- Home
- Skills
- Mobile Development
- Battery Drain Triage
More screenshots
Works with the AI Agents you already use
Battery Drain Triage
Rank an app's battery contributors from measured statistics and fix the biggest one first, instead of guessing at settings.
$5
Battery Drain Triage
Example session with this skill installed
Rank this summary: sync_job 18% (2 min foreground, 240 min background), screen 12% (120 min foreground, 10 min background), location 6% (5 min foreground, 60 min background).
- Read your context and instructions
- Compiled the battery drain triage
Running the bundled parser on that summary produces:
TOTAL-SHARE-ACCOUNTED: 36% across 3 contributors
1. sync_job: 18% fg=2m bg=240m (background-dominated) <-- FIX FIRST
2. screen: 12% fg=120m bg=10m (foreground-dominated)
3. location: 6% fg=5m bg=60m (background-dominated)
VERDICT: background drain dominates — fix background work first, not foreground rendering.
The skill's worked example matches this pattern: a sync job running every 15 minutes around the clock for hourly-changing data, fixed by lengthening the interval, skipping overnight sync, and refreshing on open — cutting the app from 18 percent to 4 percent with visible freshness unchanged.
Connects securely to your tools. The creator never sees your data.
About this skill
Battery work attracts folklore: every team has a setting someone is sure is responsible. This skill checks folklore against battery statistics. It first establishes whether the app is actually the drain (share, period, ranking), separates foreground from background drain (a split that decides the whole hunt), ranks contributors — wakeups, background jobs, location, network, screen, media — by measured share, fixes only the top contributor, re-measures with the same fixed session, and then judges whether the remaining level is acceptable for the feature.
It covers the hidden patterns statistics undercount (wake locks held across screen-off, aggressive retry loops), gives investigation thresholds for app share and background dominance, and records ruled-out contributors so the next triage does not revisit them. A runnable parser ranks a battery-stats summary and names the first fix target with a foreground/background verdict.
- Needs battery statistics for a defined period; a bare user complaint without numbers can only start, not finish, a triage.
- Battery numbers vary by device and battery health, so thresholds are ranking guides, not verdicts.
- Cannot diagnose hardware battery defects; a device that drains with no apps running is a different problem.
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 any payment.
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