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

Imfer Replication Package

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

A skill your agent uses when an IMF Economic Review (IMFER) manuscript's data and code must be packaged for reproducibility — including restricted IMF/central-bank data paths, cross-country source…

MITAuto-check passedResearch & Science

Install Imfer Replication Package

skills CLI
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill imfer-replication-package -a claude-code

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

GitHub CLI
$ gh skill install brycewang-stanford/Awesome-Journal-Skills imfer-replication-package --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/IMF-Economic-Review-Skills/skills/imfer-replication-package .claude/skills/imfer-replication-package && 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
imfer-replication-package
GitHub stars
1.2k
Token cost
~1.9k tokens
SKILL.md length
870 words
Files
1
Skills in repo
2,387
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when an IMF Economic Review (IMFER) manuscript's data and code must be packaged for reproducibility — including restricted IMF/central-bank data paths, cross-country source…

  • Works in 6 steps: Map every series to a source and… → Separate public from restricted up… → Script the build, do not hand-edit.… → …
  • Cross-country source lineage
  • SKILL.md covers When to trigger, The IMFER reproducibility…, Packaging craft and Checklist, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Imfer Replication Package is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when an IMF Economic Review (IMFER) manuscript's data and code must be packaged for reproducibility — including restricted IMF/central-bank data paths, cross-country source lineage, and a runnable environment. Builds the package; it does not produce the exhibits (imfer-tables-figures) or run the submission preflight (imfer-submission).

Its SKILL.md is about 1.9k 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 Research & Science, covering Econometrics and empirical research and Reproducible research. 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

  • Cross-country source lineage
  • A runnable environment

Example prompts

  • “/imfer-replication-package”

Requirements

  • Python 3

Workflow steps

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

  1. Map every series to a source and vintage. Cross-country panels silently mix vintages (a WEO release, an IFS pull); record exactly which…
  2. Separate public from restricted up front. Write the data-availability statement first; it dictates what ships and what needs access…
  3. Script the build, do not hand-edit. Every transformation from raw to analysis dataset must be in code, so a replicator with the restricted…
  4. Pin the environment. International-macro pipelines often span Stata, R, and Python; lock each so results do not drift with package updates.
  5. Regenerate exhibits from scratch in a clean environment before submission — the most common failure is a figure that no longer matches the…
  6. Document country and currency conventions in the codebook; a replicator must know your USD/local, gross/net, deflator choices.

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

Imfer Replication Package loads about 1.9k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 870 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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). 870 words, ~1,905 tokens.

Download SKILL.mdSave it as .claude/skills/imfer-replication-package/SKILL.md (or your agent's skills folder).
name
imfer-replication-package
description
Use when an IMF Economic Review (IMFER) manuscript's data and code must be packaged for reproducibility — including restricted IMF/central-bank data paths, cross-country source lineage, and a runnable environment. Builds the package; it does not produce the exhibits (imfer-tables-figures) or run the submission preflight (imfer-submission).

Replication Package (imfer-replication-package)

When to trigger

  • The analysis is settled and the data/code package must be assembled before submission or at acceptance
  • Some inputs are restricted (IMF program data, central-bank micro data, proprietary flows) and cannot be redistributed
  • A cross-country dataset stitches many sources (IFS, BOP, WEO, BIS, EPFR, national accounts) and the lineage is undocumented
  • A referee or editor asks for a reproducibility check or a data-availability statement
  • Code runs only on one machine; seeds, versions, and the build order are not pinned

The IMFER reproducibility reality

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 elementWhat it must contain
Data-availability statementfor each input: public vs. restricted; source; vintage; how a replicator obtains it
Source-to-analysis lineageraw downloads → cleaning → analysis dataset, scripted and ordered
Restricted-data handlingthe build script + access instructions; never ship confidential micro data
Codenumbered, run-in-order scripts that regenerate every table and figure
Environmentlanguage versions and packages pinned (lockfile / sessionInfo / requirements)
Codebook / data dictionaryvariable definitions, country codes, units, currency conventions, transformations
Seeds & determinismseeds set and reported for any simulation / bootstrap / estimation
READMEone-command (or clearly stepped) path from inputs to all exhibits
Mapping tableeach table/figure → the script and line that produces it
The restricted-data spectrum (classify each input)

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.

Packaging craft

  1. Map every series to a source and vintage. Cross-country panels silently mix vintages (a WEO release, an IFS pull); record exactly which, because revisions change results.
  2. Separate public from restricted up front. Write the data-availability statement first; it dictates what ships and what needs access instructions.
  3. Script the build, do not hand-edit. Every transformation from raw to analysis dataset must be in code, so a replicator with the restricted input can reconstruct your sample.
  4. Pin the environment. International-macro pipelines often span Stata, R, and Python; lock each so results do not drift with package updates.
  5. Regenerate exhibits from scratch in a clean environment before submission — the most common failure is a figure that no longer matches the script.
  6. Document country and currency conventions in the codebook; a replicator must know your USD/local, gross/net, deflator choices.
Show full SKILL.md (345 more words)Show less

Checklist

  • Data-availability statement: each input classified public/restricted with source, vintage, access path
  • Restricted inputs never shipped; access instructions + build script provided instead
  • Raw-to-analysis lineage fully scripted and ordered
  • Numbered code regenerates every table and figure
  • Environment pinned (versions + packages) across all languages used
  • Codebook covers variables, country codes, units, currency/deflator/gross-net conventions
  • Exhibit-to-script mapping table provided (every table/figure traceable to its code)
  • Seeds set and reported for simulation/bootstrap/estimation
  • Clean-environment rebuild verified; exhibits match the scripts
  • Current deposit / data-availability rules confirmed on official pages or marked 待核实

Anti-patterns

  • Shipping confidential IMF/central-bank micro data instead of access instructions
  • A panel with no record of which data vintage was used (results not reconstructable after revisions)
  • Hand-edited intermediate files that no script can reproduce
  • Unpinned environment, so a referee's rerun drifts from the paper
  • A README that assumes the author's exact machine and paths
  • Treating reproducibility as an acceptance-time afterthought rather than building it in
  • A data-availability statement that says "available on request" for inputs that have a real public source or access route

Worked vignette (illustrative)

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.

