ai-paper-reproduction

README-first orchestrator for minimal, auditable AI paper repository reproduction.

- Coordinates end-to-end reproduction workflows: intake, environment setup, conservative execution, and standardized output generation

- Prioritizes documented inference over evaluation over training; stops at smoke tests or startup verification rather than pursuing full training by default

- Enforces conservative patch rules (environment variables, paths, dependency fixes preferred; model architecture and training logic off-limits) and surfaces all assumptions, deviations, and human decision points

- Generates standardized repro_outputs/ bundle with SUMMARY, COMMANDS, LOG, status.json, and optional PATCHES for auditability and downstream review

- Treats README as the primary source of intent; escalates to human review before any change that could alter scientific meaning or reported conclusions

ai-paper-reproduction

Use when

- The user wants the agent to reproduce an AI paper repository.

- The target is a code repository with a README, scripts, configs, or documented commands.

- The goal is a minimal trustworthy run, not unlimited experimentation.

- The user needs standardized outputs that another human or model can audit quickly.

- The task spans more than one stage, such as intake plus setup, or setup plus execution plus reporting.

Do not use when

- The task is a general literature review or paper summary.

- The task is to design a new model, benchmark suite, or training pipeline from scratch.

- The repository is not centered on AI or does not expose a documented reproduction path.

- The user primarily wants a deep code refactor rather than README-first reproduction.

- The user is explicitly asking for only one narrow phase that a sub-skill already covers cleanly.

- The user is explicitly authorizing exploratory branch-only experimentation instead of trusted reproduction.