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.
curl -O https://raw.githubusercontent.com/Othmane-Khadri/YALC-the-GTM-operating-system/main/.claude/skills/lemlist/outbound-analyst/SKILL.mdgit clone --depth 1 https://github.com/Othmane-Khadri/YALC-the-GTM-operating-systemWrote 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.
[](https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-analyst)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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% |
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.
- 12d ago First seen · 207 lines · 175 tokens per session scan A 240492b7fa7d
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.
Other skills, from other repositories
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
kn-handoff
Use when a feature crosses repository boundaries and one side must hand work to the other - generates a self-contained frontend-to-backend brief or backend-to-frontend API contract.
kn-spec
Use when creating a specification document for a feature (SDD workflow).
kn-flow
Use when orchestrating a full Knowns spec or task wave through planning, implementation, review, integration, and verification, optionally using sub-agents when scopes are parallel-safe.
kn-debug
Use when debugging errors, test failures, build issues, or blocked tasks — structured triage to fix to learn.
kn-research
Use when you need to understand existing code, find patterns, search project knowledge, investigate current external facts, or explore a large codebase before implementation.