agentleFS
LordVayronLordVayron/video-factory/.claude/skills/format-longform/SKILL.md

format-longform

Skill67 starsChanged 17 days agoMITView on GitHub

Produces long-form ambient videos (10 minutes to 3 hours) — guided meditation, sleep stories, breathwork, affirmations, yoga nidra, focus/study music, ambient loops — with seamless looping AI scenes, a Suno music bed and an optional ElevenLabs voice-over with long pauses, delivered as 1080p YouTube video plus MP3. Use for "meditación", "meditation video", "sleep story", "música para dormir", "ambient loop", "focus music", "video largo de relajación", "yoga nidra", "affirmations".

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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. Very specific:

    Read first: .claude/skills/studio/references/verticals/meditation-longform.md (the DNA: voice pace, pause lengths, arcs, music rules, QC).

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Long-form ambient video

Read first: .claude/skills/studio/references/verticals/meditation-longform.md (the DNA: voice pace, pause lengths, arcs, music rules, QC). The studio skill's money rules apply: estimate first, gate before spending, never spend past the locked budget.

Steps

  1. Brief: the format (from the DNA table), length, language, intention ("fall asleep", "calm before an exam"), voice gender and character, music mood, visual world (forest, ocean, cosmos, candle-lit room...). For voice-free ambient, skip everything about the script.
  2. Plan (gate 1): the intake creates the project: node engine/studio.mjs new <slug> --format meditation --seconds <length in seconds> ... (studio skill). Then fill the longform block, and follow studio.mjs status <slug>:
    • script[] with pauseAfter per segment, written to the DNA's density for the length.
    • 3–6 scenes with matching look; use "kenburns" for scenes where motion would distract (paintings, interiors) or to save cost.
    • music.prompt and voice.eleven (pick a calm voice; list voices with the ElevenLabs API or ask the creator). Present the script, the scene list, the music prompt and the estimated runtime. Iterate until approved.
  3. Production Book (gate 2): node engine/longform.mjs estimate <slug> → node engine/book.mjs <slug> → show it → after the creator's yes node engine/studio.mjs approve <slug> book --said "..." (locks the budget).
  4. Voice first: node engine/gen.mjs narration <slug>. Listen to the first two segments (pace, warmth). If the voice is wrong, change it now.
  5. Music and picture: node engine/gen.mjs bed <slug> and node engine/gen.mjs loops <slug>.
  6. Preview: node engine/longform.mjs build <slug> --sample 90 and check the balance of voice and music and the first cross-fade.
  7. Final: node engine/longform.mjs build <slug> → mp4 + mp3 + contact sheet + QC → node engine/studio.mjs qc <slug>. Look at the sheet; spot-check the voice at 3 points.
  8. Deliver: node engine/studio.mjs deliver <slug> (receipt + final book), then the files, a title, a description with chapters from longform.cues, and a thumbnail (the best still, 1280×720).

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.