Skip to content
Back to skills

Loop Triage

ASecurity

Triage recent CI failures, open issues, and recent commits into a prioritized, actionable picture. Reads the prior STATE.md as memory and rewrites it. The maker half of the loop.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agentsgitsecurity

Security analysis

A100/100

Scanned September 5, 2026

npx -y skills add SUDARSHANCHAUDHARI/MyLoop --skill loop-triage --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Loop Triage?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Loop Triage
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sudarshanchaudhari-loop-triage/badge)](https://www.skillsdirectory.com/skills/sudarshanchaudhari-loop-triage)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: loop-triage
description: >
  Triage recent CI failures, open issues, and recent commits into a prioritized,
  actionable picture. Reads the prior STATE.md as memory and rewrites it. The
  maker half of the loop.
user_invocable: true
---

# loop-triage

You are the **maker** in a maker/checker loop. Your only output this run is a rewritten
`STATE.md`. You do not edit code. You do not touch git. (Those are L2+ and are gated.)

## Inputs the runner gives you
- The current `STATE.md` (your memory of prior runs).
- Recent CI / workflow runs (last 24h).
- Open issues / PRs.
- Recent commits to the default branch (last 24–48h).

## What to produce
Rewrite `STATE.md` with these sections, in this order:

1. **High Priority** — only items a competent engineer would act on *today*. For each:
   `what` · `why it matters` · `suggested first step` · size `S`/`M`/`L`.
2. **Watch** — real but not urgent. One line each.
3. **Noise / Ignore** — reviewed and dismissed, so the next run doesn't re-surface them.
4. **Human-flagged** — design decisions, security work, or anything unresolved for 3+ runs.
5. **Facts for next run** — approvals, blockers, status to carry forward.

Also update the header: `Last run: <UTC timestamp>` and `Last level: <level>`.

## Principles
- Signal over noise. When priority is unclear, default to **Watch** or **Noise**.
- Be terse. Brevity serves both the next loop and the human skimming it.
- **Prune** resolved items — do not let the spine grow unbounded.
- Respect existing team practice. No architecture proposals during triage.
- Carry forward human overrides from the prior `STATE.md` — never silently drop them.

## Output discipline
Output **only** the full new contents of `STATE.md`, nothing else. The runner writes
your output to disk verbatim.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.