID — say which regimes your window spans and whether you split them.
  3. Resolve the frequency mismatch explicitly. If the shock is daily and the outcome quarterly, state the aggregation; if you use mixed frequency, justify it (MIDAS / local projections at the native frequency).
  4. Defend the exchange-rate convention. Distinguish a dollar effect from a general exchange-rate effect; report NEER/REER alongside USD when the claim is about the exchange rate per se.
  5. Document sources to the series level. BIS, IMF IFS/BoP, IMF AREAER (capital-account openness), EPFR, Datastream/Bloomberg, Lane–Milesi-Ferretti external positions, Ilzetzki–Reinhart–Rogoff regime classification — name the exact vintage and any splicing.

Execution bridge (StatsPAI / Stata MCP)

Run the asset-pricing battery, don't just specify it. Full map: execution-with-mcp. JIMF is international macro-finance; cross-country panels + asset pricing — identification plus factor/Newey-West inference.

  • Factor regressions / time-series alphas: feols with the right SEs (Newey–West / clustered) — read the alpha and t off the return.
  • Factor-zoo haircut: after disclosing how many signals were screened, apply romano_wolf / benjamini_hochberg and report the alpha that survives.
  • Fama–MacBeth + Shanken EIV are Stata-canonical — run via mcp__stata-mcp__stata_do with the vendored resources/code/ (asreg / xtfmb).
  • Exhibits: etable; hand formatting to the tables/figures skill.

Report the economic magnitude (bps/month alpha, Sharpe gain); full factor grid → appendix. JF execution walkthrough.

Checklist

  • Country set justified; AE/EM split reported or its absence defended
  • Sample period mapped to international monetary history; regime breaks handled (split or controlled)
  • Each JIMF object measured with a declared, defended choice (USD vs. NEER, gross vs. net, CDS vs. spread)
  • Frequency alignment stated; mixed-frequency method named if used
  • Data sources named to the series and vintage; splicing/cleaning documented for audit
  • A dollar effect is not mislabeled as an exchange-rate effect (and vice versa)
  • Sample-construction steps reproducible enough for the online appendix and Mendeley Data deposit

Anti-patterns

  • Pooling advanced and emerging economies with no test for whether the mechanism is common
  • Using EPFR fund flows and calling them balance-of-payments capital flows (or vice versa) without flagging the difference
  • A "global financial cycle" measured only by VIX with no acknowledgment it is a proxy
  • An unbalanced panel where entry/exit of countries correlates with the outcome (crisis countries dropping out)
  • Spanning the GFC and ZLB with a single policy-rate measure and no regime control
  • Hiding the exchange-rate convention so a dollar-specific result reads as a general exchange-rate result
Show full SKILL.md (477 more words)Show less

Worked vignette (illustrative)

A draft regresses quarterly EM "capital flows" on a daily US surprise and finds a strong effect, but the flows are EPFR weekly fund flows aggregated to quarters and the panel drops three countries during their crises. The JIMF fix: state that EPFR captures benchmarked-fund flows (a leading indicator), not BoP flows, and either align the analysis at the native weekly frequency via local projections or report both; keep the crisis countries in with a balanced-panel robustness; and report whether the effect is a dollar phenomenon (USD bilateral) or survives in NEER terms.

Referee pushback mapped to the design fix

  • "That's a dollar effect, not an exchange-rate effect." → Report NEER/REER alongside the USD bilateral; show whether the result is dollar-specific or holds for the effective rate.
  • "EPFR is not balance-of-payments capital flows." → State what EPFR measures (benchmarked-fund flows, a high-frequency leading indicator) and either align at its native frequency or triangulate with BoP data.
  • "Your panel is unbalanced in a way that correlates with the outcome." → Show a balanced-panel robustness; report whether crisis-driven entry/exit moves the estimate.
  • "You pooled advanced and emerging economies." → Split AE/EM and test whether the mechanism is common before pooling.
  • "The ZLB breaks your policy-rate measure." → Use a shadow rate or a monetary surprise over the affected window; show the result is not an artifact of the policy-rate floor.

A note on sources international-finance referees trust

Name the canonical datasets and their roles so the design reads as field-literate: IMF IFS/BoP for macro and flows; BIS for cross-border banking and FX statistics; IMF AREAER and the Chinn–Ito index for capital-account openness; the Ilzetzki–Reinhart–Rogoff classification for de facto exchange-rate regimes; Lane–Milesi-Ferretti for external positions; EPFR for high-frequency fund flows; Datastream/Bloomberg for prices, CDS, and yields. Using the wrong dataset for an object (e.g. a de jure regime classification when the question is de facto behavior) is a credibility tell referees catch quickly.

Pre-analysis design questions to settle first

Before estimating, lock five decisions and write the one-line justification for each — they are the questions a referee asks before reading Table 1:

  1. Outcome and treatment frequency — at what frequency is each measured, and how are they aligned (aggregation, MIDAS, native-frequency local projections)?
  2. Country set and entry/exit rule — which countries, why, and what happens to crisis-driven gaps in the panel.
  3. Regime/period partition — which exchange-rate or policy regimes the window spans, and whether you split or control for the breaks.
  4. The exchange-rate convention — USD bilateral, NEER, or REER, nominal or real, and whether the claim is about the dollar or the effective rate.
  5. The flow/risk object — gross vs. net, BoP vs. fund flows, CDS vs. spread, and which the mechanism actually predicts.

Settling these up front prevents the most common revision loop, where a measurement choice the authors never justified turns out to drive the headline result.

