Reply Audit
Forensic audit of outbound replies → root cause (targeting vs pitch) → 9-section report.
npx skills add victor-shulga/outbound-engine-skills/skills/reply-auditWhat it does
Takes a batch of outbound replies from any source, classifies every one on three independent axes, diagnoses whether the engine is failing on targeting/data or on the pitch, mines the best replies into reusable templates, and ships a 9-section audit with a ready message for every named lead.
Input and output
Key features
- Three-axis reply classification
- Root cause: targeting/data vs SDR/pitch
- Extracts gold-standard reply templates
- A ready-to-send message per named lead
How to install
Node 18+ required. The command installs the skill into the current project folder:
npx skills add victor-shulga/outbound-engine-skills/skills/reply-auditTo keep the skill at hand in every project, add -g:
npx skills add -g victor-shulga/outbound-engine-skills/skills/reply-auditIn Claude Code: unzip the folder reply-audit into ~/.claude/skills/ and restart the app. In Claude Desktop or on claude.ai: Settings → Capabilities → Skills → upload the same archive.
Download the ZIP · 5 KBOpen the skill's folder on GitHub and save the files. The main file is SKILL.md, and the rest is pulled in from it.
Check it works: type /reply-audit in the chat — the skill should answer. If it does not: skills are read at session start, so restart Claude.