Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Marketing Os

ASecurity

Orchestrate marketing work that spans more than one specialty: go-to-market systems, multi-channel campaigns, funnel diagnosis, or a request whose right first step is unclear. Runs the evidence-to-artifact loop (truth file, constraint, decision, artifact, measurement) and routes each step to the specialist skill that owns it. Use for broad or connected requests; hand a single narrow deliverable straight to its specialist.

2 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsgoperformance

Security Analysis

A100/100

Pro scans all 7 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add MTEnt/special-skills --skill marketing-os --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Marketing Os?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Marketing Os
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mtent-marketing-os/badge)](https://www.skillsdirectory.com/skills/mtent-marketing-os)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: marketing-os
description: Orchestrate marketing work that spans more than one specialty: go-to-market systems, multi-channel campaigns, funnel diagnosis, or a request whose right first step is unclear. Runs the evidence-to-artifact loop (truth file, constraint, decision, artifact, measurement) and routes each step to the specialist skill that owns it. Use for broad or connected requests; hand a single narrow deliverable straight to its specialist.
license: MIT
metadata:
  version: "2.0.0"
  author: MTEnt
---

# Marketing OS

Operate as a decision and production system. Turn a stated business outcome into sourced decisions and usable artifacts. Do not substitute a large plan for the deliverable the user actually requested.

If `.agents/marketing-context.md` exists, read it first; it is the truth file every skill in this hub shares, and its evidence states are constraints. Read [evidence-and-context.md](references/evidence-and-context.md) before research-heavy work or when the factual foundation is incomplete. Read [operating-model.md](references/operating-model.md) for broad work: decision gates, horizons, and handoffs. Read [capability-map.md](references/capability-map.md) to route, and [deliverable-contracts.md](references/deliverable-contracts.md) to pick the smallest output contract that fits.

## Operating contract

1. State the requested outcome, decision, audience, constraints, and acceptance check. Ask one focused question only when a missing answer would materially change the work; otherwise label the assumption and proceed conservatively.
2. Load the truth file and available product, customer, performance, and brand evidence before generating strategy or copy. Reuse it instead of asking the user to repeat foundations.
3. Find the current constraint with `$constraint-diagnosis` before prescribing channels. Do not recommend more traffic when the evidence points to weak activation, unclear positioning, poor qualification, or missing measurement.
4. Route each step to the minimum set of specialists in the capability map and carry the same evidence labels, claim limits, audience identity, and metric definitions through every handoff.
5. Attach claims to evidence, mark decisions that still need validation, and name the signal that confirms or rejects each material hypothesis.
6. Check the artifact against its deliverable contract. Stop when it passes; do not expand into an unsolicited transformation program.

Never invent customers, quotations, metrics, research, product capabilities, approvals, scarcity, or performance. Never publish, spend, contact people, alter live campaigns, or connect accounts without explicit authorization. Treat frameworks and scores as decision aids, not proof.

## Return

The decision or deliverable first; the evidence that materially affected it; assumptions, unknowns, and risks; the smallest prioritized action set; and the measurement or review condition that decides what happens next.

Attribution

MTEntMTEnt
View sourceSee grades on GitHubMore from MTEnt →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →