Econ review setup

Skill hanlulong/econ-paper-review-skill/econ-review/skills/econ-review-setup

Prepare, verify, repair, or refresh the user-owned Python runtime and local Review Desk used by an installed econ-review plugin. Use when the user installs econ-review from a marketplace, asks to finish setup, reports missing Python packages or Poppler, needs the Review Desk launcher, or wants to check installation readiness without creating duplicate Claude Code or Codex skill copies.From its SKILL.md

Install

npx -y skills add hanlulong/econ-paper-review-skill --skill econ-review-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.5 KB, 687 tokens by cl100k_base, as published. Nobody here has run it

Set up Econ Review

Resolve PLUGIN_ROOT as the parent directory of the skills/ directory that contains this setup skill. Use the standard-library setup tool at PLUGIN_ROOT/scripts/setup_econ_review.py. Do not copy the skill into an agent home: marketplace installation already supplies it.

Find a working Python 3.10 or newer command with venv and pip bootstrapping support already on the machine. Do not install Python, a package manager, a missing python3-venv component, or system software on your own.
Choose global support setup unless the user explicitly requests one-project state. For global setup, run this exact operation first with --dry-run:
```
PYTHON PLUGIN_ROOT/scripts/setup_econ_review.py --support-only --global --with-review-desk --dry-run
```
For project state, replace --global with --local PROJECT_DIRECTORY.
Summarize the dry run in plain language. State that applying it creates or refreshes a private econ-review virtual environment, may download the version-constrained Python packages declared by the plugin, and installs the already bundled, manifest-verified Review Desk. It does not install a second skill copy, use administrator access, or upload a manuscript.
Apply the same command without --dry-run only when the user has explicitly asked to install, finish, repair, or refresh setup, or confirms after seeing the plan. Do not treat a request merely to review a paper as authorization to download packages or change user-level state.
Preserve the setup tool's exit distinction. Exit 0 means the core runtime, PDF ingestion, and requested Review Desk passed. Exit 2 means the managed runtime and Review Desk may be ready but PDF ingestion is still incomplete, normally because Poppler is absent. Do not call that a failed plugin install.
Never install Poppler, Tesseract, TeX, Pandoc, Node.js, an optional PDF backend, or any administrator-managed package automatically. If Poppler is missing, report the setup tool's platform-specific user-level options and ask separately before running a package-manager command.
Verify runtime discovery without changing files:
```
PYTHON PLUGIN_ROOT/scripts/setup_econ_review.py --runtime-path
```
After project-only setup, pass the same project scope instead:
```
PYTHON PLUGIN_ROOT/scripts/setup_econ_review.py --runtime-path --local PROJECT_DIRECTORY
```
This read-only resolver verifies and prints only the managed interpreter. Preserve the setup command's earlier PDF-doctor result and Review Desk launch command or URL when reporting overall readiness. Never expose package-index credentials or environment-secret values in the response.
When the user asks to uninstall support data, show --cleanup-support --global --dry-run (or the matching --local scope) first. Apply the same scope with --confirm-cleanup only after explicit confirmation. Explain that plugin removal alone retains the runtime, descriptor, and Review Desk, while cleanup leaves the plugin and any direct skill copy unchanged.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most quality gates skills give in 687 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07

Read the output and check the exit codein 54 of 1195, across 14 files
Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
Identify the verification command proving the claimin 51 of 1195, across 12 files
Run the full verification commandin 50 of 1195, across 11 files
Verify output confirms the claimin 49 of 1195, across 12 files
Check version control diff after agent delegationin 46 of 1195, across 6 files
State claim with evidencein 44 of 1195, across 4 files
Run the test suitein 33 of 1195, across 26 files
Keep state in memory by defaultin 27 of 1195, across 6 files
Make prototype runnable with one commandin 26 of 1195, across 5 files
Produce a verification reportin 25 of 1195, across 14 files
Detect the package manager from lockfilesin 24 of 1195, across 5 files

Said here and by no other author read

summarize the dry-run plan in plain language
apply changes only after explicit user authorization
preserve the setup tool exit code distinction
verify the runtime path without changing files
show cleanup dry-run before removing support data
apply cleanup only after explicit confirmation