content-marketing-and-brand-growth
Skill1 starsChanged 45 days agoMITView on GitHub
Plans trust-first content campaigns and creative briefs—social posts, product launches, video, thumbnails, carousels, personal brand, networking, and ethical monetization—with platform-aware formats and measurable outcomes. Use when planning, writing, or repurposing marketing content from real work.
In this repository6 other files it gives its agents.
The file
Files
Content Marketing and Brand Growth
Build a durable content system around the user's real work, audience, offer, and goals.
Context gate
Read the prompt, links, files, assets, and destination first. Capture audience, promise, evidence, campaign stage, platform and placement, organic or paid, format, CTA, publishing constraints, and success metric. Ask one to three grouped questions only when a gap changes strategy, truth, format, privacy, or spend; otherwise state a reversible assumption. Never re-ask supplied information.
Trust order: useful content and real conversation → clear positioning → product use, feedback, stars, contributors → qualified networking and client conversations → revenue (services, products, sponsorships, disclosed affiliates). Never invent proof, urgency, testimonials, metrics, partnerships, or outcomes.
Campaigns
Define audience, problem, promise, proof, pillar, journey stage, format, primary CTA, canonical destination, owner, publishing window, and metric. One master idea, then one record per channel with its own job, hook, caption or script, asset, URL, timezone, status, and performance notes. Repurpose the idea, not the copy: text for discussion, images and carousels for explanation, short video for discovery, long-form for depth, an owned page for canonical SEO content. Don't force a schedule onto a single-asset request.
For a standalone video, thumbnail, carousel, static creative, or launch asset, read content-format-execution.md.
Quality and SEO
Important meaning in crawlable text; descriptive titles, natural search language, canonical links, accurate claims, accessible media text, clear disclosures. No trend-chasing, keyword stuffing, engagement bait, or empty motivation.
Measurement
Track separately: reach, impressions, engagement, saves, shares, clicks, repo visits, stars, feedback quality, qualified conversations, leads, revenue. Review after a set window; record what to repeat, change, or stop.
Output
Goal, audience, assumptions or missing inputs, content system or single-asset job, platform matrix when relevant, drafts, production-ready brief or prompts, schedule when relevant, CTA, destination continuity, measurement plan—in the user's language and within their claims, privacy, platforms, and approvals.
Companions (optional; suggest when missing)
conversion-storytelling for narrative, proof, objections, and CTA; global-discovery-browsing-extraction for audience, market, search, or platform evidence; the relevant video, image, animation, or design skill for production.
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
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.

