Claude Code skills · scrollmark/social-skills

Teach agents how social media works.

Sixteen installable skills for Claude Code and other skill-aware agents: social-media judgement, short-form video planning, production handoffs, and toolchain checks. Eight need no dependencies. The video engine lives in the same repo and installs separately when you want execution, not just guidance — what each layer gives you.

terminal · via skills.sh
npx skills add scrollmark/social-skills                  # all 16
npx skills add scrollmark/social-skills -s hook-anatomy  # just one

# Needs Node 22.20+. No Node? Same result without it:
#   mkdir -p ~/social-skills
#   curl -Ls https://github.com/scrollmark/social-skills/archive/refs/heads/master.tar.gz \
#     | tar xz --strip-components=1 -C ~/social-skills
#   ~/social-skills/install.sh
#
# Keep that directory: install.sh symlinks into it, so extracting to /tmp
# loses all 16 skills at the next purge — at once, and with no error.

The npx route uses the skills.sh CLI — the open agent-skills ecosystem — and works with Claude Code and other supported agents. Want just one skill? Every card below has its own one-liner. Some video skills add an optional second step: pip install from the repo. The next section explains what that unlocks.

Install options

What each skill needs.

Eight skills need only the skill files. The rest can use the video engine, and four also carry small scripts that run as soon as the skill is installed.

SkillNeedsBundledReach for it…
read-the-room nothing interpreting comments, captions, replies, or DMs
hook-anatomy nothing analysing, scoring, or generating hooks
trend-radar nothing deciding if (and when) a trend is worth riding
platform-fluency nothing platform conventions, algorithms, audience behaviour
content-autopsy nothing figuring out why a post took off — or didn't
voice-matching nothing writing as a creator, or auditing consistency
repurpose-engine nothing taking one piece of content everywhere it can go
video-formats engine planning, structuring, or critiquing a short-form video
brand-kit engine keeping a run of videos visually consistent
media-acquisition engine · ffmpeg 1 deciding where a shot's pictures come from
audio-acquisition engine · [audio] · [captions] · ffmpeg 2 a video needs a voice, a bed, or a fix for bad levels
subject-compositing engine planning a shot that composites a person into a scene
edit-handoff engine an editor is picking the cut up from here
video-production engine · [qc] · ffmpeg · node 4 producing a video end to end, or a run has stalled
agent-interview nothing an agent has to interview someone before it can act
studio-setup engine · [qc] · ffmpeg · node 1 checking or repairing a video toolchain

“Engine” is video-studio-engine, installed from this repo rather than PyPI — the exact command is under One repo. Four layers. Bracketed names are its optional extras. Generated from the skills themselves, and checked on every push.

Dependency guide

One repo, four layers.

The skill pack is useful even before you install a video toolchain. Some skills are pure guidance, some ship small scripts, and some use the Python and Remotion engine in the same public repo. The layers below show what works immediately, what needs one pip install, and what reaches for an external API key or a licence you may not need to buy.

8 skills

Layer one · prose

Nothing to install.

The seven social-media skills are pure judgement — tone, hooks, trend timing, platform dialect, post-mortems, voice. No external tools, no accounts, no keys. So is agent-interview, which has nothing video-specific in it. These are the same whichever way you install them.

read-the-room hook-anatomy trend-radar platform-fluency content-autopsy voice-matching repurpose-engine agent-interview
4 skills

Layer two · prose + a bundled script

Runs as soon as the skill is installed.

Six programs use the Python standard library and take their input on the command line, so they ship inside the skill folder and travel with npx skills add: doctor.py (what is reachable right now), measure.py (durations and a track's energy structure), normalize_audio.py (loudness after a render), poster.py (thumbnail shortlist and contact sheet), qc_render.py (the render checked against the plan it was built from) and prekey.py (key a generated clip to alpha). Two of them are carried by two skills each, so the skill stays self-contained.

They want ffmpeg and ffprobe on your PATH. That is the one thing the repo cannot ship for you.

studio-setup audio-acquisition media-acquisition video-production
36 programs

Layer three · one pip install

The engine, from the repo.

The other thirty-six programs use third-party dependencies or read project state: a props document, a composer directory, a styles tree. They live in src/video_studio/ and run as video-studio <command>. The base install is small; heavier dependencies are opt-in extras, so you install only the parts you use.

terminal · optional, video skills only
uv tool install --python 3.12 --refresh 'video-studio-engine[standard] @ https://github.com/scrollmark/social-skills/archive/refs/heads/master.tar.gz'

# Needs no git, no Xcode tools and no system Python — uv brings its own.
# Get uv first:  curl -LsSf https://astral.sh/uv/install.sh | sh
#                source "$HOME/.local/bin/env"    # or open a new terminal
#
# --python 3.12 is pinned: on 3.13 the [audio] extra installs cleanly and
# silently has no voice. --refresh because GitHub's tarball is cached forever.

