snag

Triage unexpected defects by size and route them to fixes, analysis, or tracked work.

37|2|Updated Jun 28, 2025
One-click install
npx skills add https://github.com/jellyrock/jellyrock --skill snag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: snag
Source: https://github.com/jellyrock/jellyrock/tree/main/.claude/skills/snag
Command: npx skills add https://github.com/jellyrock/jellyrock --skill snag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When you encounter an unexpected defect, bug, or regression mid-development work, it is tempting to jump straight to a quick first-draft patch that may miss the root cause, introduce new issues, or waste effort on a problem that needs a larger dedicated effort. This skill eliminates that reflex by interposing a triage step between flaw discovery and any fix work.

Core Features & Use Cases

  • Size-based triage: Rates flaws by blast radius and judgment required (not line count) into trivial, small/medium, or large categories.
  • Three routing paths: Sends trivial issues to zero-ceremony immediate fixes, small/medium issues to a structured 5-gate remediation process with optional sub-agent delegation, and large issues to tracked work via /log followup or /start-project.
  • Use case: If you are working on JellyRock and spot a regression in the playback OSD, invoke /snag to get a clear triage and next steps instead of guessing at a patch.

Quick Start

Invoke the /snag skill the moment you spot an unexpected defect mid-work to receive a triage of its size and the correct next steps before drafting any fix.

Frequently Asked Questions about snag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I triage unexpected bugs and regressions discovered mid-development without applying low-quality first-draft patches?

Reactive flaw triage interposes a structured step between defect discovery and fix work, rating issues by blast radius to route them to immediate fixes, root-cause analysis with regression verification, or tracked work escalation.

What is size-based triage for bug remediation and how does it determine the routing path?

Size-based triage rates defects by blast radius and judgment required into trivial, small/medium, or large categories. Trivial flaws route to zero-ceremony fixes, small/medium to a 5-gate remediation process, and large to tracked work.

When do I need root cause analysis with regression verification instead of a quick patch?

Root cause analysis with regression verification is needed for small to medium defects where judgment is required, preventing reflexive patches that miss underlying causes or introduce new issues across cross-cutting shared mechanisms.

Can I use sub-agent delegation for identifying root causes during flaw triage?

Yes, sub-agent delegation is optionally available during the structured 5-gate remediation process for small and medium flaws, specifically assisting with judgment-heavy root cause identification tasks.

Does this reactive debugging workflow support Roku client engineering environments?

Yes, this flaw triage process applies to JellyRock Roku client engineering workflows, handling defects ranging from trivial typos to cross-cutting shared mechanism issues and large multi-session defects.

What's the best way to handle large multi-session defects discovered during development work?

Large multi-session defects should be escalated to tracked work via dedicated logging or project start commands, ensuring dedicated effort rather than attempting insufficient mid-work patches.