safe-debug
safe-debug
When to apply
- The user provides a traceback, terminal error, or concrete training or inference failure symptom.
- The user wants diagnosis, root-cause narrowing, and minimal patch suggestions before code is changed.
- The user wants a safe debug flow with explicit human approval before mutation.
When not to apply
- When the user wants a broad repository walkthrough without an active failure.
- When the task is speculative experimentation or code adaptation.
- When the user is asking for a large refactor or readability rewrite.
Clear boundaries
- Diagnose first.
- Do not modify repository code by default.
- If a patch is needed, propose the smallest fix and require explicit approval first.
- Escalate savepoint or branch creation before medium-risk or high-risk changes.
Output expectations
debug_outputs/DIAGNOSIS.mddebug_outputs/PATCH_PLAN.mddebug_outputs/status.json
Notes
Use references/debug-policy.md and the shared references/research-pitfall-checklist.md.
More from lllllllama/ai-paper-reproduction-skill
env-and-assets-bootstrap
Environment and assets sub-skill for README-first AI repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.
81.6Krepo-intake-and-plan
Narrow helper skill for README-first AI repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
81.6Kminimal-run-and-audit
Trusted-lane execution and reporting skill for README-first AI repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, or end-to-end orchestration by itself.
81.6Kexplore-code
Explore-lane code adaptation skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together low-risk migration ideas with summary-only records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, or default repository analysis.
111explore-run
Explore-lane experimental execution skill for deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with results summarized in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline execution, conservative training verification, default routing, or implicit experimentation.
109run-train
Trusted-lane training execution skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with status, checkpoint, and metric capture written to standardized `train_outputs/`. Do not use for environment setup, exploratory sweeps, speculative idea implementation, or end-to-end orchestration.
108