Stage Edit
Orkas-AI/Orkas-VideoStudio
Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained…
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries.
Install Synthesia
$ npx skills add social-media-skills/skills --skill synthesia -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install social-media-skills/skills synthesia --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/social-media-skills/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/synthesia .claude/skills/synthesia && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "synthesia" agent skill from https://github.com/social-media-skills/skills/tree/main/skills/synthesia into .claude/skills/synthesia/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "synthesia", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/social-media-skills/skills/tree/main/skills/synthesiaType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add social-media-skills/skills --skill synthesia -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install social-media-skills/skills synthesia --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/social-media-skills/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/synthesia .agents/skills/synthesia && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "synthesia" agent skill from https://github.com/social-media-skills/skills/tree/main/skills/synthesia into .agents/skills/synthesia/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "synthesia", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add social-media-skills/skills --skill synthesia -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install social-media-skills/skills synthesia --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/social-media-skills/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/synthesia .cursor/skills/synthesia && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "synthesia" agent skill from https://github.com/social-media-skills/skills/tree/main/skills/synthesia into .cursor/skills/synthesia/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "synthesia", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/social-media-skills/skills.git --path skills/synthesia--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add social-media-skills/skills --skill synthesia -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install social-media-skills/skills synthesia --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/social-media-skills/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/synthesia .gemini/skills/synthesia && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "synthesia" agent skill from https://github.com/social-media-skills/skills/tree/main/skills/synthesia into .gemini/skills/synthesia/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "synthesia", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install social-media-skills/skills synthesiaInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add social-media-skills/skills --skill synthesia -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/social-media-skills/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/synthesia .github/skills/synthesia && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "synthesia" agent skill from https://github.com/social-media-skills/skills/tree/main/skills/synthesia into .github/skills/synthesia/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "synthesia", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add social-media-skills/skills --skill synthesia -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install social-media-skills/skills synthesia --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/social-media-skills/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/synthesia .opencode/skills/synthesia && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "synthesia" agent skill from https://github.com/social-media-skills/skills/tree/main/skills/synthesia into .opencode/skills/synthesia/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "synthesia", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
synthesia- GitHub stars
- 134
- Token cost
- ~2.1k tokens
- SKILL.md length
- 894 words
- Files
- 6 (incl. references)
- Skills in repo
- 106
- Repo updated
- First seen
- Licence
- MIT
At a glance
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries.
- Works in 2 steps: The content skill… → brand-profile + voice-builder (the…
- Someone wants to make videos with Synthesia/AI avatars
- SKILL.md covers The POV: the presenter is…, Read these first, The framework: HUMAN and The reality (verify-quarterly), plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Synthesia is an agent skill from social-media-skills/skills. The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries. Use when someone wants to make videos with Synthesia/AI avatars, create a personal avatar/digital twin, localize one video into many languages, build training/L&D video at scale, or asks whether an avatar should replace them on camera. Uses the HUMAN framework. Reads the content skill + brand-profile + voice-builder…
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `evals/evals.json`, `references/fit-and-templates.md` and `references/scope-and-connections.md`).
It sits in Media & Creative, covering Educational content, Internationalization and AI video generation. It works with HeyGen. The repository describes itself as: 106 social media skills for AI agents - strategy, writing, video, design, platform growth, publishing, and analytics. Works with Claude, Cursor, OpenClaw, Hermes & 40+ agents. The licence is MIT.
When your agent uses it
- Someone wants to make videos with Synthesia/AI avatars
- Create a personal avatar/digital twin
- Localize one video into many languages
- Build training/L&D video at scale
Example prompts
- “/synthesia”
Workflow steps
2 steps, taken from the first numbered list in SKILL.md.
- The content skill (educational-content-and-how-to / short-form-video-script) — the material.
- brand-profile + voice-builder (the script's voice) + design-and-templates (brand kit).
What it can do on your machine
Read from SKILL.md and the folder at commit 6e30eeb. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Synthesia loads about 2.1k tokens when it runs, and up to ~5.5k if it reads all its reference files. Until then it costs about 249 tokens; SKILL.md has 894 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from social-media-skills/skills at commit 6e30eeb, republished under its MIT licence (© social-media-skills). 894 words, ~2,113 tokens.
