🎯

repo-intake-and-plan

🎯Skill

from lllllllama/ai-paper-reproduction-skill

What it does

Helper skill for README-first AI paper reproduction that scans a repository, extracts documented commands, and returns the smallest trustworthy inference, evaluation, and training plan.

Overview

A helper sub-skill in the ai-paper-reproduction-skill repository that scans a repository, extracts documented commands, and returns the smallest trustworthy inference, evaluation, and training plan — README-first and minimally invasive.

Key Features

Scans the repo to enumerate documented commands and candidate paths
Returns the smallest trustworthy inference / evaluation / training plan
README-first policy: prefers what the docs say before guessing
Emits a structured plan the rest of the reproduction skills can act on

Who is this for?

ML practitioners and agents reproducing AI papers who want a conservative, README-first planning step before running anything. Ideal when the goal is "show me the minimum I can trust to run from this repo".

📦

Same repository

lllllllama/ai-paper-reproduction-skill(11 items)

repo-intake-and-plan

Installation

Vibe Index InstallInstalls to .claude/skills/ - auto-recognized by Claude Code

npx vibeindex add lllllllama/ai-paper-reproduction-skill --skill repo-intake-and-plan

skills.sh Install⚠ Installs to .agents/skills/ - may not be auto-recognized by Claude Code

npx skills add lllllllama/ai-paper-reproduction-skill --skill repo-intake-and-plan

Manual InstallCopy SKILL.md content and save to the path below

~/.claude/skills/repo-intake-and-plan/SKILL.md

SKILL.md

48,490Installs

AddedApr 13, 2026

View on GitHub Back to Skills

More from this repository10

🎯

paper-context-resolver🎯Skill

Companion skill for AI paper reproduction that resolves paper context, references, and dependencies needed when reproducing AI research implementations.

🎯

env-and-assets-bootstrap🎯Skill

Sub-skill for README-first AI paper reproduction that prepares a conservative conda-first environment plus checkpoint, dataset, and cache path assumptions before any run attempt.

🎯

minimal-run-and-audit🎯Skill

Executes and audits the selected smoke test, documented inference, or evaluation command during README-first AI paper reproduction, writing standardized `repro_outputs/` evidence and patch notes.

🎯

ai-paper-reproduction🎯Skill

README-first AI paper reproduction skill that helps reproduce AI papers by choosing the smallest trustworthy documented target with minimal, auditable code changes.

🎯

ai-research-reproduction🎯Skill

A lane-aware skill repository for deep learning research workflows that separates trusted reproduction tasks from exploratory candidate work, shipping 11 skills with 42 test scripts across Windows and Linux for use with Claude Code, Codex, and Agent Skills.

Skill

Skill

Skill

analyze-project🎯Skill

Skill

🎯

safe-debug🎯Skill

Skill