- Home
- Skills
- Testing & Debugging
- Play Console Crash Triage
More screenshots
Works with the AI Agents you already use
Play Console Crash Triage
Turn a backlog of console crash and ANR reports into ranked clusters and fixable work, starting with what hurts the most users.
$5
Play Console Crash Triage
Example session with this skill installed
Cluster these rows: a Detail.bind crash with 3,100 users on version 2.4, a Settings.load crash with 900 users, and a second Detail.bind row with 200 users.
- Read your context and instructions
- Compiled the play console crash
Running the bundled clusterer on those rows produces:
CLUSTERS: 2 from input rows
1. NullPointerException Detail.bind | users=3300 events=3610 versions=2.4 first=2.4 -> top-3 cluster — work first
2. IllegalStateException Settings.load | users=900 events=950 versions=2.1 first=2.0 -> top-3 cluster — work first
The skill's worked example scales this to a 28-day triage: 4,200 events across 38 console groups merged into 24 fixable clusters, a home-screen regression ranked first with a data-layer fix, and every remaining cluster given a disposition with a reason, plus a re-check date two weeks after the fix release.
Connects securely to your tools. The creator never sees your data.
About this skill
A console with thousands of reports cannot be triaged report by report; the unit of work is the cluster. This skill defines a window, separates crashes from ANRs, clusters reports by signature into one cluster per fixable cause (merging groups that share root frames, splitting groups that hide two causes), ranks clusters by a stated rule — affected users first, then rising trend, then core-flow blocking — and assigns every cluster a disposition: fix now, fix next, monitor, need more data, or third-party/system with a mitigation.
Top clusters get full work items: cause hypothesis with trace evidence, version and device concentration analysis, reproduction steps or a plan, a fix direction, and a verification criterion checked at a set re-check date. The skill also names the traps: console grouping errors, count-vs-rate confusion after a release, and triage without a re-check. A runnable clusterer merges report rows by signature and ranks them by affected users.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
- Needs console data for a defined window; a single-device report with no console data is a different workflow.
- Obfuscated clusters without the matching mapping file can only be marked need-more-data until the file is recovered.
- Crash and ANR triage are kept separate; merging them into one ranking hides both failure modes.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago