AI TOOLS RADAR
Soumettre
Tous les Skills / SOCIAL-MEDIA-SKILLS
social-media-skills/skills

capcut

- The CapCut craft skill — edit short-form social video (TikTok, Reels, Shorts) fast and safely: retention-paced cuts, auto-captions, beat-synced sound, exports.

Voir la source
Document Skill original

Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.

capcut

The short-form editing tool skill — edit to the script, drive the pace, ink the captions, tighten sound with the license check, and ship safe + to spec. The agent plans and flags the hazards; the human executes and approves; WoopSocial publishes the finished file. (Ships with tools/integrations/capcut.md.)

The POV: the edit serves the script — and "free" has fine print

CapCut earned its place as the default short-form editor: auto-captions in seconds, beat-sync, background removal, trend templates, phone-to-desktop sync — with a ~15-minute ceiling by design (it's a short-form tool; route long-form to Descript/Resolve). Two top-1% edges most creators learn the hard way. (1) The licensing fine print: the June 2025 ToS grants ByteDance a perpetual, transferable, sublicensable license to anything uploaded/synced (you keep copyright — it's a license, not ownership, stated precisely) — so client/NDA material edits locally, never synced; and the music trap: free-library assets are personal-use only, and even tracks labeled "Commercial use" are reported cleared for TikTok/CapCut platforms only — YouTube/IG claims still happen, verify per track. (2) Check the tier before you build: features migrate behind Pro over time, and the documented failure is hours of editing ending at a paywalled export. The craft line: the edit executes what `short-form-video-script` designed — pacing, captions, and sound serve the beats; and auto-captions always get an accuracy pass, because a wrong claim in a caption is a published error.

Read these first

  1. short-form-video-script — the beats this edit executes.
  2. brand-profile + design-and-templates (caption style/type/color) + voice-builder (any copy/TTS).

The framework: EDITS

(Depth: references/the-edits-framework.md.)

  • E — Edit to the script: load the beats; cut everything that isn't in them; the hook lands in the first

seconds; the last cut is the loop.

  • D — Drive the pace: visual change every ~2–4s (jump cuts, punch-ins/keyframes, B-roll, text pops);

beat-sync; scrub-test for dead stretches.

  • I — Ink the captions: auto-captions + the mandatory accuracy pass; style once, save the preset; sound-off

first; SRT/VTT export when copy travels.

  • T — Tighten sound + effects (the license gate): license-check music BEFORE export (the "Commercial

use"-is-TikTok-only trap); platform-native audio, licensed tracks, or ai-music-and-sound; effects sparingly.

  • S — Ship safe + to spec: right resolution/fps per destination; ToS hygiene (local-only for client work);

likeness/AI-disclosure handled; export → scheduling-and-queue → WoopSocial.

The reality (verify-quarterly)

2026 CapCut: auto-captions (free ~10-min/project cap; Pro unlimited; SRT/VTT/ASS export), real-time background removal, motion/camera tracking, vocal isolation + flicker removal (Pro), TTS/avatars, Long-Video-to-Shorts, keyframes/beat-sync, MP4/MOV to 4K (Pro). Plans restructured early 2026 — Standard ≈ $9.99 / Pro ≈ $19.99 (~$15 annual); sources conflict (regional/legacy $7.99–9.99 figures) — verify in-app, and features migrate behind Pro over time (check tiers before building). Documented billing/cancellation complaints (manage via app store). The ToS + music-license spines as above. India ban since 2020. Attribute all; verify-quarterly. Full detail: references/capcut-2026-reality.md. The daily loop, the pre-edit tier check, the client-work hygiene checklist, long-form routing, and two worked examples: references/workflows-and-templates.md.

Honest scope (never violate)

  • The agent plans the edit (cut plan, pacing, caption spec, sound plan + license gates, export spec) and

flags every ToS/licensing hazard; the human executes in CapCut, judges footage, approves the cut (no CapCut agent connector — never pretend to see or edit video; never fabricate "that cut works"). WoopSocial publishes the finished export (TikTok's required fields validate there) — it does not edit video; CapCut's direct-to-TikTok path exists and the split is a stated choice.

  • Licensing/ToS spine: personal-use free assets; "Commercial use" music verified per track; uploaded-content

license → client/NDA work local-only, never synced (counsel for high-stakes; not legal advice); users bear responsibility for uploads. Likeness + AI-disclosure: no non-consensual lip-sync/deepfakes; disclose TTS/AI voices where required (EU AI Act; C2PA). Never pirated packs, unlicensed music, uncorrected captions, or fabricated prices/gates/metrics. (Full scope: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

capcut (this) = the short-form timeline edit · short-form-video-script = designs the beats (read first) · captions-and-clipping / opus-clip = clip long video into shorts (feeds this) · descript = text-based talk/long-form editing (the >15-min route) · canva = graphics + simple motion · ai-video / veo-3 / kling / runway = generate footage (this edits it) · talking-head-and-piece-to-camera = the performance the footage comes from · tiktok-video-publishing / instagram-reels-publishing / youtube-shorts = platform publish specifics.

Where this connects

Reads first: short-form-video-script + brand-profile/design-and-templates + voice-builder. Pulls footage from: talking-head-and-piece-to-camera, ai-video/heygen (disclosed), captions-and-clipping. Feeds: tiktok-video-publishing, instagram-reels-publishing, youtube-shorts, before-after-and- transformation, content-recycling. Publishes via: export → scheduling-and-queue → WoopSocial. Tool file: `tools/integrations/capcut.md`. Measure with: native + analytics-and-reporting on watch-through / 3s hold — never fabricated.

Definition of done

A short-form edit that executes the script's beats (hook inside the first seconds, dead air gone, the loop cut last), paced with a visual change every ~2–4s and beat-synced sound, captioned via auto-captions plus the mandatory accuracy pass in a saved on-brand preset inside safe zones, with every asset license-checked before export (personal-use free assets avoided for commercial work; "Commercial use" music verified per destination platform; no pirated packs or unlicensed songs), the ToS hygiene held (client/NDA material local-only, never synced), likeness/AI-disclosure handled (no non-consensual lip-sync; TTS/avatars disclosed where required), and the export to spec per destination; tiers checked before the edit was built (no paywall surprise at export), the human executing and approving the cut, and the finished file published via WoopSocial; measured on watch-through/ 3s hold natively; no fabricated prices, feature gates, capabilities, or metrics; and correctly distinguished from short-form-video-script, captions-and-clipping/opus-clip, descript, canva, and the video generators.

du même dépôt

Autres Skills

Tous les Skills
social-media-skills
Communauté

short-form-video-script

- The master craft of scripting short-form vertical video (Reels, TikTok, Shorts) for watch-through. Use when someone wants a short-form video script, a Reel/TikTok/Short script, help with hooks, retention, pacing, the ending/loop, sound-off captions, or fixing early drop-off. Watch-through, not likes, rules short-form; the script's only job is to be un-skippable. Uses the WATCH framework. Reads brand-profile + voice-builder first; pulls the 'what' from the content-angle skills and the hook from hook-writer. The agent writes the script (spoken lines + on-screen text + beat/shot direction + hook variants + CTA); the human shoots/performs/edits; WoopSocial publishes the finished file. Routes platform specifics to reels-script / tiktok-script / youtube-shorts; pairs with talking-head-and-piece-to-camera. NEVER bait-and-switches the hook or fabricates a stat. Distinct from hook-writer, captions-and-clipping, and ai-video/veo-3/heygen (which generate the video this scripts).

installations
4
GitHub Stars
98
Mis à jour
17 sept.
MIT6 Fichiers
Voir les détails →
social-media-skills
Communauté

brand-profile

- Use FIRST, before any other social media skill, to load or create the brand profile — the durable record of who a business is, who it serves, how it sounds, and what it will and won't say. Run this when the user says "set up my brand," "brand profile," "brand guidelines," "define our brand voice," "onboard," "get started," when work begins for a new business or client, or any time another social skill needs brand context that isn't already loaded. Works for ANY business: B2B SaaS, ecommerce, local and small business, agencies and their clients, personal brands and creators, and nonprofits. For writing actual posts, see the content skills; to derive a voice from an existing body of writing, use voice-builder; this skill only builds the shared context they all read.

installations
3
GitHub Stars
98
Mis à jour
17 sept.
MIT7 Fichiers
Voir les détails →
social-media-skills
Communauté

captions-and-clipping

- The long-form-to-Shorts + sound-off captions mini-skill (Opus Clip / CapCut / Submagic). Use when someone wants to "clip my podcast/webinar/long video into Shorts," "make TikToks/Reels from a YouTube video," "add captions/subtitles to a video," "repurpose long-form into short-form," or "auto-generate clips." Tools clip and caption; a human reviews; WoopSocial schedules/publishes. Below the ai-video router; sibling to veo-3, heygen, ai-voiceover. This is the general craft: route OpusClip-specific pipelines (credits, Virality Score, tiers) to opus-clip, hands-on short-form editing to capcut, and the long-form talk edit itself to descript. Export clean (no watermark); disclose AI-edited video.

installations
3
GitHub Stars
98
Mis à jour
17 sept.
MIT6 Fichiers
Voir les détails →
social-media-skills
Communauté

talking-head-and-piece-to-camera

- The on-camera delivery craft — helping a real human film themselves talking to a lens and look like themselves doing it. Use when someone wants a "talking head video" or "piece to camera," says "film myself" or "I look stiff on camera," asks about a teleprompter, framing, lighting, audio, or retakes, or wants to batch-film videos. Uses the TAKES framework. Phone-first: gear is almost never the bottleneck. Reads brand-profile + voice-builder first; takes its script from short-form-video-script (that writes it, this delivers it). The agent coaches setup + delivery, formats prompter/beat-map scripts, and plans batch days; the HUMAN films and picks the take (the agent cannot see footage); WoopSocial publishes the finished file. Camera-shy? Route honestly to heygen/synthesia or faceless formats. Never fabricates "that take looks great." Distinct from scripting-and-storyboarding (the shoot plan), heygen/synthesia (avatars), and captions-and-clipping/capcut/descript (the edit).

installations
3
GitHub Stars
98
Mis à jour
17 sept.
MIT6 Fichiers
Voir les détails →