Agent skill

Outbound Campaign Architect

by Othmane-Khadri in Othmane-Khadri/YALC-the-GTM-operating-system

Designs high-performance outbound sequences based on ICP, available channels, and empirical lemlist data from hundreds of thousands of campaigns.

MITAuto-check passedSales & Support

Install Outbound Campaign Architect

skills CLI
$ npx skills add Othmane-Khadri/YALC-the-GTM-operating-system --skill outbound-campaign-architect -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Othmane-Khadri/YALC-the-GTM-operating-system outbound-campaign-architect --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Othmane-Khadri/YALC-the-GTM-operating-system.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/lemlist/outbound-campaign-architect .claude/skills/outbound-campaign-architect && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
outbound-campaign-architect
GitHub stars
318
Token cost
~1.9k tokens
SKILL.md length
1,038 words
Files
1
Skills in repo
57
Repo updated
First seen
Licence
MIT

At a glance

Designs high-performance outbound sequences based on ICP, available channels, and empirical lemlist data from hundreds of thousands of campaigns.

  • Works in 3 steps: Gather inputs → Apply the decision framework → Output the sequence architecture
  • The user wants to build
  • SKILL.md covers Step 1 — Gather inputs, Step 2 — Apply the decision…, Step 3 — Output the sequence… and 🎯 Campaign: [Short name — ICP…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Outbound Campaign Architect is an agent skill from Othmane-Khadri/YALC-the-GTM-operating-system. Designs high-performance outbound sequences based on ICP, available channels, and empirical lemlist data from hundreds of thousands of campaigns. Use this skill whenever the user wants to build, design, or optimize an outbound sequence, campaign, or cadence — whether they say "create a sequence", "build a campaign", "what steps should I use", "how should I structure my outreach", or "help me reach out to X". Also trigger when the user mentions an ICP + a goal (e.g. "I want to book meetings with VP Sales at Series…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Sales & Support, covering Cold outreach. It works with LinkedIn. The repository describes itself as: YALC 1.0, the open-source Clay alternative. MIT, CLI-first, self-hosted, runs in Claude Code. Yalc today is an intelligent orchestration layer that runs pre configured GTM agents…. The licence is MIT.

When your agent uses it

  • The user wants to build
  • Optimize an outbound sequence
  • Cadence — whether they say create a sequence
  • Build a campaign

Example prompts

  • “create a sequence”
  • “build a campaign”
  • “what steps should I use”
  • “/outbound-campaign-architect”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Gather inputs
  2. Apply the decision framework
  3. Output the sequence architecture

What it can do on your machine

Read from SKILL.md and the folder at commit 5686d1f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Outbound Campaign Architect loads about 1.9k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 1,038 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~153
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Othmane-Khadri/YALC-the-GTM-operating-system at commit 5686d1f, republished under its MIT licence (© Othmane-Khadri). 1,038 words, ~1,942 tokens.

Download SKILL.mdSave it as .claude/skills/outbound-campaign-architect/SKILL.md (or your agent's skills folder).
name
outbound-campaign-architect
description
Designs high-performance outbound sequences based on ICP, available channels, and empirical lemlist data from hundreds of thousands of campaigns. Use this skill whenever the user wants to build, design, or optimize an outbound sequence, campaign, or cadence — whether they say "create a sequence", "build a campaign", "what steps should I use", "how should I structure my outreach", or "help me reach out to X". Also trigger when the user mentions an ICP + a goal (e.g. "I want to book meetings with VP Sales at Series B SaaS"). Always use this skill before any sequence is written.

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.

  1. ICP: Who are you targeting? (role, company size, industry, seniority)
  2. Offer: What are you selling, and what's the core value prop in one sentence?
  3. Channels available: Email only? Email + LinkedIn? Email + LinkedIn + calls?
  4. List size: How many contacts are in this campaign (approx)?
  5. Context: Cold outreach, post-trigger event (e.g. funding, job change), warm list (they know you)?
  6. 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 mixGlobal reply rate
Email only1.1%
LinkedIn + Email4.7% (4.3x email-only)
LinkedIn + Email + Call2.8%

Counterintuitive finding: adding calls lowers the global reply rate. Why? Calls are manual and time-intensive, so teams that add calls either send to far fewer contacts, or abandon the follow-through. Calls are higher quality per touchpoint, but they create a volume bottleneck that hurts the overall numbers.

