01
It starts by itself
daily delivery report. Runs in cron or Claude Code routine.
- ↻ daily delivery report
0 8 * * *
sentdm · 3K installsMessaging Performance Analyzer skill
Runs by itself, daily delivery report.
Delivery drops get caught early.
Install the Messaging Performance Analyzer skill and make it a habit: follow https://gethabit.dev/skills/sentdm/messaging-performance-analyzer.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
3K installs48 starsMIT licenceSource on GitHub ↗
Messaging Performance Analyzer
by sentdm · 3K installs
The skill
The messaging performance analyzer skill turns Sent message, activity and webhook data into one diagnosis of delivery failures, funnel drop-offs, read-rate gaps and fallback problems.
Only when you ask.
The habit
Delivery drops get caught early.
↻ Runs by itselfdaily delivery report
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
One export per run and one primary diagnosis.
- 01
Read the baseline
Load past rates per channel and the last diagnosis from the log.
- 02
Pin the cohort
Fix the time window, profile, template, channel and recipient segment before counting.
- 03
Run funnel script
Run python scripts/analyze_mdr_funnel.py on the export with --threshold and --format json.
- 04
Check webhook health
If callbacks are missing, compare GET /v3/webhooks/{id}/events with the endpoint before blaming delivery.
- 05
Split by channel
Compare SMS, WhatsApp and RCS funnels on their own, with READ counted only as engagement.
- 06
Name one diagnosis
Give one main diagnosis, a confidence level and the next verification step tied to evidence.
- 07
Hand off if needed
Pass compliance, RCS or template causes to sms-10dlc-registration, rcs-agent-onboarding or waba-template-author.
- 08
Update the log
Write the day's rates and diagnosis as the new baseline.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only inloops/message-delivery-funnel-loop/
- Talks tono outside service
- Sendsnothing
- Your OKNothing goes out, so it needs no OK.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the Messaging Performance Analyzer skill helps.
Use it when
- ✓ delivery rate dropped
- ✓ messages did not arrive
- ✓ you have an MDR export
Skip it when
- – you need 10DLC registration
- – you write WhatsApp templates
Messaging Performance Analyzer skill, answered.
What do the script exit codes mean?
0 means no observed breach, 2 means bad input or no usable cohort, 3 means an observed breach.
Does it rotate webhook secrets?
Only when you ask or a credential leak is suspected, because rotation invalidates the old secret at once.
Why not average all channels?
SMS, WhatsApp and RCS fail in different ways, so the skill splits them before naming a cause.
How do I install the Messaging Performance Analyzer skill?
Copy the prompt at the top into your agent. It installs the skill from sentdm/sent-plugin and sets up the habit. Or run npx skills add sentdm/sent-plugin --skill messaging-performance-analyzer.
Is the Messaging Performance Analyzer skill free?
Yes. It is published under MIT. Habit is free too.
Messaging Performance Analyzer. Now as a habit.
Install the Messaging Performance Analyzer skill and make it a habit: follow https://gethabit.dev/skills/sentdm/messaging-performance-analyzer.md
All sentdm skills →More ops skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by sentdm, published under MIT. Habit links to the original and never changes it. Is this your skill?