Download SKILL.mdSave it as
.claude/skills/synthesia/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- synthesia
- description
- The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries. Use when someone wants to make videos with Synthesia/AI avatars, create a personal avatar/digital twin, localize one video into many languages, build training/L&D video at scale, or asks whether an avatar should replace them on camera. Uses the HUMAN framework. Reads the content skill + brand-profile + voice-builder first. The agent scripts and plans (API where connected); the HUMAN approves every video; WoopSocial publishes. Spines: the fit test (avatars win at scale/localization/training, lose to a real face for trust-led content); consent-first likeness; the script is most of avatar quality — lock copy before generating. Never impersonate, fake endorsements, or skip AI-disclosure. Distinct from heygen, talking-head-and-piece-to-camera, ai-video/luma, ai-voiceover, and descript.
- version
- 1.0.0
synthesia
The avatar-video tool skill — have a reason for an avatar, use consented likeness only, make the script
spoken-word, assemble + localize, note the disclosure. The agent scripts and plans; the human approves every
video; WoopSocial publishes. (Ships with tools/integrations/synthesia.md.)
The POV: the presenter is synthetic — the standards stay human
Synthesia is the enterprise avatar category leader: one locked script becomes a consistent presenter in 140+
languages with no re-shoots, which makes it unbeatable for training, onboarding, explainers, and localization
at scale. The top-1% operator holds four lines. (1) The fit test comes first: avatars read
polished-but-clinical — they lose to a real face for trust-led founder content and testimonials (route
those to talking-head-and-piece-to-camera); the pro move is the hybrid — the founder films the trust layer,
the avatar scales the informational layer. (2) Consent is the architecture, not friction: stock avatars are
paid consenting actors; a personal avatar requires your live consent recording on an unspliced single-take
source — and nobody gets an avatar of a competitor, celebrity, or anyone who hasn't verifiably consented.
(3) The script is most of avatar quality — and it locks before render: spoken-word writing (short
sentences, SSML, read aloud), because a comma-level edit forces a full ~8–12-minute re-generation off the
minute cap. (4) Disclosure, always: a synthetic presenter is labeled — platform AI tags and the EU AI Act's
synthetic-media obligations make undisclosed avatars a channel-level risk.
Read these first
- The content skill (educational-content-and-how-to / short-form-video-script) — the material.
- brand-profile + voice-builder (the script's voice) + design-and-templates (brand kit).
The framework: HUMAN
(Depth: references/the-human-framework.md.)
- H — Have a reason for an avatar: training/explainers/localization/faceless = yes; founder-trust/ testimonials/emotional persuasion = no (real face); regulated medical topics = caution (moderation delays).
- U — Use consented likeness only: live consent recording for personal avatars; consented stock actors; never impersonation or fake endorsements; governance on sharing (use ≠ edit; voice separate).
- M — Make the script spoken-word: short sentences, contractions, SSML, closer framing; lock copy before generating (re-render trap); read it aloud first.
- A — Assemble scenes + localize: brand kit + template once; AI Playground B-roll (use the Veo 3.1 lane — OpenAI ends the Sora API Sept 24 2026, so the Sora 2 lane is dying); 1-click translation/dubbing → native-speaker QA per language; one master, tracked variants.
- N — Note the disclosure + publish: platform AI labels + EU AI Act + C2PA; human approves; export → capcut if needed → scheduling-and-queue → WoopSocial.
