agentleFS
Sign inStart free
qwwiwiqwwiwi/agentos-skills-public/skills/content-engine/SKILL.md

content-engine

Skill4 starsChanged 4 months agoMITView on GitHub

Content engine. Classify incoming content, write posts, market reports, YouTube scripts, X posts, market reviews, voice/audio routing, cross-post, screenshot handling. Triggers: "write a post", "make a post", "post about", "record idea", "save as reference", "save", "this is my stance", "my position", sending a link, repost, tweet, screenshot, audio or voice message.

59 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brand-discovery, agent-sort and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ysyecustSkill

    brand-discovery

    Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).

    Also in 6 projects that use this

  • niloykumarbarmanSkill

    agent-sort

    Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

    Also in 14 projects that use this

  • royaluniondesign-sysSkill

    configure-ecc

    Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.

    Also in 12 projects that use this

  • junimnjwSkill

    ralphinho-rfc-pipeline

    RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

    Also in 12 projects that use this

  • InfopibeSkill

    investor-materials

    Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

    Also in 37 projects that use this

  • TironFoxSkill

    agent-payment-x402

    Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Fact-check (BEFORE humanizer!): Verify: numbers not from API, historical dates, quotes, names.

    line 59
  2. Distinctive:

    Publish: ONLY on command. After → offer to save to library.

    line 62
  3. Very specific:

    Use skills/market-data/SKILL.md to collect data (BTC, RSI, F&G, OI, funding, liquidations, SPY, Fed).

    line 76

“Common” is measured: kept by at least 6 in 10 of the 51 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 v5

1. Routing matrix

IncomingSkill / action
YouTube linkskills/transcript/SKILL.md → transcript
X/Twitter linkskills/twitter/SKILL.md → tweet content
Voice/audio (.ogg)skills/groq-voice/SKILL.md → transcription
Web linkskills/markdown-new/SKILL.md (fallback: skills/chromium/SKILL.md)
Market requestskills/market-data/SKILL.md → data + indicators
Screenshot/imageVision models (describe content, extract text)

Extract content via routing matrix before command routing.

2. Command routing

Explicit command → execute:

CommandAction
"write a post" / "make a post"Post pipeline (§3)
"record idea"Save to ideas storage
"this is my stance" / "my position"Update stance/core
"save as reference"Save to library (is_reference: true)
"save"Save to sources

No explicit command → ASK:

"Got it, this is [brief summary]. What should I do with it? -- write a post / record as idea / save as material / update position / just for reference"

Never guess intent.

3. Post pipeline (10 steps)

  1. Channel. Crypto/macro → main channel. Ambiguous → ask.
  2. Idea. From user or from ideas storage -- suggest 2-3. After approval → mark status in_progress.
  3. Persona Lock. Load from channel profile. Override per-task only if explicitly requested.
  4. Context (required sources):
    • TOV (Tone of Voice): load from your TOV storage
    • Channel profile: load from channel profiles storage
    • Library (3-5 posts): load from library storage
    • Stance (crypto/macro): load from stance/core storage
    • Local mirrors as fallback if storage unavailable
  5. Pre-draft brief. 1 thesis, 2-4 supporting points, sources. Show to user or go straight to draft (simple tasks).
  6. Draft. Opus subagent. Pass: persona lock + TOV + library + task. Save to drafts storage.
  7. Fact-check (BEFORE humanizer!). Verify: numbers not from API, historical dates, quotes, names. Links only from sources, never invented.
  8. Humanizer. 3 passes per skills/content-engine/references/humanizer-patterns.md. DO NOT touch: facts, numbers, levels, position, categoricality.
  9. Show. Draft + fact-check to user. Silently, without listing steps. Apply edits verbatim, don't soften. Ask: "One-time edit or add to TOV?"
  10. Publish. ONLY on command. After → offer to save to library. Update idea → status: published.

4. Fallbacks

SituationAction
Library emptyWrite by TOV + stance, warn: "Library empty, style may be imprecise"
Storage unavailableLocal mirrors, mark [unverified]
Stance conflictAsk user: update stance or one-time exception?
Cross-postOne draft → adapt for each channel (TOV + profile for each)

5. Market report

On "what's the market doing" / "market overview":

  1. Use skills/market-data/SKILL.md to collect data (BTC, RSI, F&G, OI, funding, liquidations, SPY, Fed).
  2. Apply stance from stance/core storage.
  3. Format: price → indicators → macro → conclusion through user's position.

6. YouTube

Scripts, descriptions, timecodes -- details in skills/content-engine/references/youtube-guide.md. YouTube scripts go through steps 3-9 of the pipeline (persona lock, context, brief, draft, fact-check, humanizer, show). Clarify format with user: Shorts / 5-7 min / 15-20 / 30+. Outline → approval → full script.

7. Two idea banks

BankPurpose
Content ideasPosts, videos
Project ideas (status=pipeline)NOT for content

8. TOV update (every 5 posts)

  1. Get learnings from storage -- edits for the period.
  2. Get library -- recent originals.
  3. Patterns (minimum 2 repetitions) → suggest 2-5 rules → after "yes" → update TOV storage.

9. Rights and rules

  • ideas, sources, drafts -- without asking.
  • library -- only after "add to library".
  • TOV -- only on explicit request.
  • Draft ALWAYS show to user.
  • Publish -- ONLY on command.
  • Library = main style source.
  • Humanizer pass -- MANDATORY between fact-check and show.
  • Persona Lock -- MANDATORY before draft.
  • Storage commands: full reference in skills/content-engine/references/storage-commands.md.

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.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free