marketing-guru

marketing-guru is a skill for Claude Code, Codex from dasein108/slope-studio. It costs 121 tokens per session (2,274 once invoked), scanned A, original, MIT.

A coordinator for a YouTube channel’s repeating growth process: generate ideas, publish a test, wait, review results, and choose what to try next.

In plain words
What is it for?
Use it to read channel state, generate and select marketing bets, coordinate publishing, and connect measurement and learning steps.
Why use it?
It keeps ideas, experiments, results, and lessons in one journal so future decisions use the channel’s own history.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/dasein/dev/slope-studio.

Good fit Use it to read channel state, generate and select marketing bets, coordinate publishing, and connect measurement and learning steps.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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 marketing-guru

README.md
[![agentmods](https://agentmods.dev/badge/skills/dasein108/slope-studio/marketing-guru/github.svg)](https://agentmods.dev/skills/dasein108/slope-studio/marketing-guru)
Your own site
<a href="https://agentmods.dev/skills/dasein108/slope-studio/marketing-guru"><img src="https://agentmods.dev/badge/skills/dasein108/slope-studio/marketing-guru/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 marketing-guru

Your own site · 80×15
<a href="https://agentmods.dev/skills/dasein108/slope-studio/marketing-guru"><img src="https://agentmods.dev/badge/skills/dasein108/slope-studio/marketing-guru.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,274 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.
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 $0.00121 $0.02274
Opus 5 $0.00060 $0.01137
Sonnet 5 $0.00024 $0.00455
Haiku 4.5 $0.00012 $0.00227

Measured 11d ago against content hash 57fb5224b890, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

marketing-guru 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 11d 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.

.agent-instructions/skills/marketing-guru/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

marketing-guru — orchestrate the growth loop

Make a channel go viral by running a closed feedback loop backed by a persistent journal. You don't guess once — you bet, deploy, measure against the channel's own history, learn, and bet again. The creative steps are their own lego-block skills any agent can use alone; this skill is the conductor, and it also owns the thin read/pick/report helpers.

   ┌──────────────────────────────────────────────────────────────┐
   │  IDEATE  → BACKLOG → DEPLOY → (wait 48-72h) → MEASURE → LEARN  │
   │     ▲                                                      │   │
   │     └──────────── strategy + next_seeds ◀─────────────────┘   │
   └──────────────────────────────────────────────────────────────┘

The skills (invoke any one directly)

Step Skill / here One-liner CLI it drives
setup youtube-branding channel identity: banner/avatar/logo + keywords/description (once / on rebrand) studio brand
0 guru: journal read phase + strategy + bets (start here) journal · recall
1 marketing-ideate agent generates falsifiable bets → backlog addideate fallback)
2 guru: backlog pick the next bet (bandit, 60/40 fallback) backlog · bandit
3 marketing-deploy produce+publish via film-maker, then link studio run · link
4+5 marketing-measure-learn score virality, snapshot age buckets, slice hidden relations, then reflect → strategy (wait 48-72h) measure · snapshots · insights · slice · compare · strategy
guru: report write the growth brief to disk report
marketing-autopilot run the WHOLE loop on a schedule (deferred-measurement aware) tick · autopilot

Design rule: the thinking (what to make, which bet, what was learned) is the agent's, done in the skills; the studio marketing CLI commands are helpers — pure I/O for persistence (add/strategy), retrieval (recall/backlog/journal/bandit), and deterministic work (link, measure). ideate/learn keep scripted LLM fallbacks for quick non-agent passes.

Read the full file on GitHub · 149 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 149 lines · 121 tokens per session scan A 57fb5224b890

Subscribe to this mod's changes

marketing-guru is a skill published in the GitHub repository dasein108/slope-studio (3 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 2,274 once invoked, about $0.0006 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 2026-08-31.