→ Recommend calls only when list size is small (under 50 contacts) and the deal size justifies the manual effort. Position calls as high-intent follow-ups, not openers.

Rule 3 — Fewer steps beats more steps (especially email-only)
StepsEmail onlyLinkedIn + Email
2 steps1.9%7.0%
3 steps1.3%7.2% ← sweet spot
4 steps1.1%5.0%
5+ steps0.7%3.4%

For email-only: keep it to 2 steps max. Each additional step degrades performance significantly. Less is more — better to improve the 2 steps than add a 3rd.

For LinkedIn + Email: 3 steps is the sweet spot (7.2%). Performance drops noticeably at 4 steps and sharply at 5+. Don't build long sequences — build better ones.

Rule 4 — List size is a performance multiplier
List sizeGlobal reply rate
6–50 leads5.3%
51–200 leads3.2%
201–500 leads2.3%
501–1,000 leads1.9%
1,000+ leads1.1%

Smaller, more targeted lists dramatically outperform large blasts. This isn't just about personalization — it reflects ICP sharpness, message relevance, and sender reputation.

→ If the user's list exceeds 200 contacts, recommend splitting into tighter segments (by trigger, by sub-ICP, by company size) rather than sending one big campaign.

Rule 5 — Simulate human behavior with conditional steps

The sequences that perform best mimic how a real human would follow up — not just a timer firing. Build in these behavioral logic patterns wherever relevant:

  • LinkedIn profile visit before email: signals that a human looked you up, increases open rate
  • Email right after an unanswered call: natural follow-up ("just tried to reach you")
  • If LinkedIn invite not accepted after 7 days → switch to email: don't wait forever
  • If LinkedIn invite accepted but no reply → send a message, not an email: use the warm channel
  • Don't stack two emails back to back if LinkedIn is available — use the channel switch as the pattern interrupt
Show full SKILL.md (384 more words)Show less
Rule 6 — Voice notes: selective use only

LinkedIn voice notes increase LinkedIn reply rate from 26.9% to 29.5% (+10% relative uplift). Worth using — but only for the right audience.

Use voice notes when: audience is under ~35, works in tech/startup, urban, informal culture. Do NOT use voice notes when: audience is 40+, traditional industry (finance, legal, manufacturing, pharma), corporate/enterprise, or any context where formality is expected.

When in doubt, don't use them. A voice note that feels out of place damages the relationship more than it helps.


Step 3 — Output the sequence architecture

Produce the sequence as a visual step-by-step plan. Use this exact format:


🎯 Campaign: [Short name — ICP + goal]

ICP: [Restate target] Offer: [Restate value prop] Recommended list size: [Based on Rule 4 — cap or split recommendation] Expected global reply rate: [Benchmark from data, given the channel mix and list size]


Sequence Architecture

Step 1 — [Day X] — [Channel] — [Action type] Purpose: [What this step is trying to do psychologically / what it signals to the prospect] Conditional logic: [If any — e.g. "Only send if LinkedIn invite was accepted"] Timing note: [Why this timing, not another]

Step 2 — [Day X] — [Channel] — [Action type] Purpose: ... Conditional logic: ... Timing note: ...

(repeat for each step)


Conditional branches

List any if/then logic that should be configured:

  • If [condition] → [action]
  • If [condition] → [action]

Why this architecture (brief)

2–3 sentences explaining the core reasoning: why this channel order, why this step count, why this timing. Ground it in the data where relevant.


⚠️ What NOT to do

2–3 common mistakes for this specific ICP/context that would kill performance.


Next step

After the sequence architecture is approved, the next step is to write the actual messages for each step. Suggest: "Want me to write the copy for each step now, with the right angle for this ICP?"


