agentleFS
Sign inStart free
FmarzochiFmarzochi/EGC/.agents/skills/content-engine/SKILL.md

content-engine

Skill61 starsChanged 46 days agoApache-2.0View on GitHub

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

We split this skill into the rules it gives an agent

25 rules. 3 are common, 19 are distinctive, and 3 are very specific to this project.

  • 3

    Common

    Most of the 48 edited versions we read keep these.

  • 19

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start from source material, not generic post formulas.

    line 20
  2. Distinctive:

    No engagement bait unless the user explicitly asks for it.

    line 24
  3. Distinctive:

    Before drafting, identify the source set:

    line 28
  4. Very specific:

    If the user wants a specific voice, build a voice profile from real examples before writing.

    line 37
  5. Very specific:

    Use brand-voice as the canonical workflow when voice consistency matters across more than one output.

    line 38
  6. Distinctive:

    Run it first when:

    line 44
  7. Very specific:

    If the user wants Felipe / EGC voice specifically, still treat brand-voice as the source of truth and feed it the best live or …

    line 51
  8. Distinctive:

    Delete and rewrite any of these:

    line 55
  9. Distinctive:

    keep the compression if the source voice is compressed

    line 68
  10. Distinctive:

    if writing a thread, each post must advance the argument

    line 69
  11. Distinctive:

    do not pad with context the audience does not need

    line 70
  12. Distinctive:

    do not turn it into a fake lesson post unless the source material actually is reflective

    line 75
  13. Distinctive:

    no corporate inspiration cadence

    line 76
  14. Distinctive:

    no praise-stacking, no "journey" filler

    line 77
  15. Distinctive:

    do not write narration that sounds better on paper than on screen

    line 83
  16. Distinctive:

    use chaptering only when it helps clarity

    line 89
  17. Distinctive:

    do not spend the first paragraph warming up

    line 94
  18. Distinctive:

    every section needs to add something new

    line 95
  19. Distinctive:

    Run the quality gate.

    line 105
  20. Common:

    When asked for a campaign, return:

    line 109
  21. Distinctive:

    every draft sounds like the intended author, not the platform stereotype

    line 119
  22. Distinctive:

    every draft contains a real claim, proof point, or concrete observation

    line 120
  23. Common:

    no generic hype language remains

    line 121
  24. Distinctive:

    no fake engagement bait remains

    line 122
  25. Common:

    no duplicated copy across platforms unless requested

    line 123

“Common” is measured: kept by at least 6 in 10 of the 48 edited versions of this file we could read. “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

Content Engine

Build platform-native content without flattening the author's real voice into platform slop.

When to Activate

  • writing X posts or threads
  • drafting LinkedIn posts or launch updates
  • scripting short-form video or YouTube explainers
  • repurposing articles, podcasts, demos, docs, or internal notes into public content
  • building a launch sequence or ongoing content system around a product, insight, or narrative

Non-Negotiables

  1. Start from source material, not generic post formulas.
  2. Adapt the format for the platform, not the persona.
  3. One post should carry one actual claim.
  4. Specificity beats adjectives.
  5. No engagement bait unless the user explicitly asks for it.

Source-First Workflow

Before drafting, identify the source set:

  • published articles
  • notes or internal memos
  • product demos
  • docs or changelogs
  • transcripts
  • screenshots
  • prior posts from the same author

If the user wants a specific voice, build a voice profile from real examples before writing. Use brand-voice as the canonical workflow when voice consistency matters across more than one output.

Voice Handling

brand-voice is the canonical voice layer.

Run it first when:

  • there are multiple downstream outputs
  • the user explicitly cares about writing style
  • the content is launch, outreach, or reputation-sensitive

Reuse the resulting VOICE PROFILE here instead of rebuilding a second voice model. If the user wants Felipe / EGC voice specifically, still treat brand-voice as the source of truth and feed it the best live or source-derived material available.

Hard Bans

Delete and rewrite any of these:

  • "In today's rapidly evolving landscape"
  • "game-changer", "revolutionary", "cutting-edge"
  • "here's why this matters" unless it is followed immediately by something concrete
  • ending with a LinkedIn-style question just to farm replies
  • forced casualness on LinkedIn
  • fake engagement padding that was not present in the source material

Platform Adaptation Rules

X

  • open with the strongest claim, artifact, or tension
  • keep the compression if the source voice is compressed
  • if writing a thread, each post must advance the argument
  • do not pad with context the audience does not need

LinkedIn

  • expand only enough for people outside the immediate niche to follow
  • do not turn it into a fake lesson post unless the source material actually is reflective
  • no corporate inspiration cadence
  • no praise-stacking, no "journey" filler

Short Video

  • script around the visual sequence and proof points
  • first seconds should show the result, problem, or punch
  • do not write narration that sounds better on paper than on screen

YouTube

  • show the result or tension early
  • organize by argument or progression, not filler sections
  • use chaptering only when it helps clarity

Newsletter

  • open with the point, conflict, or artifact
  • do not spend the first paragraph warming up
  • every section needs to add something new

Repurposing Flow

  1. Pick the anchor asset.
  2. Extract 3 to 7 atomic claims or scenes.
  3. Rank them by sharpness, novelty, and proof.
  4. Assign one strong idea per output.
  5. Adapt structure for each platform.
  6. Strip platform-shaped filler.
  7. Run the quality gate.

Deliverables

When asked for a campaign, return:

  • a short voice profile if voice matching matters
  • the core angle
  • platform-native drafts
  • posting order only if it helps execution
  • gaps that must be filled before publishing

Quality Gate

Before delivering:

  • every draft sounds like the intended author, not the platform stereotype
  • every draft contains a real claim, proof point, or concrete observation
  • no generic hype language remains
  • no fake engagement bait remains
  • no duplicated copy across platforms unless requested
  • any CTA is earned and user-approved

Related Skills

  • brand-voice for source-derived voice profiles
  • crosspost for platform-specific distribution
  • x-api for sourcing recent posts and publishing approved X output

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.

Reviews can't be read right now.

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.

Check your setup, free