agentleFS
ekusiadadusekusiadadus/video-edit-harness/.agents/skills/tiktok/SKILL.md

tiktok

Skill0 starsChanged 41 days agoMITView on GitHub

Edit a local video for TikTok, Reels or YouTube Shorts with a clear short-form story, appropriate grade, audio, captions and a reviewed 9:16 MP4. Use when the user invokes /tiktok or asks for a vertical short; do not upload or post by default.

10 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use linkedin, gmail and 1 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.
  • kkoppenhaverSkill

    linkedin

    Write LinkedIn posts in Keanan's voice. Use when drafting LinkedIn content, creating professional posts, or sharing builder-focused insights. Triggers include requests to "write a LinkedIn post", "draft something for LinkedIn", "help me post on LinkedIn", or any LinkedIn content creation. Generates upbeat, builder-centric content mixing practical how-tos with candid humor.

    Also in 3 projects that use this

  • refly-aiSkill

    gmail

    Integrate with Gmail for email management and automation. Use when you need to: (1) send and compose emails with attachments, (2) read and search emails by criteria, (3) manage drafts and email labels, or (4) reply to email threads and conversations.

    Also in 3 projects that use this

  • AnthropicSkill

    slack

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    After the graded preview/full edit exists, run:

    line 32
  2. Distinctive:

    Do not post, schedule, upload, add platform music or claim TikTok playback without a further explicit instruction.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 7 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

TikTok editing

In Claude Code, /tiktok /path/to/video.mov [brief] supplies the video path and optional brief in $ARGUMENTS. In Codex, use $tiktok with the same path and brief. A marketplace plugin exposes the namespaced /video-editing:tiktok; install this standalone skill under .claude/skills/tiktok for the exact /tiktok spelling.

Use the Video Edit Harness checkout (v0.1.0-alpha.7). Locate it through VIDEO_EDIT_HARNESS_ROOT or the project checkout. If absent, follow the installation guide. Read README.md and AGENTS.md; run uv run video-harness --help from the harness root. This skill is editing guidance, not authorization to install dependencies, send footage, post to TikTok, or publish a screen recording.

Run uv run video-harness doctor before editing. Check root, versions, skills, commands and required tools; resolve relevant findings. Persist source upload allow/deny through session cloud-policy, using the actual current authorization and provider scope. Unknown blocks cloud calls; existing deny survives resume. Reuse an unchanged allowed source without repeated permission questions.

Understand the request and preserve the source

Resolve the actual local input path; never interpret an arbitrary URL as permission to download or upload. Inspect duration, dimensions, rotation, frame rate, color space and audio. Preserve the input. Determine the audience, message, target length and style from the request and footage. Ask only for a critical unresolved choice; continue local inspection while waiting. When unspecified, make a short preview with fit framing, natural color and clear speech; keep the original duration until a transcript-backed story is selected. A 15–60-second target can be an editorial starting point, not a TikTok upload limit or a reason to cut a sentence.

Honor no-upload/no-publication restrictions, including private footage of children. No cloud transcription, screenshots, previews, clips or stills of protected media may be uploaded. Public demonstrations use permitted synthetic media. OpenAI then Azure are the only transcription providers, and require explicit source upload authorization. Do not start local Whisper. When upload is forbidden and no sealed transcript exists, prepare local grading/framing/audio only; explain that word-anchored story edits need a permitted transcript. Never make up alignment.

Make the short understandable

Use the video-editing skill in this checkout for source-bound transcription, word IDs, ordered chapter spans, omissions, revisions and render review. Give the viewer useful context early, focus on one coherent point, and retain the payoff. Remove redundant setup only when evidence supports it. Preserve negation, qualifications, names, sentence endings, breaths and emphasis. Do not add invented claims, clickbait, music rights, engagement promises, or a forced call to action. Check both audio-only clarity and the silent/caption viewing experience.

For a more lively short, begin with the actual action or question, let one or two meaningful visual changes build toward the answer, and give the payoff room to land. Alternate wide context, close detail and reaction only when those shots exist; use B-roll to explain the spoken point, not to conceal a missing claim. Put a selective punch-in, split-screen comparison, brief monochrome turn or color frame on a real emphasis or observed cut. A sound hit must follow the audio rights and cue plan; a mapped beat may guide placement, but never move spoken words to meet it. Preserve at least one calm interval so the emphasis is legible. Review every effect in 9:16 with captions and interface clearance. Follow the exact video_effects schema, render evidence and quiet-version comparison in the shared skill and docs/VIDEO_EFFECTS.ja.md; do not infer effect timing from a platform trend or an unmeasured beat phase.