Timing reference (defaults)

Use these as defaults unless the context suggests otherwise:

GapRecommended
LinkedIn action → First email1–2 days
Email → LinkedIn follow-up2–3 days
Email → Email follow-up3–5 days
After unanswered call → EmailSame day or next morning
LinkedIn invite timeout (no accept)7 days, then switch to email
Total sequence duration10–21 days max

Keep sequences tight. The goal is to be memorable and relevant, not persistent and annoying. A 3-week sequence that ends cleanly is better than a 6-week sequence that trails off.

© Othmane-Khadri, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/lemlist/outbound-campaign-architect of Othmane-Khadri/YALC-the-GTM-operating-system.

Open the folder on GitHubat commit 5686d1f

Compare with similar skills

Outbound Campaign Architect next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Outbound Campaign Architect compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Outbound Campaign Architect this skillOthmane-Khadri/YALC-the-GTM-operating-system318—~1.9kAutomated safety check: PassMIT
Prospectingcoreyhaines31/marketingskills54k—~5kAutomated safety check: PassMIT
Sales OsromangojiberryAI/gojiberryai-sales-os139—~2kAutomated safety check: PassMIT
Cold Outreach Personalizeraiskilloftheweek/claude-ai-skill-of-the-week149—~2.6kAutomated safety check: PassNone
B2B Lead Generationminhnv0807/ai-business-skills609—~1.2kAutomated safety check: PassMIT
Cold Emailcoreyhaines31/marketingskills54k—~3.1kAutomated safety check: PassMIT

Similar skills

  • Prospecting

    coreyhaines31/marketingskills

    When the user wants to find, qualify, and build a list of prospects to reach out to, across B2B SaaS, general B2B, or local small businesses.

    54k GitHub stars~5k tokensUpdated 2 days ago
    Sales & SupportAuto-check passed
  • Sales Os

    romangojiberryAI/gojiberryai-sales-os

    A complete outbound sales department in one skill. An agent skill from romangojiberryAI/gojiberryai-sales-os.

    139 GitHub stars~2k tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed
  • Cold Outreach Personalizer

    aiskilloftheweek/claude-ai-skill-of-the-week

    Generates hyper-personalized cold outreach messages (email, LinkedIn DM, connection request) from raw prospect research.

    149 GitHub stars~2.6k tokensUpdated 4 mo ago
    Sales & SupportAuto-check passed
  • B2B Lead Generation

    minhnv0807/ai-business-skills

    Plans B2B pipeline work from ICP definition and prospecting through lead scoring, outbound sequences, sales assets and MQL to SQL handoff, aiming at qualified pipeline.

    609 GitHub stars~1.2k tokensUpdated 29 days ago
    Sales & SupportAuto-check passed
  • Cold Email

    coreyhaines31/marketingskills

    Write and run B2B cold outbound that gets replies, from cold emails and follow-ups to sending setup, LinkedIn, multichannel cadences, and reply handling.

    54k GitHub stars~3.1k tokensUpdated 2 days ago
    Sales & SupportAuto-check passed
  • Cold Outreach Sequence Builder

    BrianRWagner/ai-marketing-claude-code-skills

    Builds researched LinkedIn and email outreach for prospects, from a single message to a multi-prospect system, with personalization graded by the signals found.

    441 GitHub stars~1.9k tokensUpdated 6 mo ago
    Sales & SupportAuto-check passed

More from Othmane-Khadri/YALC-the-GTM-operating-system

All 57 skills in this repo
  • Claap Weekly Recap

    Othmane-Khadri/YALC-the-GTM-operating-system

    Turns a week of Claap-recorded sales calls into action items and focus blocks on a Notion Kanban, delivered with a Slack summary.

