YALC-the-GTM-operating-system: Skill for Claude Code

.claude/skills/lemlist/outbound-analyst/SKILL.md

outbound-analyst is a skill for Claude Code from Othmane-Khadri/YALC-the-GTM-operating-system. It costs 175 tokens per session (2,072 once invoked), scanned A, original, MIT.

An analysis guide for judging outbound sales campaign results using data from lemlist, an outreach platform. It covers measures such as reply and open rates.

In plain words
What is it for?
It is for benchmarking campaign metrics, diagnosing underperforming outreach, and suggesting one or two concrete improvements.
Why use it?
It helps determine whether campaign results are good or weak and points to likely reasons when people are not replying.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Othmane-Khadri/YALC-the-GTM-operating-system's own configuration. It tells Claude Code how to work on YALC-the-GTM-operating-system itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything YALC-the-GTM-operating-system configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Othmane-Khadri/YALC-the-GTM-operating-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Othmane-Khadri/YALC-the-GTM-operating-system/main/.claude/skills/lemlist/outbound-analyst/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Othmane-Khadri/YALC-the-GTM-operating-system

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for outbound-analyst

README.md
[![agentmods](https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst/github.svg)](https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst)
Your own site
<a href="https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for outbound-analyst

Your own site · 80×15
<a href="https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,072 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00175 $0.02072
Opus 5 $0.00088 $0.01036
Sonnet 5 $0.00035 $0.00414
Haiku 4.5 $0.00017 $0.00207

Measured 12d ago against content hash 240492b7fa7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

outbound-analyst scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/lemlist/outbound-analyst/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Outbound Analyst

Your job

Give a clear, honest verdict on outreach stats — not "it depends." Every metric has a benchmark. Pull the right one, deliver the verdict, explain the root cause, and give 1–2 concrete fixes. No padding.


Step 1 — Identify what's being evaluated

Check the conversation for:

  • Which metric(s) the user is asking about (reply rate, open rate, accept rate, etc.)
  • Their channel mix (email only / LinkedIn + email / multichannel)
  • Their list size (# of leads in the campaign)
  • Number of steps in the sequence
  • Whether they're asking about a single metric or want a full audit

If they share multiple stats, do a full audit. If they share one number, give a focused verdict on that metric first, then flag if you need more context.


Step 2 — Apply the right benchmark

🎯 Reply Rate — THE metric that matters most

The single KPI to track. If there's only one number to care about, it's this one.

Email-only campaigns (from 244K campaigns, 249M emails):

Verdict Rate
❌ Bad < 2%
🟡 Average ~2–4%
✅ Good 4–10%
🚀 Really good 15%+
🏆 Exceptional 25%+ (tight list + sharp copy)

Global reply rate by channel (accounts for all touchpoints):

Channel mix Global reply rate
Email only 1.1%
LinkedIn + Email 4.7%
LinkedIn + Email + Call 2.8%*
LinkedIn-first sequences 5.7%
Email-first sequences 2.6%

*Call adds friction at scale — the bottleneck effect kicks in.

By list size (tighter = better):

List size Global reply rate
6–50 leads 5.3%
51–200 leads 3.2%
201–500 leads 2.3%
501–1,000 leads 1.9%
1,000+ leads 1.1%

By steps — LinkedIn + Email (sweet spot = 3 steps):

Steps Global reply rate
2 steps 7.0%
3 steps 7.2% ← sweet spot
4 steps 5.0%
5+ steps 3.4%

By steps — Email only (more steps ≠ better):

Steps Global reply rate
2 steps 1.9%
3 steps 1.3%
4 steps 1.1%
5+ steps 0.7%

Read the full file on GitHub · 207 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 207 lines · 175 tokens per session scan A 240492b7fa7d

Subscribe to this mod's changes

outbound-analyst is a skill published in the GitHub repository Othmane-Khadri/YALC-the-GTM-operating-system (301 stars, last pushed 22d ago), licensed MIT. It adds 175 tokens to every session and 2,072 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.