The reality (verify-quarterly)
Synthesia 3.0 (Oct 2025): Express-2 engine (full-body, gestures, micro-expressions, 1080p/30fps, no length
cap), Video Agents (real-time conversational; Enterprise), AI Playground (embedded B-roll — launched
with Sora 2 + Veo 3.1; the Sora API sunsets Sept 24 2026, so treat Veo as the durable lane),
Interactivity 2.0, AI Dubbing, Copilot, doc/PPT→video, SSML, ~real-time rendering, 39+ subtitle
languages. Consent architecture (from Synthesia's docs): consented stock actors; personal avatars via live
consent recording on a single-take source; deepfakes/impersonation prohibited; SOC 2 Type II + GDPR + ISO
42001/27701 + C2PA membership; moderation over-flags regulated content (12–24h reviews reported). Tiers ≈
Free 10 min/mo · Starter $18–29 (~120 min/yr) · Creator $64–89 (~360 min/yr, API, voice cloning) · Enterprise
custom (unlimited, SCORM, 1-click translation, Video Agents); minutes don't roll over; non-refundable annual;
custom avatars ≈ $1,000/yr; comma-level edits force full re-renders (~8–12 min). Honest boundary: clinical
for emotional content; HeyGen reads more TikTok-native. Attribute all; verify-quarterly. Full detail:
references/synthesia-2026-reality.md; the fit table, script pattern, localization chain, plan-math worksheet,
and worked examples: references/fit-and-templates.md.
Show full SKILL.md (351 more words)Show less
Honest scope (never violate)
- The agent runs the fit test, writes locked spoken-word scripts, plans scenes/localization/QA, and drives the API where connected (exact human steps otherwise; no unreviewed auto-publish); the human approves every video (no fabricated "that looks natural"; native-speaker QA per language); WoopSocial publishes the exports — it does not generate avatars; LMS/SCORM distribution is the human's.
- Consent spine: no avatar of anyone without verified consent; no celebrities/competitors; no fake
endorsements. Disclosure always (platform labels; EU AI Act; C2PA). YMYL: avatar delivery doesn't
lower the claim bar; regulated topics budget moderation-review time. Never fabricate tiers, gates,
render times, or capabilities. (Full scope:
references/scope-and-connections.md.)
Distinct from its siblings (route correctly)
synthesia (this) = the enterprise/L&D/localization avatar lane · heygen = the creator/social-native lane (test both; state trade-offs) · talking-head-and-piece-to-camera = the real human (trust content routes there; the hybrid is the pro move) · ai-video / luma / veo-3 / kling = cinematic footage, no presenter (the AI Playground embeds two of them for B-roll) · ai-voiceover / elevenlabs = voice-only · descript = editing recordings (this generates the presenter) · capcut = post-render captions/pace.
Where this connects
Reads first: the content skill + brand-profile + voice-builder + design-and-templates. Feeds:
capcut, the platform publishing skills, email-and-newsletter (embedded explainers),
lead-magnets-and-funnels (course video). Publishes via: export → scheduling-and-queue → WoopSocial
(social); the LMS (training — human). Tool file: tools/integrations/synthesia.md. Measure with: native +
analytics-and-reporting on completion/watch-through — never fabricated.
Definition of done
Avatar video that passed the fit test first (training/explainers/localization/faceless = avatar; trust-led founder content routed to a real face; the hybrid split applied where both exist), built on consented likeness only (stock actors or the owner's live-consent personal avatar; no impersonation or fake endorsements), scripted as locked spoken-word (short sentences, SSML, read aloud, signed off before a single render — no re-render burn), assembled on the brand kit with honest B-roll and localized through the chain (master → 1-click translation/dubbing → native-speaker QA per language → tracked variants), and published disclosed (platform AI labels; EU AI Act; C2PA) via WoopSocial after human approval, with plan math done honestly (minute caps, no rollover, Enterprise gates, $1,000/yr custom avatars, moderation-review buffer for regulated topics); no undisclosed synthetic presenters, no unconsented likeness, no fabricated tiers/capabilities; and correctly distinguished from heygen, talking-head-and-piece-to-camera, ai-video/luma, ai-voiceover, and descript.
© social-media-skills, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in skills/synthesia of social-media-skills/skills.
- SKILL.md
- evals/evals.json
- references/fit-and-templates.md
- references/scope-and-connections.md
- references/synthesia-2026-reality.md
- references/the-human-framework.md
Open the folder on GitHubat commit 6e30eeb
Compare with similar skills
Synthesia next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Synthesia this skillsocial-media-skills/skills | 134 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Stage EditOrkas-AI/Orkas-VideoStudio | 499 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Heygenzapier/connectors | 177 | — | ~4.4k | Automated safety check: Pass | Elastic-2.0 | |
| Scenario Videoscenario-labs/skills | 946 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Super Video MakerBomx/super-video-maker-skill | 310 | — | ~11k | Automated safety check: Notes | None | |
| Develop Timeline Studio PluginMartinDelophy/ai-video-editor | 905 | — | ~989 | Automated safety check: Pass | MIT |
Similar skills
- Official
Heygen
zapier/connectors
Agent-callable HeyGen tools — generate AI avatar videos, translate and lip-sync videos, synthesize speech, and clone or browse voices and avatars.
