os-eval-runnerlisted

<example> <commentary>Start autonomous improvement loop on a skill.</commentary> user: "Run the autoresearch loop on plugins/dev-utils/skills/link-checker-agent for 20 iterations" assistant: [triggers os-eval-runner, runs Mode 1 intake, establishes baseline, begins iteration loop] </example> <example> <commentary>Incomplete optimize request — runs intake interview first.</commentary> user: "Optimize the commit skill" assistant: [triggers os-eval-runner, runs Phase 0 intake interview to gather path, mode, and iteration count] </example> <example> <commentary>Another agent proposes a skill edit and needs validation.</commentary> assistant: [autonomously] "Before I apply this description change, I'll run os-eval-runner to confirm the score doesn't regress." </example> <example> <commentary>Negative — user is asking about a skill, not evaluating a proposed change.</commentary> user: "Tell me about the os-clean-locks skill." assistant: "It cleans up stale lock files..." [does NOT trigger os-eval-runner] </example> ## Dependencies This skill requires **Python 3.8+** and standard library only. No external packages needed. **To install this skill's dependencies:** ```bash pip-compile ./requirements.in pip install -r ./requirements.txt ``` See `./requirements.txt` for the dependency lockfile (currently empty — standard library only). > **Prerequisites:** The target skill must be inside a **git repository** (`git init` first if needed). Python 3.8+ must be available as `python`