Individual skill

outbound-performance-diagnosis

Use this skill when an outbound campaign is underperforming and the cause isn't obvious — replies dropped, meetings dried up, a sequence that worked stopped working, or the numbers look fine but nothing closes. Works through the funnel in fixed order so the real leak gets fixed instead of the most visible one. Produces the diagnosis, the evidence for it, and the single next fix. Trigger phrasings: "why did our reply rate drop", "campaign isn't working", "diagnose this campaign", "opens are fine but no replies", "replies but no meetings", "should we change the copy", "our sequence stopped working".

skills/tanyo-gochev/outbound-performance-diagnosis/SKILL.md

Read pinned source

Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 237
Repository last updated: Oct 20, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

marketing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,127 bytes

Read excerpt


Applies to a live campaign with data. Produces the leak, the evidence, and one fix — not a list of everything that could be improved.

## Work the layers in order and stop at the first break

The order is not optional. Each layer's numbers are meaningless until the layer above it is healthy, and the classic failure is optimising subject lines for an audience that never received the email.

**Layer 1 — delivery.** Bounce rate, spam complaints, inbox placement. **If this layer is broken, stop. Change nothing else.** You cannot learn anything about copy, offer, or targeting from messages that never arrived, and every test you run in that state teaches you something false.

**Layer 2 — engagement.** Opens, and how they decay across steps. Treat opens as diagnostic, not as a result: tracking pixels cost you placement, and open data is unreliable enough on some clients that low opens with healthy replies usually means the pixel, not the copy. A drop of more than about a fifth per step is sequence fatigue or degrading deliverability, not a subject-line problem.

**Layer 3 — replies.** Total reply rate and reply rate by step. Read it against opens:

- Opens healthy, replies near zero → **copy or offer.** They're reading and not moved.
- Opens weak and replies weak → **fix delivery and subject first.** Reply data isn't readable yet.