agentleFS
AZ-1224AZ-1224/riff/skill.md

riff

Skill0 starsChanged 5 months agoMITView on GitHub

One source → every channel. Turn a YouTube video, X article, or blog post into a trend-pegged X article, a week of platform posts, an SEO blog post, and a split-screen avatar video script — then publish them. Use when the user wants to repurpose content, write an X article from a video, generate social posts, draft an SEO article from a source, or fan one piece of content out across channels.

  • Reads credentials
  • Installs packages

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. hraness/personal-monorepo-template★ 4same name
    2. NasonZ/riff★ 2same name
    3. develop212/riff★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    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:

    Read the printed SYSTEM and USER blocks.

    line 35
  2. Distinctive:

    Write it to a file and store it:

    line 41
  3. Distinctive:

    Write like a sharp human operator.

    line 53
  4. Distinctive:

    Every claim traces to the source: Never invent stats, quotes, or outcomes.

    line 54
  5. Very specific:

    Run riff channels to see what's configured.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 3 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

Riff — agent-native content repurposing

You are driving Riff, a CLI that turns one source into a full multi-channel content bundle. You (the agent) are the brain: Riff handles ingest and publishing deterministically; you do the writing.

Install (once)

npx skills add https://github.com/AZ-1224/riff
# Riff CLI auto-installs from npm if missing:
npm i -g riffkit   # provides the `riff` command

The flow

  1. Set the product (once per workspace) — what gets softly woven into every output:
    riff init --name "Postiz" --url "https://postiz.com" --one-liner "Run your social on autopilot with AI agents" --cta-link "https://postiz.pro/you"
  2. Ingest the source — a YouTube URL, an article/X URL, or pasted text:
    riff ingest "https://www.youtube.com/watch?v=XXXX"
    # → prints a <slug>. Source saved to .riff/<slug>/source.json
  3. Generate the bundle — THIS IS YOUR JOB. Get the prompt + source, then write the JSON yourself (no API key needed — you are the model):

    riff brief <slug> --trend "Claude Opus 4.8 launch"

    Read the printed SYSTEM and USER blocks. Produce one JSON object with exactly these keys:

    • xArticle: { hook, body, productMention, cta, trendPeg } — the trend-pegged long X post (the headline asset)
    • posts: array of { platform, text, threadOrder?, mediaHint? } — 6–9 posts across x/linkedin/instagram/threads
    • blog: { title, slug, metaDescription, keywords[], bodyMarkdown } — a real-value third-person SEO article
    • videoScript: { title, estDurationSec, hook, segments[ { say, screen } ] } — split-screen avatar short

    Write it to a file and store it:

    riff save <slug> bundle.json
  4. Publish — render markdown + ship to every configured channel:
    riff publish <slug>

Generation rules (follow the brief's SYSTEM block exactly)

  • Write like a sharp human operator. No AI-slop tells: no em-dash spray, no "unlock/leverage/delve", no hashtag spam, no emoji confetti.
  • Every claim traces to the source. Never invent stats, quotes, or outcomes.
  • The X article rides a trend (trendPeg). Hook honestly, deliver the value in tight lines, one credible product line, CTA with {{LINK}}. Keep a stockpile: pre-write articles, swap trendPeg for the next big release, fire when it lands.
  • The product mention is ONE line, earned by the surrounding value. Never a hard sell.
  • The blog post is real value in third person, product woven into the narrative — not something a ChatGPT search would surface.

Channels

Run riff channels to see what's configured.

  • export — always on, writes markdown to .riff/<slug>/outputs/ (x-article.md, posts.md, blog.md, video-script.md).
  • social — schedules posts as Postiz drafts (POSTIZ_API_KEY).
  • blog — posts the SEO article to WordPress as a draft (WORDPRESS_URL + WORDPRESS_USER + WORDPRESS_APP_PASSWORD).
  • video — renders a HeyGen avatar short (HEYGEN_API_KEY + HEYGEN_AVATAR_ID + HEYGEN_VOICE_ID; dry-run unless RIFF_HEYGEN_LIVE=1).

Publish a subset: riff publish <slug> --channel export,social.

Unattended mode (no agent in the loop)

For cron / autonomous pipelines, skip steps 3 and let Riff call the model itself:

ANTHROPIC_API_KEY=sk-... riff repurpose <slug> --trend "..." --llm --publish

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.