Scenario Video
scenario-labs/skills
A skill your agent uses when generating or editing video on Scenario via MCP: text-to-video, a music video from a song, image-to-video (still animation, frame anchors), motion prompting, lipsync and…
Super Video Maker
Bomx/super-video-maker-skill
End-to-end AI video production skill for agentic frameworks.
Develop Timeline Studio Plugin
MartinDelophy/ai-video-editor
Design, evaluate, implement, or review image and video generation connectors for Timeline Studio.
Collage B-Roll Video Maker
imraywang/rayskills
Turns a spoken line or a full topic into editorial-collage videos of halftone cut-outs assembled piece by piece, as 5-second B-roll or a narrated explainer.
More from social-media-skills/skills
All 106 skills in this repoAI Image Editing
social-media-skills/skills
The AI image-editing router — inpainting/object removal, background removal, upscaling, outpainting, old-photo restoration, and retouch, routed task-first to the right engine.
AI Music And Sound
social-media-skills/skills
The AI music + sound-design skill for social -- original/licensed audio beds and sound design for Reels/TikToks/Shorts/videos.
AI Search Optimization
social-media-skills/skills
A skill your agent uses to get a brand and its content CITED and RECOMMENDED by AI answer engines — the GEO (Generative Engine Optimization) / AI-search-visibility skill.
AI Video
social-media-skills/skills
The model-agnostic AI-video router and brief — the counterpart to image-prompt.
AI Voiceover
social-media-skills/skills
The AI narration / voiceover mini-skill (ElevenLabs-led). An agent skill from social-media-skills/skills.
Analytics And Reporting
social-media-skills/skills
Social media analytics and reporting — read native platform data honestly and turn it into next actions.
Related
Works with
Categories
Questions about Synthesia
What does Synthesia do?
The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries. Synthesia is an agent skill from social-media-skills/skills. The Synthesia craft skill — produce avatar video (training, onboarding, explainers, localized series, faceless educational content) with the consent-first architecture and honest fit boundaries.
When should I use Synthesia?
Synthesia fits situations like: someone wants to make videos with Synthesia/AI avatars; create a personal avatar/digital twin; localize one video into many languages; build training/L&D video at scale.
How do I install Synthesia in Claude Code?
Run `npx skills add social-media-skills/skills --skill synthesia -a claude-code`. Or copy the skill folder (skills/synthesia in social-media-skills/skills) into .claude/skills/synthesia in your project. Claude Code loads it when a task matches its description.
How do I install Synthesia in Codex?
Run `npx skills add social-media-skills/skills --skill synthesia -a codex`. Or copy the skill folder (skills/synthesia in social-media-skills/skills) into .agents/skills/synthesia in your project. Codex loads it when a task matches its description.
Can I use Synthesia in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add social-media-skills/skills --skill synthesia -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/synthesia, .gemini/skills/synthesia, .github/skills/synthesia and .opencode/skills/synthesia in your project.
What does Synthesia need to run?
SKILL.md names no scripts, command-line tools or credentials: Synthesia is instructions for the agent only.
Does Synthesia access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Synthesia safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Synthesia use?
Synthesia is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Synthesia use?
About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.
What are the alternatives to Synthesia?
Skills that share tags, products or a category with Synthesia: Stage Edit (Orkas-AI/Orkas-VideoStudio, 499 stars), Heygen (zapier/connectors, 177 stars), Scenario Video (scenario-labs/skills, 946 stars) and Super Video Maker (Bomx/super-video-maker-skill, 310 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Synthesia?
social-media-skills (a GitHub organization) maintains it in social-media-skills/skills, which has 134 GitHub stars. The repository holds 106 skills in this directory. The repository was last updated on October 1, 2026.
Source: social-media-skills/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.