ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, score chasing, or broad research assistance outside repository-grounded reproduction.
Install
With your agent
Install OMGSkills skill "lllllllama/rigorpilot-skills:ai-research-reproduction" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/lllllllama/RigorPilot-Skills /tmp/RigorPilot-Skills && ln -s /tmp/RigorPilot-Skills/skills/ai-research-reproduction ~/.claude/skills/ai-research-reproductionFrom README
ai-research-reproduction Purpose Guide README-first deep learning reproduction toward the smallest trustworthy run with auditable evidence. Preserve documented meaning; record assumptions, deviations and blockers instead of changing semantics to manufacture success. Load specialized references only for a concrete uncertainty. Fast Path For a routine bounded run, keep the control path short: Read the target README and only the target test/config/source needed to understand the documented command. Run scripts/orchestraterepro.py --repo --plan-only --agent-output with any explicit user timeout bound (--timeout or --train-timeout) already supplied; review commandcandidates, the selected cmd-XX, side-effect contract, selection fingerprint, and returned reviewedrunargs. With no --output-dir, later evidence goes to /reprooutputs regardless of caller cwd.
More from this repo
paper-context-resolver
Rigor Paper Context helper for README-first deep learning repo reproduction.
repo-intake-and-plan
Rigor Intake helper for README-first deep learning repo reproduction.
env-and-assets-bootstrap
Rigor Setup skill for README-first deep learning repo reproduction.