For local-only grading, copy a project template, set its actual source and color space, and choose the use case from the scene (indoor talk, outdoor daylight/night, backlight, etc.), not from the platform name. Start with natural or clean_editorial; compare another style on the same interval where useful. Run preview PROJECT --styles ... without a transcript. After an actual selection, use the chosen profile to render; do not assert human approval yourself. Avoid double-transforming Apple Log. Normalize measured speech as a project choice; do not amplify clipping or invent a platform LUFS rule.

Produce 9:16 delivery

Use the common optional-pattern contract in .agents/skills/video-editing/SKILL.md for requested BGM, effects, beat edits and supporting visuals. A vertical format alone does not choose playful_short or beat_montage. Check subject, captions and platform UI clearance for every added visual; keep voice and meaningful environment sound. Platform-library music added later remains a separate unperformed task until actually applied under the outlet's conditions.

After the graded preview/full edit exists, run:

uv run video-harness tiktok-export /absolute/path/to/graded-video.mp4 \
  --output output/my-tiktok --framing fit

Default fit/padding preserves the whole picture. Choose --framing center_crop only when the user wants it and the subject/text survive inspection across the clip. There is no automatic face tracking. Do not crop hands, demonstrations or multi-person conversations blindly. This export consumes graded SDR/Rec.709 media; it does not transform raw Apple Log or HDR by itself.

When an actual reviewed SRT matches this exact input edit, add --subtitles /absolute/path/to/subtitles.srt to burn captions. Inspect Japanese wording, line breaks, timing, readability and overlays at the top, bottom and right. The exporter uses conservative working margins; TikTok's actual UI safe area varies with device, caption and interactive elements. These margins are not an official guarantee. Do not attach a stale SRT from another edit, invent subtitles without listening, or imply automatic captions are reviewed.

For transcript-backed sessions, register the export with session register-vertical SESSION RENDER_ID /path/to/export/result.json. Record a separate exact-video-SHA review with session review-vertical SESSION DERIVATIVE_ID --data-file REPORT_JSON: framing, captions, audio and playback each need the actual status, basis and note. Package the selected portrait through session package SESSION RENDER_ID --target mp4 --derivative-id ID, then finish only after its gates pass. Changed source/render, subtitle, font, framing or video invalidates the old review. Standalone local-only previews remain previews and carry their unresolved scope.

The deliverable is a local 1080×1920 H.264/AAC MP4, technical checks and source/output fingerprints. Review framing, every edit boundary, captions and audio; offer the path to the result and list any unresolved checks. Verify full decode, dimensions, aspect, duration and audio coverage. Separate agent selection, human perceptual review and platform playback. The vertical export does not modify the original-source FCPXML framing: apply and verify portrait framing separately in FCP if needed.

Do not post, schedule, upload, add platform music or claim TikTok playback without a further explicit instruction. Use TikTok workflow notes for examples and evidence limits.

For structure alternatives, use session compare-candidates SESSION FIRST_RENDER SECOND_RENDER --mode structure with different sealed plans under the same brief/source pool/color/base audio/FPS/preview conditions. Include a natural version without retiming. Inspect ordered original source ranges and reasons, added/removed ranges including repeated uses, duration and retime operations. Play each full video independently; equal output times do not mean equal source moments. Selection exports are exact-video-SHA proposals, not adoption or human review. The default effects mode and same-plan timing mode retain their stricter boundaries. See docs/RETIME.ja.md; this capability is included in alpha.7.

Import a downloaded comparison proposal with session select-comparison SESSION --data-file comparison-selection.json --actor ACTOR --note REASON. The unadopted candidate restores the selected render's exact plan/project and retained transcript/context inputs, not the current plan with old effects. It validates video SHA, current brief, source and output time. Render the candidate before explicit adoption, then review the exact full output. Restoring older inputs does not restore human approval or publish a video. Legacy speech renders without input references require their actual embedded transcript; context is regenerated from that transcript and the same brief rather than inventing alignment. Included in alpha.7.

For motion_trail, read docs/VIDEO_EFFECTS.ja.md and propose an explicit session effects add operation on the actual mapping. Limit it to an observed movement within one shot; do not add it to natural edits. Render the unadopted candidate and compare against natural picture with the same audio. Inspect duplicated faces/hands, baked text, low-FPS stepping and phone readability; temporal_inputs proves frame/weight provenance, not aesthetic acceptance. It is full-frame temporal mixing, not a subject mask. This feature is included in alpha.7.

