Agent skill
founder-content-engine
Turn a founder's actual point of view into a repeatable content engine: extract the opinions worth publishing, structure them into posts, and build a 90-minutes-a-week operating rhythm.
Filed under Content and SEO.
From vcxcvii/pipeline-skills · 10 skill entries · 0 · pushed 2026-09-25
What it does when it runs
Turn a founder's actual point of view into a repeatable content engine: extract the opinions worth publishing, structure them into posts, and build a 90-minutes-a-week operating rhythm. Use when a founder posts inconsistently, when content sounds generic or AI-written, or when the user asks how to build founder-led or LinkedIn content that compounds.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/vcxcvii/pipeline-skills.git /tmp/pipeline-skills git -C /tmp/pipeline-skills sparse-checkout set "skills/founder-content-engine" mkdir -p ~/.claude/skills/founder-content-engine cp -R "/tmp/pipeline-skills/skills/founder-content-engine/." ~/.claude/skills/founder-content-engine/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
Or take the whole library
This repo ships a .claude-plugin manifest, so Claude Code can install all 10 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.
/plugin marketplace add vcxcvii/pipeline-skills /plugin
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from vcxcvii/pipeline-skills/blob/d284df833e7dd2f21ff15384461ea6fcd3f454c4/skills/founder-content-engine/SKILL.md, which is licensed MIT (repository). 514 words, 11 headings.
Founder Content Engine (B2B SaaS)
Founder content fails for one of two reasons: the founder has no time, or the content has no opinion. This skill fixes the second one and then designs around the first.
Setup
Interview the founder for the raw material. Ask these, and keep the answers verbatim:
- What does almost everyone in your category believe that you think is wrong?
- What did you believe two years ago that you no longer believe, and what changed your mind?
- What do buyers consistently get wrong in the first call?
- What is the most expensive mistake you watched a customer make?
- What are you refusing to build, and why?
If the answers are safe and agreeable, push once: ask what they would say if no prospect were watching. Safe answers produce content nobody remembers.
Build the engine
1. Isolate the spikes
From the answers, pull three to five positions that are specific enough to disagree with. Discard anything that a competitor's founder could post unchanged. That test removes most of the list, and that is the point.
2. Turn each spike into a post ladder
For every position, draft three posts at different depths: the claim on its own, the story that proves it, and the tactical how-to that follows from it. One position becomes three weeks of material without repeating itself.
3. Write to the shape of the platform
Open with the claim, not the setup. One idea per post. Short lines. No hook formulas, no "here's what I learned" preamble, no engagement bait. If a post needs a listicle to be interesting, the idea underneath is weak.
4. Design the 90-minute rhythm
One 45-minute recorded conversation every two weeks produces the raw material. The rest is editing. Specify who edits, who posts, and what the founder actually has to do, which should be talking and approving, never drafting from blank.
5. Decide what compounds
Pick the one asset per month that outlives the feed: a teardown, a data point, a written position. Feed posts point at it. Without this, the engine produces attention that ends when the scrolling ends.
Output
- The three to five positions, written as claims
- Nine to fifteen drafted posts, grouped by position
- The two-week operating rhythm, with owners
- The monthly compounding asset, named and scoped
- A kill list: the generic topics this founder should never post about
Rules
- Keep the founder's own words and speech rhythm. If the draft sounds like a marketer wrote it, it will not get posted, and it should not be.
- Never fabricate a story, a customer, or a number from the founder's life.
- No em-dashes, no engagement bait, no "unpopular opinion" framing.
- If the founder has no genuine disagreement with their category, say so. The honest fix is research, not a posting schedule.
Related skills
positioning-canvas for the claim underneath the content.
aeo-page-audit to make the compounding asset citable.
icp-sharpener-b2b to know who the posts are for.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- leveling-up-content-engine by ericosiu · 3,608
- video-content-engine by ericosiu · 3,608
- founder-led-content by AIDevGTM · 310
- seo-content-engine by edupegoretti · 0
- content-strategy by coreyhaines31 · 53,460
- linkedin-content-planner by sergebulaev · 4,230
- linkedin-content-planner by sergebulaev · 4,230
- content-aeo-optimizer by irinabuht12-oss · 3,698
Need help setting it up?
This page tells you what founder-content-engine does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.