# Or one extra at a time — same URL, different bracket:
#   [sourcing]  + source_clips (yt-dlp)
#   [audio]     + tts_kokoro, gen_music, duck_music
#   [captions]  + gen_captions (local whisper word timings)
#   [generate]  + gen_veo, gen_boil
#   [vision]    + composite_subject, track_pointing  (needs mediapipe)
#   [export]    + export_edit (OpenTimelineIO)
#   [qc]        + qc_analyze — the render checked against its plan, decoded
#
# The four model-backed QC checks stay opt-in, one extra each:
#   [qc-ocr]  captions and text layout    [qc-yolo]  planned subjects on screen
#   [qc-face] lip sync                    [qc-clip]  scene footage vs its prompt

It installs from the repo, not from PyPI — the name video-studio-engine is not published there, so a bare pip install video-studio-engine does not get you this. The URL is the install.

The engine is independent of the skills and installed separately: npx skills add never touches it. The cards below spell out which skills still work without it and which become planning guidance only.

licences, not code

Layer four · yours to licence

A Remotion licence, or not.

The Remotion composer ships in this repo nowcomposer/, React driven entirely by the props document the engine writes. What is still not ours to ship is Remotion itself: the project declares it as a dependency and vendors none of it, because Remotion requires a paid Company Licence above three people and for hosted or automated rendering. The code is here; that license stays between you and them. It is Node, not Python, so npm install in composer/ once, and then npx remotion render turns a storyboard into a file.

That licence is now optional. Scrollmark's own editor renders too — MIT, no seat threshold, no paid tier — and an agent drives it over MCP. It does not read the props document: it has its own project format, so the agent builds the timeline from the same storyboard through the editor's own commands. The trade is honest rather than hidden. Remotion renders headless, so it suits a run nobody is watching; the editor needs to be running, which suits one where somebody is.

ElevenLabs voice has a script now — video-studio tts_eleven — but it bills per character and returns no word timings, so captions for an ElevenLabs read come from gen_captions. The local voice is free and runs offline; reach past it deliberately. The automated quality gate at the last step of a production run used to be an unpublished internal CLI; it is now qc_render.py, bundled, needing no install. It proves a render matches its plan — it cannot tell you the plan was worth rendering, so the looking is still yours.

Remotion · Node or the editor · no licence ElevenLabs · paid API ffmpeg on PATH

Without the engine

What you still get.

Layer three is optional. Here is what each video skill still gives you without it.

loses nothing

Unaffected

The whole social half.

All seven social-media skills and agent-interview are untouched by any of this.

studio-setup loses the least of the video skills: doctor.py ships with it, so the status report and the triage work immediately. Only the install plan — video-studio setup and its auto/system/manual classification — needs the package.

audio-acquisition is the best-off of the production skills. It carries measure and normalize_audio, so the measure-don't-trust discipline and the music-costs-6-dB fix are both executable out of the box. Voice, generated music and licence-filtered effects are [audio].

holes in it

Partly executable

Useful, but incomplete.

video-formats still works for eight of its ten formats. Those are structure you can follow in any editor. Boil is roughly 40% inoperative without [generate]: its mark vocabulary, shape files, and palette workflow are gen_boil, so the interview questions have no answers to pick from. PointerPopups does not work at all as written without [vision] — its entire grammar is the output of a hand-tracking pass.

brand-kit lets you agree a brand with someone and hand-write the files. The preset mechanism that lists, shows, saves and applies one is video-studio styles, so applying a brand becomes manual editing.

media-acquisition keeps prekey. The provider ladder and the landmine list will still tell a human which library to open, but the searching, generating, licence filtering and the five-way check on what came back are [sourcing,generate].

briefings

Package-side

Briefings, not workflows.

subject-compositing is entirely package-side: segmentation, the feathered occlusion seam, the arm punch-through and the gesture timing all need [vision], because MediaPipe and OpenCV cannot be bundled into a skill folder. What survives is the footage brief — what a segmenter needs from a take — and it is worth having before anyone films.

edit-handoff cannot produce a file without [export]; the exporters read the engine's per-project timeline document. What generalises is the judgement: which format each application actually imports, and that no interchange format carries effects.

video-production ships doctor, normalize, poster and qc_render, but it sequences the whole engine — props, preview, preflight — and a renderer on top, whether that is Remotion or the editor. With none of those present there is nothing to sequence. What survives is the shape of a production run: which decision precedes which, and where money enters.

Each of those skills states its own dependency in a ## Requires section near the top of its SKILL.md — that is where the authoritative answer lives. The longer version of this page is in the README.

The full deck

Sixteen skills, three jobs.

Understanding social media, producing short-form video, and running the working method underneath both. Each skill is a compact playbook: patterns and judgement calls, not API wrappers. They pair well with the SocialGPT MCP server, which brings your real numbers into the conversation.

Group one · 7 skills

Understanding social media.

Tone, hooks, trends, platform conventions, creator voice. All seven run standalone — no external tools, no accounts, no keys.

