Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger Timing

When a reproduction target and setup plan already exist, and the main skill or user needs execution evidence from a smoke test, documented inference/evaluation command, or other short non-training verification, plus normalized reporting.

Working Mechanism

  • Receive runnable commands, environment assumptions, and optional patch metadata
  • Execute or receive evidence via scripts/run_command.py
  • Normalize outputs using scripts/write_outputs.py and references/reporting-policy.md
  • Write repro_outputs/ with status, PATCHES.md, SCIENTIFIC_CHANGELOG.md, COMPARABILITY_REPORT.md

Result

Standardized auditable run evidence: clear verified/partial/blocked states, patch notes, and scientific-meaning change logs for trustworthy reproduction.

Use Cases

Two Typical Use Cases

Scenario 01

Smoke test documented inference command

A researcher has set up a repo and wants to run the documented inference command as a smoke test. They use minimal-run-and-audit to execute the command, capture stdout/stderr and metrics, and generate repro_outputs/ with verified status and PATCHES.md if files changed. This gives auditable evidence and saves manual reporting effort.

Scenario 02

Audit patched evaluation run evidence

During reproduction, a small evaluation script needed a one-line fix. The user invokes minimal-run-and-audit to run the eval and record the patch in PATCHES.md plus SCIENTIFIC_CHANGELOG.md. The standardized COMPARABILITY_REPORT.md shows README/baseline comparability, preventing hidden changes from slipping into the repro bundle.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

Tier 2 · Current Skill

  • minimal-run-and-auditWorkflow

Tier 3 · I Use These Skills

  • No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.