Output format

text
【Journal】Journal of International Money and Finance
【Skill】jimf-empirical-design
【Country set / split】AE / EM / both → justified? [Y/N]
【Sample period / regimes】window + breaks handled
【Key measures declared】FX convention / flows type / risk measure / GFCy proxy
【Frequency】native / aggregated / mixed-frequency method
【Data sources】named to series + vintage; splicing documented? [Y/N]
【Next skill】jimf-robustness

© brycewang-stanford, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in Journal-of-International-Money-and-Finance-Skills/skills/jimf-empirical-design of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Jimf Empirical Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Jimf Empirical Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jimf Empirical Design this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~2.4kAutomated safety check: PassMIT
Bio Differential Expression Timeseries DeFreedomIntelligence/OpenClaw-Medical-Skills3.1k1 repos~2.6kAutomated safety check: PassNone
Power Analysisgaasher/Agent-Loop-Skills174—~2.2kAutomated safety check: PassMIT
Senior Data Scientistborghei/Claude-Skills891—~1.7kAutomated safety check: PassMIT
Journal Of Quantitative Technological Economicsfranklee16/academic-research-skills2231 repos~595Automated safety check: PassNone
TimesFM Forecastinggoogle-research/timesfm34k—~4.7kAutomated safety check: PassApache-2.0

Similar skills

  • Bio Differential Expression Timeseries De

    FreedomIntelligence/OpenClaw-Medical-Skills

    Analyze time-series RNA-seq data using limma voom with splines, maSigPro, and ImpulseDE2.

    3.1k GitHub starsUsed in 1 repo~2.6k tokens
    Data & AnalyticsAuto-check passed

  • Power Analysis

    gaasher/Agent-Loop-Skills

    A skill your agent uses when the user is planning a two-arm comparison (an A/B test, a simple RCT, a behavioral study, or a two-model/two-config evaluation) and needs to size it and preregister it…

    174 GitHub stars~2.2k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed

  • Senior Data Scientist

    borghei/Claude-Skills

    A skill your agent uses when the user asks to "design an experiment", "build a predictive model", "run A/B test analysis", "perform causal inference", "engineer features", "evaluate model…

    891 GitHub stars~1.7k tokensUpdated 4 days ago
    Data & AnalyticsAuto-check passed

  • Journal Of Quantitative Technological Economics

    franklee16/academic-research-skills

    A skill your agent uses when targeting 《数量经济技术经济研究》(The Journal of Quantitative & Technological Economics, JQTE) — the CASS journal for quantitative economics, econometric methods, technical…

    223 GitHub starsUsed in 1 repo~595 tokens
    Data & AnalyticsAuto-check passed

  • TimesFM Forecasting

    google-research/timesfm

    Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.

    34k GitHub stars~4.7k tokensUpdated 11 days ago
    Data & AnalyticsAuto-check passed

  • Statsmodels

    zLanqing/codex-claude-academic-skills

    Statistical models library for Python. An agent skill from zLanqing/codex-claude-academic-skills.

    4.7k GitHub starsUsed in 15 repos~4.9k tokens
    Data & AnalyticsAuto-check passed

More from brycewang-stanford/Awesome-Journal-Skills

All 2,387 skills in this repo

  • Aaag Data Analysis

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed

  • Aaag Literature Positioning

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed

  • Aaag Rebuttal

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed

  • Aaag Research Design

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…

    1.2k GitHub stars~1.4k tokensUpdated 14 days ago
    Auto-check passed

  • Aaag Review Process

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…

    1.2k GitHub stars~1.3k tokensUpdated 14 days ago
    Auto-check passed

  • Aaag Submission

    brycewang-stanford/Awesome-Journal-Skills

    A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…

    1.2k GitHub stars~1.6k tokensUpdated 14 days ago
    Auto-check passed

Categories

Questions about Jimf Empirical Design

What does Jimf Empirical Design do?

A skill your agent uses when the cross-country/time-series data construction, sample, frequency, or measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck. Jimf Empirical Design is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when the cross-country/time-series data construction, sample, frequency, or measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck.

When should I use Jimf Empirical Design?

Jimf Empirical Design fits situations like: the cross-country/time-series data construction; measurement of a Journal of International Money and Finance (JIMF) manuscript is the bottleneck.

How do I install Jimf Empirical Design in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jimf-empirical-design -a claude-code`. Or copy the skill folder (Journal-of-International-Money-and-Finance-Skills/skills/jimf-empirical-design in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/jimf-empirical-design in your project. Claude Code loads it when a task matches its description.

How do I install Jimf Empirical Design in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jimf-empirical-design -a codex`. Or copy the skill folder (Journal-of-International-Money-and-Finance-Skills/skills/jimf-empirical-design in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/jimf-empirical-design in your project. Codex loads it when a task matches its description.

Can I use Jimf Empirical Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill jimf-empirical-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jimf-empirical-design, .gemini/skills/jimf-empirical-design, .github/skills/jimf-empirical-design and .opencode/skills/jimf-empirical-design in your project.

What does Jimf Empirical Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Jimf Empirical Design is instructions for the agent only.

Does Jimf Empirical Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Jimf Empirical Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Jimf Empirical Design use?

Jimf Empirical Design is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jimf Empirical Design use?

About 2.4k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Jimf Empirical Design?

Skills that share tags, products or a category with Jimf Empirical Design: Bio Differential Expression Timeseries De (FreedomIntelligence/OpenClaw-Medical-Skills, 3.1k stars), Power Analysis (gaasher/Agent-Loop-Skills, 174 stars), Senior Data Scientist (borghei/Claude-Skills, 891 stars) and Journal Of Quantitative Technological Economics (franklee16/academic-research-skills, 223 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jimf Empirical Design?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,231 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.

Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.