Install any skill in seconds. Free to start, no credit card required.
Get Started Free →docxology/infrastructure-doctor
Skill for the doctor infrastructure module providing repository-level diagnostics and safe, reversible automated repair.
Passed 22 of 22 test cases with the skill, and 6 of 22 without it.
and 13 more in the full report
16 fixed6 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
Before any filesystem mutation occurs during an automated fix, the safety subsystem snapshots affected files. What directory path relative to the repository root stores these byte-for-byte snapshots?
| Checked | Without skill | With skill |
|---|---|---|
| The response identifies `.doctor/backups/<action_id>/` as the snapshot path. | Missed | Passed |
The instructions your model reads when the skill loads.
Repository-level "doctor mode": a diagnostic engine plus an automated, audited resolution engine. The doctor never leaves the patient worse off — every mutation is snapshotted before it runs and can be reversed by a single undo command.
# Diagnose only (read-only).
uv run python -m infrastructure.doctor
# Same, JSON for an agent.
uv run python -m infrastructure.doctor --json diagnose
# Show what would be fixed (no changes).
uv run python -m infrastructure.doctor fix --plan
# Apply the safest set of fixes.
uv run python -m infrastructure.doctor fix --apply
# Allow `uv sync` and other moderate-therapy fixes.
uv run python -m infrastructure.doctor fix --apply --moderate
# Allow radical fixes (e.g. delete orphan output directories — still backed up).
uv run python -m infrastructure.doctor fix --apply --aggressive
# Reverse the most recent applied, reversible action.
uv run python -m infrastructure.doctor undo --last
# Reverse one specific action (see `history`).
uv run python -m infrastructure.doctor undo --action-id <id>
# Inspect the journal.
uv run python -m infrastructure.doctor history
# Agent-facing capability manifest.
uv run python -m infrastructure.doctor capabilities
# Stable-text robot manual.
uv run python -m infrastructure.doctor robot-docs
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.