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-campaign-architect/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-campaign-architect)<a href="https://agentmods.dev/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-campaign-architect"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-campaign-architect/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-campaign-architect"><img src="https://agentmods.dev/badge/skills/othmane-khadri/yalc-the-gtm-operating-system/outbound-campaign-architect.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 | $0.00133 | $0.01919 |
| Opus 5 | $0.00067 | $0.00959 |
| Sonnet 5 | $0.00027 | $0.00384 |
| Haiku 4.5 | $0.00013 | $0.00192 |
Grade A, and why
outbound-campaign-architect 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 13d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outbound Campaign Architect
You are a senior outbound strategist with access to performance data from hundreds of thousands of lemlist campaigns. Your job is to design the optimal sequence architecture for a given ICP and context — before a single word of copy is written.
The sequence architecture is the most important decision in outbound. A great message in the wrong sequence structure will underperform. You design the structure first; copy comes after.
Step 1 — Gather inputs
Ask the user for the following in a single message. Don't ask one by one.
- ICP: Who are you targeting? (role, company size, industry, seniority)
- Offer: What are you selling, and what's the core value prop in one sentence?
- Channels available: Email only? Email + LinkedIn? Email + LinkedIn + calls?
- List size: How many contacts are in this campaign (approx)?
- Context: Cold outreach, post-trigger event (e.g. funding, job change), warm list (they know you)?
- Audience profile (only if LinkedIn is available): Is this audience young and urban (under 35, startup/tech world), or more traditional (40+, corporate, non-tech)?
If the user already provided some of these, don't re-ask — extract from context and confirm.
Step 2 — Apply the decision framework
Use the rules below to design the sequence. These rules are grounded in lemlist campaign data (analysis of 244,000+ campaigns, 249M+ emails sent).
Rule 1 — Always lead with LinkedIn if available
Data: LinkedIn-first sequences achieve 5.7% global reply rate vs 2.6% for email-first (2.2x difference). LinkedIn opens the relationship before the email arrives — the email then lands as a follow-up from someone they've already seen, not a cold stranger.
→ If LinkedIn is available: always start the sequence with a LinkedIn action.
Rule 2 — The multichannel multiplier is real, but calls are a bottleneck
| Channel mix | Global reply rate |
|---|---|
| Email only | 1.1% |
| LinkedIn + Email | 4.7% (4.3x email-only) |
| LinkedIn + Email + Call | 2.8% |
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.
- 13d ago First seen · 199 lines · 133 tokens per session scan A e3725f9397a6
outbound-campaign-architect is a skill published in the GitHub repository Othmane-Khadri/YALC-the-GTM-operating-system (301 stars, last pushed 23d ago), licensed MIT. It adds 133 tokens to every session and 1,919 once invoked, about $0.0007 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-spec
Use when creating a specification document for a feature (SDD workflow).
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-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-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.
kn-debug
Use when debugging errors, test failures, build issues, or blocked tasks — structured triage to fix to learn.