Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints.

MITAuto-check passedMedia & Creative

Install Veed

skills CLI
$ npx skills add Anil-matcha/awesome-muse-connectors --skill veed -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Anil-matcha/awesome-muse-connectors veed --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git skills-src && mkdir -p .claude/skills && cp -r skills-src/connectors/veed .claude/skills/veed && rm -rf skills-src

Use ~/.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/

Facts

Skill name
veed
GitHub stars
1.3k
Token cost
~926 tokens
SKILL.md length
337 words
Files
2
Skills in repo
153
Repo updated
First seen
Licence
MIT

At a glance

Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints.

  • Works in 4 steps: Confirm before every background-remove:… → Bulk/batch processing multiplies the… → Never invent a base host. If VEED has… → …
  • Remove video background
  • SKILL.md covers Purpose, Tooling, Auth and Operating Rules, plus 2 more sections
  • Runs Python scripts from its folder; needs API_KEY

What it does

Veed is an agent skill from Anil-matcha/awesome-muse-connectors. Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints. Trigger phrases: veed, remove video background, background removal, transparent video.

Its SKILL.md is about 930 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `bin/veed.py`).

It sits in Media & Creative, covering Image editing. It works with fal. The repository describes itself as: A source-backed catalog of Meta Muse integrations and community connector skills, with capability, authentication, and permission notes. The licence is MIT.

When your agent uses it

  • Remove video background
  • Background removal
  • Transparent video

Example prompts

  • “/veed”

Requirements

  • Python 3
  • A credential in API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Confirm before every background-remove: usage is metered per second/minute/frame with no subscription, so each call has a real cost. Name…
  2. Bulk/batch processing multiplies the cost; confirm the batch size explicitly.
  3. Never invent a base host. If VEED has not confirmed one, say so and stop.
  4. Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/veed.py). Do not print, log, or transmit the key value.

What it can do on your machine

Read from SKILL.md and the folder at commit d6dc5d8. 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

    Ships script files (Python), which the agent can run.

    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 these keys or tokens, usually read from environment variables:

    • API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Veed loads about 926 tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 337 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~48
When it runs · the whole SKILL.md, loaded when a task matches
~926

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 Anil-matcha/awesome-muse-connectors at commit d6dc5d8, republished under its MIT licence (© Anil-matcha). 337 words, ~926 tokens.

Download SKILL.mdSave it as .claude/skills/veed/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
veed
description
Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints. Trigger phrases: veed, remove video background, background removal, transparent video.
metadata.includeInPrompt
true
tagline
Remove backgrounds from video with VEED's direct developer API (POST /v1/video/background-remove): standard quality, fast throughput and green-screen…
catalog_auth
API key via the secure credential flow
catalog_hosts
the host you pass via --api-host

VEED

Purpose

Remove backgrounds from video with VEED's direct developer API (POST /v1/video/background-remove): standard quality, fast throughput and green-screen chroma-key with spill suppression. Outputs are VP9-with-alpha or H.264 RGB+alpha, up to 4K.

VEED also serves lip-sync and talking-video models through fal.ai (veed/lipsync, veed/fabric-1.0); those are covered by the separate fal-ai connector.

Tooling

All commands go through bin/veed.py. --api-host is required on every command (see Auth):

bash
bin/veed.py auth --api-host https://<VEED_API_HOST>                      # check readiness (no free status endpoint)
bin/veed.py background-remove --api-host https://<VEED_API_HOST> \
    --file ./talking-head.mp4 --endpoint standard --output-format vp9_alpha  # confirm first: metered
bin/veed.py background-remove --api-host https://<VEED_API_HOST> \
    --file ./bulk.mp4 --endpoint fast --output-format h264_rgba --resolution 4k
bin/veed.py background-remove --api-host https://<VEED_API_HOST> \
    --file ./greenscreen.mp4 --endpoint green_screen --output-format vp9_alpha \
    --webhook-url "https://..."                                          # async completion for long jobs

The API returns a time-limited signed output_url; download the processed video promptly instead of storing the URL. Long jobs can run async with a webhook callback.

Auth

  • Provider id: veed (credential is collected as custom.veed)
  • Collection: API key via the secure credential flow (credentials.request_api_access); VEED's developer docs describe how to obtain one
  • Header: Authorization: Bearer <API_KEY> (the CLI builds this from the credential surrogate)
  • Allowed hosts: the host you pass via --api-host (the credential is only ever sent there)
  • Status check: bin/veed.py auth --api-host <host> (VEED has no free status endpoint, so this only confirms the credential is stored and the host is set)

Open item (unresolved, never guessed): VEED publishes the path POST /v1/video/background-remove but no base host in its public developer docs (veed.io/api currently routes new developers to fal.ai keys). The CLI refuses to run without an explicit --api-host; confirm the host from VEED's developer documentation or your VEED API dashboard before use.

Operating Rules

  1. Confirm before every background-remove: usage is metered per second/minute/frame with no subscription, so each call has a real cost. Name the file, the endpoint and the output format.
  2. Bulk/batch processing multiplies the cost; confirm the batch size explicitly.
  3. Never invent a base host. If VEED has not confirmed one, say so and stop.
  4. Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/veed.py). Do not print, log, or transmit the key value.

Files

  • SKILL.md
  • bin/veed.py

Maturity

Draft: written from VEED's published API docs; not live-tested end-to-end, and the direct API base host is an unresolved open item (see Auth). The fal-hosted VEED models are intentionally out of scope here.

© Anil-matcha, 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 1 other file in connectors/veed of Anil-matcha/awesome-muse-connectors.

  • SKILL.md
  • bin/veed.py

Open the folder on GitHubat commit d6dc5d8

Compare with similar skills

Veed 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.