Interpretation

read-the-room

Helps agents interpret captions, comments, replies, and DMs by reading tone, sarcasm, emoji, parasocial language, and comment-section context.

Reach for it interpreting comments, captions, replies, or DMs
npx skills add scrollmark/social-skills -s read-the-room

Craft

hook-anatomy

Breaks down the first 1–3 seconds of a post into concrete hook patterns, then shows why one opening keeps attention and another gets skipped.

Reach for it analysing, scoring, or generating hooks
npx skills add scrollmark/social-skills -s hook-anatomy

Timing

trend-radar

Decides whether a trend is emerging, peaking, saturated, or already only useful as parody, so an agent can recommend timing instead of chasing noise.

Reach for it deciding if (and when) a trend is worth riding
npx skills add scrollmark/social-skills -s trend-radar

Strategy

platform-fluency

Explains how discovery differs across TikTok, Instagram, YouTube, X, and LinkedIn: algorithms, formats, content lifespan, and audience expectations.

Reach for it platform conventions, algorithms, audience behaviour
npx skills add scrollmark/social-skills -s platform-fluency

Analysis

content-autopsy

Looks at reach, engagement, saves, shares, and repeated patterns before calling a post successful, broken, or just lucky.

Reach for it figuring out why a post took off — or didn't
npx skills add scrollmark/social-skills -s content-autopsy

Voice

voice-matching

Turns a creator's voice into usable writing guidance: vocabulary, rhythm, opening moves, humor, CTA habits, and what to avoid.

Reach for it writing as a creator, or auditing consistency
npx skills add scrollmark/social-skills -s voice-matching

Distribution

repurpose-engine

Adapts one idea for different platforms by changing the format, hook, length, and framing while keeping the core message and voice intact.

Reach for it taking one piece of content everywhere it can go
npx skills add scrollmark/social-skills -s repurpose-engine

Group two · 7 skills

Producing video.

Craft skills for making a short-form video, not only planning one. The judgement is prose you can follow anywhere; execution comes from scripts bundled with the skill or from the engine in the same repo.

Structure

video-formats

Provides ten reusable short-form video structures, from talking-head clips to hand-drawn motion graphics, with guidance for planning and critique.

Reach for it planning, structuring, or critiquing a short-form video
8 of 10 formats need nothing Boil + PointerPopups: pip install
npx skills add scrollmark/social-skills -s video-formats

Consistency

brand-kit

Captures the visual and writing rules for a run of videos: captions, colors, layout, title treatment, logos, fonts, voice, and CTAs.

Reach for it keeping a run of videos visually consistent
presets need pip install
npx skills add scrollmark/social-skills -s brand-kit

Sourcing

media-acquisition

Helps choose and verify source media for a shot: public-domain archives, stock, generated footage, or user-supplied URLs.

Reach for it deciding where a shot's pictures come from
ships prekey.py pip install [sourcing,generate]
npx skills add scrollmark/social-skills -s media-acquisition

Sound

audio-acquisition

Guides narration, music, and sound effects: voice choice, publish-safe music sources, timing edits to a track, and fixing bad levels.

Reach for it a video needs a voice, a bed, or a fix for bad levels
ships measure + normalize voice + music: pip install [audio]
npx skills add scrollmark/social-skills -s audio-acquisition

Compositing

subject-compositing

Plans shots where a filmed person is composited into another scene, including replacement backgrounds, foreground props, motion, and pointer popups.

Reach for it planning a shot that composites a person into a scene
pip install [vision]
npx skills add scrollmark/social-skills -s subject-compositing

Handoff

edit-handoff

Explains how to hand a cut to Premiere Pro, DaVinci Resolve, Final Cut Pro, or CapCut, including what exports cleanly and what must be rebuilt.

Reach for it an editor is picking the cut up from here
pip install [export]
npx skills add scrollmark/social-skills -s edit-handoff

Pipeline

video-production

Runs the video workflow in order: interview, storyboard, source media, preview, render, and quality check, with cost and stall-handling rules.

Reach for it producing a video end to end, or a run has stalled
ships 4 scripts pip install + a renderer
npx skills add scrollmark/social-skills -s video-production

Group three · 2 skills

Working method and toolchain.

How to ask a person the right questions, and how to tell whether the machine can do the job.

Method

agent-interview

Shows agents how to ask a user for decisions in a guided setup, intake, wizard, or onboarding flow without leaving the questions too open-ended.

Reach for it an agent has to interview someone before it can act
standalone
npx skills add scrollmark/social-skills -s agent-interview

Toolchain

studio-setup

Checks whether a machine can produce video, what the pipeline depends on, how to triage failures, and which tool or API key to add next.

Reach for it checking or repairing a video toolchain
ships doctor.py install plan: pip install
npx skills add scrollmark/social-skills -s studio-setup

Open invitation

Add a skill

A skill here is prose: a SKILL.md, the reference files it needs, and a description saying when to reach for it. If you know something about the feed that Claude keeps getting wrong, that is a pull request.

Read CONTRIBUTING.md
Read the source on GitHub