For experimental tracked_background, read docs/TRACKING.ja.md. Use a full-subject observed box on the retained pre-effects stage, not a torso-only pose box; pose requires manual masks for every selected frame. session track-effect --effect tracked_background prepares local GrabCut masks as an unadopted candidate. Keep the manifest/PNG/correction hashes and inspect every contour, hair, hands, clothing and occlusion on the exact rendered comparison. Manual full-size binary PNGs replace individual masks; never hide loss or fall back to a rectangle. Require the SHA-bound subject_masks visual check. Baked mix/video_only only; no depth or semantic matting claim. This alpha.7 feature is experimental: an eight-frame real-footage trial kept wall/ceiling in the foreground and the agent rejected the visual result. No human review is recorded. Require full contour review and manual masks before use; do not claim universal person matting.

For development compound effects, read docs/MOTION_TEMPLATES.ja.md and inspect motion-templates. Use session motion-template on an actual render with explicit frame-aligned interval, observed purpose, parameters and reduced_motion choice. The beat_focus recipe combines zoom/saturation; reveal_callout sequences zoom and a supplied keyword. Reduced variants limit animation, not all visual change. No beat, depth or native Motion/TikTok analysis is implied. Recipes remain unadopted and retain source-render/mapping SHA provenance; compare a natural baseline and review the exact final video. Do not bypass natural/off, composition or text collision checks. This development feature is not in alpha.7.

For development relative-depth image layers, read docs/DEPTH_LAYERS.ja.md. Prepare or infer fields on the full render’s retained visual-graded.mp4, preserving raw fields and interval-shared normalization; use depth correct for observed frame corrections. If flicker warrants it, propose opt-in depth stabilize with declared source-frame cuts; preserve the original, inspect recorded coverage/resets and compare actual moving contours. Low confidence resets history. Propose session depth-layer with a registered same-canvas RGBA asset and permitted visual-asset policy, compare a natural baseline, and retain the candidate through selection/adoption. Require exact-final-SHA depth_contours visual review of hair, hands, all performers, occlusions and flicker. Unrelated audio/effect revisions retain depth; changed grading must regenerate fields. Natural reset removes depth. Baked mix/video_only handoff preserves redacted field provenance; models and original images remain external. Relative depth is not a person mask, metric distance or guaranteed temporal consistency. A technical pass is not human acceptance or a finished video. This development feature is not in alpha.7.

For development portrait caption wrapping, read docs/CAPTION_LAYOUT.ja.md. Use an explicit ja/en layout and observed protected terms with tiktok-export --caption-layout; preserve reviewed SRT timing and manual breaks. The actual font/stroke ink must fit three measured lines; revise oversized cues rather than inventing timing or splitting terms. Inspect missing glyphs, reading time, subjects and platform UI on the exact portrait render. Portable delivery retains visible-line/runtime proof without input paths or unused protected terms. This is not semantic transcript regrouping, complete JLREQ compliance or an official platform safe zone; it is not in alpha.7.

For development editable FCP visual cues, read docs/FCP_OVERLAY_PLACEMENT.ja.md. Image/video/title exports retain static placement and actual source dimensions through a shared preview pixel model; preserve its pending FCP GUI calibration status. Inspect geometry against the exact preview, and do not claim playback parity from DTD or XML comparison alone. Return import accepts unchanged placement and rejects unknown spatial edits/locations/automation. Audio ducking/normalization parity remains a separate unfinished stage. This is not in alpha.7.

For development audio-cue renders, read docs/AUDIO_GAIN_EVIDENCE.ja.md. Retain measured sample gain arrays and the actual speech/environment and mixed WAV inputs; cache restoration must validate their fingerprints. For an explicitly requested experimental editable handoff, set fcp_handoff: editable and fcp_audio_automation: measured; bounded dB keyframes and separate dialogue PCM retain pre-normalization gains. Apply a final common normalization scalar only after all-sample proof against retained pre-AAC WAVs. Return import allows supported visual cue revisions while preserving all generated audio; reject changed audio automation/ranges/dialogue. Preserve pending FCP GUI calibration; inspect original-audio muting, loop source clocks and interpolation in FCP. Final normalization/playback parity remains pending. Local evidence references can contain private paths. Review the exact MP4 by listening; never infer human approval from gain data. This is not in alpha.7.

