format-reels
Skill0 starsChanged 2 months agoMITView on GitHub
15-60s short-form video script structure (hook/context/value/CTA), shot list format, b-roll cues, text overlays, and caption brief. Use when mkt-content builds a Reels/Shorts-style script from an approved hook.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- global/CLAUDE.mdCLAUDE.md
- copywriting-frameworksSkill
- design-mdSkill
- format-carouselSkill
- format-hooksSkill
- format-linkedinSkill
- funnel-designSkill
- humanizationSkill
- launch-playbooksSkill
- offer-designSkill
- pipeline-brandSkill
- pipeline-campaignSkill
- pipeline-contentSkill
- pipeline-copySkill
- pipeline-landing-pageSkill
- pipeline-luxoSkill
- pipeline-refino-uiSkill
- pipeline-sistemaSkill
- scroll-worldSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
If no b-roll is needed for a block, say so explicitly rather than leaving it blank.
- Distinctive: line 52
No emoji spam; cap strategic tags at 3-5 when the platform uses them.
≈ “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.
Files
Format: Reels
Recording-ready short-form video scripts (15-60s) for Reels/Shorts-style vertical formats. Produced by mkt-content after a hook is selected via format-hooks. Output must be usable on camera without further interpretation by the person recording or the editor.
Script Structure
HOOK (0-3s) → CONTEXT (3-8s) → VALUE (content blocks, one idea each, a pattern interrupt every 3-5s) → CTA (final 3-5s).
- The hook is adopted from
format-hooks, not written from scratch here. - Context sets up why the value matters in one beat — do not re-hook, move forward.
- Value blocks carry one idea each; each block should be short enough that a pattern interrupt (a cut, an overlay, a tonal shift) lands before attention drifts.
- The CTA names a specific next action — never "link in bio" as the entire instruction; state what happens and why to act now.
Word Budget by Duration
| Duration | Spoken word ceiling |
| 30s | ~75 words |
| 45s | ~110 words |
| 60s | ~150 words |
Going over budget means cutting a content block, not talking faster — pace is part of what holds retention.
Shot List Format
For every beat, specify:
- Framing — wide / medium / close-up / extreme close-up
- Talent direction — energy level, eye contact, gesture, pace
- Cut point — where the editor slices
- Pause markers — where a beat of silence lands for emphasis
B-Roll Cues
- Tag every content block with what overlay or cutaway supports the line — b-roll should illustrate the claim, not just fill time.
- If no b-roll is needed for a block, say so explicitly rather than leaving it blank; an unmarked gap forces the editor to guess.
Text Overlays
- Exact on-screen text and timing for every overlay — subtitles are mandatory for vertical formats given sound-off viewing.
- Overlay text should reinforce the spoken line, not duplicate it word-for-word or contradict it.
Caption Brief
- The caption complements the hook, it doesn't repeat it — it can carry a secondary angle.
- Include a soft CTA in the caption even when the video's spoken CTA is the primary one.
- No emoji spam; cap strategic tags at 3-5 when the platform uses them.
- First-comment strategy: if a link is needed and the platform penalizes outbound links in the main post, place the link in the first comment instead.
Output Format
# Reels Script — <Topic>
Format: <duration>s, vertical | Hook source: <from format-hooks> | Word budget: <X words>
## HOOK (0-3s)
Spoken: <> | Framing: <> | Talent: <> | Text overlay: <> | Cut point: <>
## CONTEXT (3-8s)
[same structure]
## VALUE BLOCK 1 (Xs-Ys)
[same structure] | B-roll: <> | Pattern interrupt: <>
## VALUE BLOCK 2+
[repeat as needed]
## CTA (final 3-5s)
Spoken: <exact text, specific action> | Text overlay: <>
---
Shot list (flat): [...]
B-roll list: [...]
Text overlays (timed table): [...]
Caption brief: <caption, hashtags, first comment if applicable>Handoff
Mark the output READY FOR MKT-EDITOR and hand it to mkt-editor for the humanization and quality-gate pass before it is approved for recording or publishing.
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
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.

