Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/21/2026
What it changes
Passed 19 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill86%
Checks it passed that the model alone missed
The README draft includes a dedicated Quick start section demonstrating single-example inference in under 5 commands.
Recommends organizing top-level folders into dedicated subdirectories including `src/`, `scripts/`, `configs/`, and `results/`.
The reproducibility checklist includes per-experiment verification items covering hyperparameter configuration matching and hardware requirements.
2 fixed17 passed either way3 still failing0 broke
Pass-rate lift
+9 pp
Tokens
+18%
Agent turns
0%
Response time
-25%
Model gemini-3.6-flashMeasured 8/21/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 2
Prompt
What standard directory layout should we adopt for an academic ML project containing source modules, evaluation scripts, configuration YAML files, and result outputs?
What was checked, without and with the skill
Checked
Without skill
With skill
Recommends organizing top-level folders into dedicated subdirectories including `src/`, `scripts/`, `configs/`, and `results/`.
Missed
Passed
case-19 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md111 linessingle file
Research Publishing Methodology
You are helping a researcher prepare their code and artifacts for public release alongside a paper submission.
Step 1: Repository Assessment
Before any changes, audit the current state:
Sensitive content scan:
API keys, tokens, credentials (grep for common patterns)
Hardcoded paths specific to the researcher's machine
Internal URLs or private infrastructure references
Personal identifiable information in comments or data
Dependency audit:
List all dependencies with pinned versions
Identify any proprietary or restricted-license dependencies
Check for abandoned/unmaintained dependencies
Verify all dependencies are pip/conda installable
Code organization:
Identify dead code, debugging artifacts, scratch files
Find duplicated code that should be unified
Check for overly complex code that can be simplified
Step 2: Repository Structure
A publishable research repository should have:
project/
README.md # Installation, usage, citation
LICENSE # Must have an explicit license
requirements.txt # or pyproject.toml with pinned deps
setup.py / setup.cfg # Package installation
src/ # Source code
scripts/ # Training, evaluation, inference scripts
configs/ # Configuration files
data/ # Sample data or download instructions
checkpoints/ # Download instructions (not actual weights)
Compresión textual por eliminación / text compression by deletion. Acorta cualquier texto eliminando redundancias, repeticiones y prosa decorativa, preservando estructura, terminología, definiciones, citas, datos factuales y secuencia argumentativa. NO reescribe ni parafrasea. Usar cuando el usuario pida comprimir, condensar, acortar, reducir o resumir un texto —"hacé más corto esto", "resumí sin perder contenido", "comprimí este PDF", "acortá este documento", "haceme un resumen de este archivo"