Referee/editor pushback mapped to the package fix

  • "Some inputs are restricted — is this reproducible?" → Provide build scripts plus access instructions for the restricted inputs; never ship them.
  • "Which data vintage produced these numbers?" → Record source and vintage for every series in the data-availability statement and codebook.
  • "Your rerun gives different numbers." → Pin the environment across Stata/R/Python and verify a clean-environment rebuild before submission.

Output format

text
【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

© 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 IMF-Economic-Review-Skills/skills/imfer-replication-package of brycewang-stanford/Awesome-Journal-Skills.

Open the folder on GitHubat commit 932eb23

Compare with similar skills

Imfer Replication Package 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.

Imfer Replication Package compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Imfer Replication Package this skillbrycewang-stanford/Awesome-Journal-Skills1.2k—~1.9kAutomated safety check: PassMIT
Replication Packagepedrohcgs/claude-code-my-workflow1.6k—~2.8kAutomated safety check: NotesMIT
Audit Reproducibilitypedrohcgs/claude-code-my-workflow1.6k—~6.4kAutomated safety check: NotesMIT
Reproducible Pipelinesbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~3.3kAutomated safety check: PassCustom licence
Audit Replicationbrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~984Automated safety check: NotesCustom licence
Scholar Openjoshzyj/open-scholar-skill168—~14kAutomated safety check: PassCustom licence

Similar skills

  • Replication Package

    pedrohcgs/claude-code-my-workflow

    Assemble a submission-ready replication package to the AEA Data and Code Availability Standard (DCAS) / openICPSR / Social Science Reproduction Platform expectations — standard replication README…

    1.6k GitHub stars~2.8k tokensUpdated 11 days ago
    Research & ScienceAuto-check: notes

  • Audit Reproducibility

    pedrohcgs/claude-code-my-workflow

    Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs.

    1.6k GitHub stars~6.4k tokensUpdated 11 days ago
    Research & ScienceAuto-check: notes

  • Reproducible Pipelines

    brycewang-stanford/Auto-Empirical-Research-Skills

    This skill covers reproducible research pipelines and replication packages.

    4.5k GitHub stars~3.3k tokensUpdated 3 days ago
    Research & ScienceAuto-check passed

  • Audit Replication

    brycewang-stanford/Auto-Empirical-Research-Skills

    Validate the replication package for the sewage-house-prices project.

    4.5k GitHub stars~984 tokensUpdated 3 days ago
    Research & ScienceAuto-check: notes

  • Scholar Open

    joshzyj/open-scholar-skill

    Implement open science practices for a social science study.

    168 GitHub stars~14k tokensUpdated 20 days ago
    Research & ScienceAuto-check passed

  • Ecta Replication Package

    franklee16/academic-research-skills

    A skill your agent uses when assembling the code and data deposit for an Econometrica manuscript under the journal's Data and Code Availability Policy, including reproducible Monte Carlo and (for…

    223 GitHub starsUsed in 1 repo~1.8k tokens
    Research & ScienceAuto-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 11 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 11 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 11 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 11 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 11 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 11 days ago
    Auto-check passed

Categories

Questions about Imfer Replication Package

What does Imfer Replication Package do?

A skill your agent uses when an IMF Economic Review (IMFER) manuscript's data and code must be packaged for reproducibility — including restricted IMF/central-bank data paths, cross-country source…. Imfer Replication Package is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when an IMF Economic Review (IMFER) manuscript's data and code must be packaged for reproducibility — including restricted IMF/central-bank data paths, cross-country source lineage, and a runnable environment.

When should I use Imfer Replication Package?

Imfer Replication Package fits situations like: cross-country source lineage; A runnable environment.

How do I install Imfer Replication Package in Claude Code?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill imfer-replication-package -a claude-code`. Or copy the skill folder (IMF-Economic-Review-Skills/skills/imfer-replication-package in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/imfer-replication-package in your project. Claude Code loads it when a task matches its description.

How do I install Imfer Replication Package in Codex?

Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill imfer-replication-package -a codex`. Or copy the skill folder (IMF-Economic-Review-Skills/skills/imfer-replication-package in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/imfer-replication-package in your project. Codex loads it when a task matches its description.

Can I use Imfer Replication Package 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 imfer-replication-package -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/imfer-replication-package, .gemini/skills/imfer-replication-package, .github/skills/imfer-replication-package and .opencode/skills/imfer-replication-package in your project.

What does Imfer Replication Package need to run?

SKILL.md names no scripts, command-line tools or credentials: Imfer Replication Package is instructions for the agent only. Our summary lists: Python 3.

Does Imfer Replication Package 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 Imfer Replication Package 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 Imfer Replication Package use?

Imfer Replication Package 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 Imfer Replication Package use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 Imfer Replication Package?

Skills that share tags, products or a category with Imfer Replication Package: Replication Package (pedrohcgs/claude-code-my-workflow, 1.6k stars), Audit Reproducibility (pedrohcgs/claude-code-my-workflow, 1.6k stars), Reproducible Pipelines (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars) and Audit Replication (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Imfer Replication Package?

brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,219 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.