    318 GitHub stars~5.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Fullenrich Plg Reverse Lookup

    Othmane-Khadri/YALC-the-GTM-operating-system

    A skill your agent uses when the user says "set up FullEnrich reverse lookup for trial signups", "PLG enrichment webhook", "identify free trial signups via FullEnrich", "reverse email lookup for…

    318 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Fullenrich Content Engagers

    Othmane-Khadri/YALC-the-GTM-operating-system

    A skill your agent uses when the user says "enrich people who engaged with this post", "qualify post engagers with FullEnrich", "scrape and enrich LinkedIn post {URL}", "engagers from this post into…

    318 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Fullenrich Event Attendees

    Othmane-Khadri/YALC-the-GTM-operating-system

    A skill your agent uses when the user says "enrich this LinkedIn event", "enrich attendees of this event", "enrich this attendees CSV", "scrape and enrich LinkedIn event {URL}", "FullEnrich event…

    318 GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Answer Linkedin Comments

    Othmane-Khadri/YALC-the-GTM-operating-system

    Reply to comments on a LinkedIn post via Unipile — drafts thread-aware replies grounded in the user's voice and the conversation context, then sends on approval.

    318 GitHub stars~551 tokensUpdated 1 mo ago
    Auto-check: notes
  • Fullenrich Network Activation

    Othmane-Khadri/YALC-the-GTM-operating-system

    A skill your agent uses when the user says "activate co-founder network with FullEnrich", "enrich LinkedIn connections export", "qualify my LinkedIn connections CSV", "turn Connections.csv into a…

    318 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check: warnings

Works with

Categories

Questions about Outbound Campaign Architect

What does Outbound Campaign Architect do?

Designs high-performance outbound sequences based on ICP, available channels, and empirical lemlist data from hundreds of thousands of campaigns. Outbound Campaign Architect is an agent skill from Othmane-Khadri/YALC-the-GTM-operating-system. Designs high-performance outbound sequences based on ICP, available channels, and empirical lemlist data from hundreds of thousands of campaigns.

When should I use Outbound Campaign Architect?

Outbound Campaign Architect fits situations like: the user wants to build; optimize an outbound sequence; cadence — whether they say create a sequence; build a campaign.

How do I install Outbound Campaign Architect in Claude Code?

Run `npx skills add Othmane-Khadri/YALC-the-GTM-operating-system --skill outbound-campaign-architect -a claude-code`. Or copy the skill folder (.claude/skills/lemlist/outbound-campaign-architect in Othmane-Khadri/YALC-the-GTM-operating-system) into .claude/skills/outbound-campaign-architect in your project. Claude Code loads it when a task matches its description.

How do I install Outbound Campaign Architect in Codex?

Run `npx skills add Othmane-Khadri/YALC-the-GTM-operating-system --skill outbound-campaign-architect -a codex`. Or copy the skill folder (.claude/skills/lemlist/outbound-campaign-architect in Othmane-Khadri/YALC-the-GTM-operating-system) into .agents/skills/outbound-campaign-architect in your project. Codex loads it when a task matches its description.

Can I use Outbound Campaign Architect in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Othmane-Khadri/YALC-the-GTM-operating-system --skill outbound-campaign-architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/outbound-campaign-architect, .gemini/skills/outbound-campaign-architect, .github/skills/outbound-campaign-architect and .opencode/skills/outbound-campaign-architect in your project.

What does Outbound Campaign Architect need to run?

SKILL.md names no scripts, command-line tools or credentials: Outbound Campaign Architect is instructions for the agent only.

Does Outbound Campaign Architect access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Outbound Campaign Architect safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Outbound Campaign Architect use?

Outbound Campaign Architect is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Outbound Campaign Architect use?

About 1.9k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Outbound Campaign Architect?

Skills that share tags, products or a category with Outbound Campaign Architect: Prospecting (coreyhaines31/marketingskills, 54k stars), Sales Os (romangojiberryAI/gojiberryai-sales-os, 139 stars), Cold Outreach Personalizer (aiskilloftheweek/claude-ai-skill-of-the-week, 149 stars) and B2B Lead Generation (minhnv0807/ai-business-skills, 609 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Outbound Campaign Architect?

Othmane-Khadri (a GitHub user) maintains it in Othmane-Khadri/YALC-the-GTM-operating-system, which has 318 GitHub stars. The repository holds 57 skills in this directory. The repository was last updated on August 20, 2026.

Source: Othmane-Khadri/YALC-the-GTM-operating-system on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.