Veed compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Veed this skillAnil-matcha/awesome-muse-connectors1.3k—~926Automated safety check: PassMIT
Fal AI Generationwitnesstodark/mr-mak-workspace343—~1kAutomated safety check: NotesMIT
Character Design with genmediafal-ai-community/skills250—~1.3kAutomated safety check: PassNone
Fal UpscaleCraftOS-dev/CraftBot392—~953Automated safety check: PassMIT
Image Generation Gatewayscalesthio/generative-media-skills193—~20kAutomated safety check: PassMIT
Fal Image Editnexu-io/open-design100k—~301Automated safety check: PassApache-2.0

Similar skills

  • Fal AI Generation

    witnesstodark/mr-mak-workspace

    Generate and edit images, create video, audio, 3D assets or material maps through fal.ai MCP or the Python queue client.

    343 GitHub stars~1k tokensUpdated today
    Media & CreativeAuto-check: notes
  • Character Design with genmedia

    fal-ai-community/skills

    Builds consistent characters, reference and expression sheets, outfit variations and character-to-video shots with the genmedia CLI while keeping identity stable.

    250 GitHub stars~1.3k tokensUpdated 10 days ago
    Media & CreativeAuto-check passed
  • Fal Upscale

    CraftOS-dev/CraftBot

    Upscale and enhance image resolution using AI. An agent skill from CraftOS-dev/CraftBot.

    392 GitHub stars~953 tokensUpdated today
    Media & CreativeAuto-check passed
  • Image Generation Gateways

    calesthio/generative-media-skills

    Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts…

    193 GitHub stars~20k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Fal Image Edit

    nexu-io/open-design

    AI-powered image editing with style transfer, background removal, object removal, and inpainting via fal.ai hosted models.

    100k GitHub stars~301 tokensUpdated today
    Media & CreativeAuto-check passed
  • Fal Upscale

    nexu-io/open-design

    Upscale and enhance image and video resolution using AI super-resolution models hosted on fal.ai.

    100k GitHub stars~286 tokensUpdated today
    Media & CreativeAuto-check passed

More from Anil-matcha/awesome-muse-connectors

All 153 skills in this repo
  • Airtable

    Anil-matcha/awesome-muse-connectors

    List Airtable bases, read table records, and add records. An agent skill from Anil-matcha/awesome-muse-connectors.

    1.3k GitHub stars~511 tokensUpdated 3 days ago
    Auto-check passed
  • Alphavantage

    Anil-matcha/awesome-muse-connectors

    Stock quotes and daily price history. An agent skill from Anil-matcha/awesome-muse-connectors.

    1.3k GitHub stars~517 tokensUpdated 3 days ago
    Auto-check passed
  • Amadeus

    Anil-matcha/awesome-muse-connectors

    Search travel with Amadeus: flight offers and prices, airport autocomplete, hotel offers, cheapest dates.

    1.3k GitHub stars~699 tokensUpdated 3 days ago
    Auto-check passed
  • Apollo

    Anil-matcha/awesome-muse-connectors

    Search B2B contacts with Apollo.io: find people by title and company, enrich contacts and companies.

    1.3k GitHub stars~492 tokensUpdated 3 days ago
    Auto-check passed
  • Aqara

    Anil-matcha/awesome-muse-connectors

    Read and control Aqara smart home devices: plugs, switches, lights, AC, locks, curtains, scenes.

    1.3k GitHub stars~1.6k tokensUpdated 3 days ago
    Auto-check passed
  • Asana

    Anil-matcha/awesome-muse-connectors

    Read and manage Asana tasks: my tasks, task details, create tasks.

    1.3k GitHub stars~481 tokensUpdated 3 days ago
    Auto-check passed

Works with

Questions about Veed

What does Veed do?

Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints. Veed is an agent skill from Anil-matcha/awesome-muse-connectors. Remove video backgrounds with VEED's direct developer API: standard, fast and green-screen endpoints.

When should I use Veed?

Veed fits situations like: remove video background; background removal; transparent video.

How do I install Veed in Claude Code?

Run `npx skills add Anil-matcha/awesome-muse-connectors --skill veed -a claude-code`. Or copy the skill folder (connectors/veed in Anil-matcha/awesome-muse-connectors) into .claude/skills/veed in your project. Claude Code loads it when a task matches its description.

How do I install Veed in Codex?

Run `npx skills add Anil-matcha/awesome-muse-connectors --skill veed -a codex`. Or copy the skill folder (connectors/veed in Anil-matcha/awesome-muse-connectors) into .agents/skills/veed in your project. Codex loads it when a task matches its description.

Can I use Veed 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 Anil-matcha/awesome-muse-connectors --skill veed -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/veed, .gemini/skills/veed, .github/skills/veed and .opencode/skills/veed in your project.

What does Veed need to run?

Going by SKILL.md and its folder, Veed needs Python for the scripts in its folder and credentials named API_KEY. Our summary lists: Python 3; A credential in API_KEY.

Does Veed 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 Veed 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 Veed use?

Veed 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 Veed use?

About 926 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Veed?

Skills that share tags, products or a category with Veed: Fal AI Generation (witnesstodark/mr-mak-workspace, 343 stars), Character Design with genmedia (fal-ai-community/skills, 250 stars), Fal Upscale (CraftOS-dev/CraftBot, 392 stars) and Image Generation Gateways (calesthio/generative-media-skills, 193 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Veed?

Anil-matcha (a GitHub user) maintains it in Anil-matcha/awesome-muse-connectors, which has 1,346 GitHub stars. The repository holds 153 skills in this directory. The repository was last updated on October 5, 2026.

Source: Anil-matcha/awesome-muse-connectors on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.