agentleFS
Othmane-KhadriOthmane-Khadri/YALC-the-GTM-operating-system/.claude/skills/yalc-orientation/SKILL.md

yalc-orientation

Skill298 starsChanged 6 months agoMITView on GitHub

First-touch onboarding for someone who just opened the YALC repo. Triggers when the user pastes the repo URL `https://github.com/Othmane-Khadri/YALC-the-GTM-operating-system` (with or without trailing slash, with or without `.git`), or says any of: 'what is yalc', 'what is this', \"let's start\", \"let's go\", 'i just cloned this', 'how do i use this', 'got the repo', 'where do i begin', \"i'm new to yalc\". Introduces YALC, checks prerequisites, asks the user what they want to do, and routes to the right capability. Hands off to /setup if the environment isn't initialized.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run these checks silently and report only what's missing.

    line 18
  2. Very specific:

    If ~/.gtm-os/ is not initialized, route to /setup immediately regardless of what the user says next.

    line 31
  3. Distinctive:

    Wait for the answer. Don't assume.

    line 44
  4. Very specific:

    Hard guard: if at any point during routing you discover ~/.gtm-os/ is not initialized (e.g., a command errors with a missing-config …

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

YALC Orientation

A new user just opened this repo. Walk them through a 4-step orientation so they know what YALC is, that their environment is ready, and which capability fits their first job.

Do NOT duplicate setup logic. If the user needs to install or configure, hand off to the existing /setup skill at .claude/skills/setup/SKILL.md.

Step 1 — Overview

Read CLAUDE.md at the repo root and surface the "What YALC is" section to the user. Quote or paraphrase it — that file is the single source of truth, DO NOT duplicate the text into this skill body. Keep the intro to 3–5 sentences. End with one sentence framing the architecture split: "Read context from your knowledge base, execute from this repo."

Step 2 — Prerequisite check

Run these checks silently and report only what's missing. If everything passes, say "environment looks good" and continue.

  1. Node ≥ 20 (node --version).
  2. ~/.gtm-os/ exists (test -d ~/.gtm-os).
  3. ~/.gtm-os/.env is non-empty (test -s ~/.gtm-os/.env).
  4. yalc-gtm is resolvable on PATH (which yalc-gtm).

For each failure, surface the specific fix from CLAUDE.md "Common stuck states":

  • yalc-gtm not on PATH → npm i -g yalc-gtm-os (or pnpm link --global from the repo root if hacking on YALC itself).
  • ~/.gtm-os/ missing or .env empty → run yalc-gtm start to scaffold; the CLI writes the template and opens it for editing.
  • Localhost won't open → confirm yalc-gtm start exited cleanly, copy the URL from the terminal banner, check port 3847 isn't taken (lsof -i :3847).
  • Node < 20 → upgrade via nodejs.org.

If ~/.gtm-os/ is not initialized, route to /setup immediately regardless of what the user says next. The /setup skill owns install + scaffold + key entry + capture + preview + commit + doctor + framework recommendation. Don't reimplement any of it here.

Step 3 — Intent question

Once prerequisites pass, ask the user this exact question with 4 multi-choice options:

What would you like to do first?

(a) Qualify leads — score a CSV/JSON list against your ICP using the 7-gate pipeline. (b) Launch a LinkedIn campaign — multi-step outreach with A/B variants. (c) Scrape a LinkedIn post for engagers — pull likers/commenters into a lead list. (d) Show me everything / I'm exploring — guided tour of every command.

Wait for the answer. Don't assume.

Step 4 — Route

Based on the user's choice, route to the matching CLI command. Use the invocation pattern:

cd ~/Desktop/gtm-os && set -a && source .env.local && set +a && npx tsx src/cli/index.ts <command>
ChoiceRoute to
(a) Qualify leads`leads:import --source <csvjsonnotionvisitorsengagers> --input <path>thenleads:qualify --result-set <id>`. Ask the user for the input source and path before running.
(b) Launch a LinkedIn campaigncampaign:create --title <t> --hypothesis <h>. Ask for title and hypothesis.
(c) Scrape a LinkedIn postleads:scrape-post --url <linkedin-url>. Ask for the post URL.
(d) Show me everythingRun yalc-gtm --help, then offer a guided tour of the major command families (leads:*, campaign:*, email:*, orchestrate).

Hard guard: if at any point during routing you discover ~/.gtm-os/ is not initialized (e.g., a command errors with a missing-config message), stop the routed flow and hand off to /setup first. Resume the original intent after setup completes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.