For development visual retime, read docs/RETIME.ja.md: default --timeline-settings migrate maps compatible explicit cues, pulse effects and fixed guides through exact frame membership into an unadopted candidate. Preserve the sealed migration evidence and inspect the actual rendered mapping. Phase maps retain old-frame zoom/saturation values and keyword-title fade/rise during holds and omissions. A title beginning at a surviving visible old frame must still pass collision checks. BGM plays normally on the new clock; its declared beat offset follows the music. Video overlays use version-2 phase maps selecting actual-output RGBA samples sealed by the original render, rather than reconstructing input clocks. Preserve the layer fingerprint and source/trim/placement digest. Changed opacity/placement/trim, layer tamper or preview canvas mismatch requires a fresh full original render; do not upscale the layer. Old timestamp-only maps need a fresh original render. Private layer references stay in the local session; baked MP4 retains the picture. Sealed version-2 video layers preserve loop position and baked fade. SFX content, including loops, follows the continuous picture map with pitch-preserving audio retime; use baked mix/video_only handoff. Wipe/trail content uses sealed original-stage samples through content_map when the original render retained them. Keep original event/plan/asset/order and picture-setting bindings, original and remapped layer hashes, and exact frame selections. Changed grade, overlays or effect parameters requires a fresh original candidate. Old renders without samples allow only complete one-to-one translation; speed changes need a fresh full render. All temporal stages keep their captured order when omissions collapse start times. Stale/omitted/unaligned intervals, ambiguous beat anchors, insufficient media/fades, tracked artifacts and previously retimed mapping must reject without silently dropping settings. Depth requires regeneration. Explicit --timeline-settings clear removes old settings with a report; speech-setting migration remains unsupported. Compare and review the exact full MP4; migration is not perceptual approval. This development feature is not in alpha.7.

For development semantic caption grouping, read docs/CAPTION_GROUPS.ja.md. Use session caption-source on a sealed speech render, then session caption-groups --spec-file to propose exact source word-ID/occurrence groups. Interpret requests such as keeping negation, names and units together using actual words; preserve complete ordered coverage and record reasons. Set ja/en, exact protected phrases and editor-selected reading thresholds; never use example IDs or invent timing/spelling. Unknown/missing/reordered refs, stale spelling and groups crossing edit junctions reject. Caption times follow actual cut-word times, retimed word frames or J/L audio samples. Review reading/overlap/punctuation diagnostics, the retained SRT and exact resulting MP4; diagnostics and agent grouping are not human approval. Regular YouTube uses separate SRT; burn captions into vertical MP4 through the existing export and review route when requested. Preserve caption-evidence.json, its SRT SHA and sealed delivery copy. Old renders without word evidence require a fresh render. This feature does not provide full semantic understanding, JLREQ or platform-UI compliance and is not in alpha.7.

In a post-alpha.7 checkout exposing SFX audio_retime, visual session migration preserves effect audio, including loops, through the continuous picture ramp. Original cue fades are applied before pitch-preserving stretch; freezes insert silence and resume source PCM. BGM remains normal speed and ducking is calculated against the new speech clock. Keep source/trim/fade/mapping SHA bindings and content-retime evidence. Changing the original fade or trim requires a fresh original candidate; do not remove these bindings to force reuse. Looped SFX binds its original decoded period and seam taper in version-2 metadata, repeating on the original clock before stretch; do not restart loops on the new clock. Version-1 nonloop metadata remains readable. Composed SFX retime is not supported. Use baked mix/video_only handoff; editable FCP must reject normal-rate substitution. Synthetic sample/pitch tests do not replace full human listening or device playback review.

In a post-alpha.7 checkout with video_loop_periods, video loop cues repeat only the selected source trim after one output-CFR conform. Keep the actual period-frame count, source/period SHA and sealed RGBA layer. Sealed version-2 phase replay preserves loop position and baked video fade/alpha; never replace old loop content with a newly started loop. Visual cue fades apply alpha. In development first-retime migration, image/static title fades select sealed version-2 RGBA samples from the original output clock, preserving alpha during holds and omissions. Keep source/image or generated title raster SHA, text, placement, opacity and fade bindings. Old static renders without samples allow only complete one-to-one translation; otherwise render a fresh original. Changing loop, trim, placement, opacity or a nonzero video fade requires a fresh original layer. Inspect entry, seam, exit and any repeated gesture. Editable FCP must reject unrepresented loops/visual fades; use baked mix/video_only. Technical synthetic checks do not approve aesthetic repetition or real-device playback.

For development comparison-page strength/off adjustments, follow the shared video-editing skill and docs/COMPARISON_ADJUSTMENTS.ja.md; review the newly rendered vertical result with caption and platform-UI clearance. Page undo resets staged proposals, not adopted edits. This is not in alpha.7.

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.