From imf-economic-review-skills
Packages IMF Economic Review manuscript data and code for reproducibility, handling restricted data paths and cross-country source lineage.
How this skill is triggered — by the user, by Claude, or both
Slash command
/imf-economic-review-skills:imfer-replication-packageThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- The analysis is settled and the data/code package must be assembled before submission or at acceptance
IMFER work leans on international-macro data that is often partly restricted — IMF surveillance data, central-bank confidential series, commercial flow data (EPFR), or program-specific files. The package must make everything reproducible in principle even when some inputs cannot be shipped: provide the build scripts, the exact source and vintage of each series, and clear instructions for obtaining the restricted inputs, so a replicator with access can rebuild the analysis dataset and regenerate every exhibit. Confirm the journal's current data-availability and deposit requirements on the official pages (检索于 2026-06;以官网为准).
| Package element | What it must contain |
|---|---|
| Data-availability statement | for each input: public vs. restricted; source; vintage; how a replicator obtains it |
| Source-to-analysis lineage | raw downloads → cleaning → analysis dataset, scripted and ordered |
| Restricted-data handling | the build script + access instructions; never ship confidential micro data |
| Code | numbered, run-in-order scripts that regenerate every table and figure |
| Environment | language versions and packages pinned (lockfile / sessionInfo / requirements) |
| Codebook / data dictionary | variable definitions, country codes, units, currency conventions, transformations |
| Seeds & determinism | seeds set and reported for any simulation / bootstrap / estimation |
| README | one-command (or clearly stepped) path from inputs to all exhibits |
| Mapping table | each table/figure → the script and line that produces it |
International-macro inputs are rarely all-public or all-secret; classify each on a spectrum and document accordingly. Fully public (IFS, WEO, BIS statistics, World Bank): ship the pull scripts and vintage. Public-but-licensed (Bloomberg, Refinitiv, EPFR, Datastream): ship cleaning code plus the license/access route, not the raw series. Restricted-by-agreement (central-bank confidential micro data, IMF surveillance files): ship the build script plus contact/access instructions and any aggregate that the agreement permits. Author-constructed (a hand-coded narrative classification, an event list): ship it in full with the coding rules. The data-availability statement is just this classification made explicit, input by input.
A capital-flows paper merges EPFR fund flows (commercial, licensed), IFS balance-of-payments (public), and a central bank's confidential intervention log (restricted). The package ships the public IFS pulls and all build scripts, but for EPFR and the intervention log it ships only the cleaning code plus access instructions (how to license EPFR, whom to contact at the central bank). The data-availability statement classifies each input, records the IFS vintage (2024 Q1 release) and the EPFR pull date, and the README runs the public-data portions end to end. A replicator with the licenses can rebuild the full analysis dataset and regenerate every exhibit — reproducible in principle without redistributing restricted data.
【Journal】IMF Economic Review
【Skill】imfer-replication-package
【Data-availability】public vs restricted, with sources + vintages: ___
【Restricted handling】access instructions + build script (not shipped): ___
【Lineage】raw→analysis fully scripted? [Y/N]
【Code】numbered, regenerates all exhibits? [Y/N]
【Environment】versions/packages pinned across languages? [Y/N]
【Codebook】variables, country codes, currency/gross-net conventions? [Y/N]
【Clean rebuild】exhibits match scripts? [Y/N]
【Next skill】imfer-referee-strategy
npx claudepluginhub brycewang-stanford/awesome-journal-skills --plugin imf-economic-review-skillsCreates a replication package for Economic Policy manuscripts with one-command reproducibility, data citations, README, and exhibit-to-script mapping. Handles restricted data with synthetic alternatives.
Assembles the data/code replication package for a WBER manuscript, meeting the condition-of-publication data release policy. Builds the deposit and README including restricted data handling.
Builds a data and code replication package for an Economic Journal manuscript to RES/EJ Data Editor standard, including README, data documentation, and Zenodo deposit preparation. Does not run the analysis.