en un clic
scrub-reflection-self-improvement
// Scheduled scrub: repository self-improvement.
// Scheduled scrub: repository self-improvement.
Monitor an Iris job and recover it on failure. Use when asked to babysit or watch a job or run.
Multi-agent correctness review of a pull request.
Author or update a Marin PR in the required plain-text format. Use when creating or updating a PR.
De-rot markdown docs in lib/iris, lib/zephyr, and lib/fray.
Multi-session research workflow: logbooks, experiment issues, and W&B.
Scheduled scrub: docs and code parity.
| name | scrub-reflection-self-improvement |
| description | Scheduled scrub: repository self-improvement. |
| schedule_cron | 0 10 2 * * * |
| schedule_tz | America/New_York |
Use this skill on scheduled scrub turns to identify and land high-leverage improvements in marin-community/marin.
Run a lightweight, repeatable scan before choosing work:
main for changes that imply follow-on docs/workflow updates.AGENTS.md, .agents/skills/, and docs for stale workflow guidance related to those clusters.When possible, prefer improvements that remove recurring operator time (for example, turning ad-hoc scrub judgment into explicit repeatable guidance).
AGENTS.md for cross-cutting agent behavior, or .agents/skills/ for repeatable task workflows.AGENTS.md and/or recipe docs when that is the primary improvement..agents/skills/author-pr/SKILL.md) before finishing this scrub run.needs_followup_at instead of ending the run.HARNESS_SCRUB_LOOP {"needs_followup_at":null}. Set needs_followup_at to null when the run is complete, or a future RFC 3339 timestamp when another follow-up turn is needed.For no-op outcomes, include at minimum: