beatra-ai-video-studio – skill Thiết kế & UI cho agent AI

Beatra AI Video Studio

Overview

Beatra AI Video Studio is Beatra's official agent package for short AI video

work: text-to-video, image-to-video, first/last-frame interpolation,

reference-guided generation, and editing or extending an existing clip. The

video is produced on the hosted, paid Beatra service (mcp.beatra.ai).

This catalog entry is a reviewed pointer, not the executable package. It

contains no client code and performs no Beatra operation by itself. The package

it points to bundles three standard-library Python scripts that make network

calls and store a credential. It has no self-updater: it never downloads

code and never changes its own files. Read

[Install](#install-pinned-verified-approved-twice) and

[Security & Safety Notes](#security--safety-notes) before activating it.

| Pinned identity | Value |

| --- | --- |

| Package | beatra-ai-video-studio 1.3.5 |

| Source commit | [beatra-ai/beatra-skills@b7ab8ed](https://github.com/beatra-ai/beatra-skills/tree/b7ab8ed02980ee44b6dac62633f8d79daf0809ab/skills/beatra-ai-video-studio) (full SHA b7ab8ed02980ee44b6dac62633f8d79daf0809ab) |

| Package tree | 5183c76c894e650691c8bb638257dd202b23e66c (Git tree ID of skills/beatra-ai-video-studio at that commit) |

| License | MIT No Attribution (MIT-0) |

The pinned tree holds regular files only (no symlinks, no executable bits, no

binaries). Confirm that with the inspect commands below.

When to Use This Skill

• Use when the user explicitly wants a short AI video clip produced on Beatra

and accepts that the work is paid and runs on a hosted service.

• Use when a still image should be animated, two frames interpolated, or an

existing clip edited or extended by Beatra.

• Do not use for local-only or offline video editing, timeline assembly, or

when the user has not agreed to send prompts and media to a third party.

Install (pinned, verified, approved twice)

Step 1: Fetch the pinned tree into a review directory

Explain that this fetches an external package from github.com, then ask

for approval. Only after approval:

set -e
umask 077
review_dir="$(mktemp -d)"
cd "$review_dir" || exit 1
git clone --quiet --filter=blob:none --no-checkout https://github.com/beatra-ai/beatra-skills.git src
git -C src checkout --quiet b7ab8ed02980ee44b6dac62633f8d79daf0809ab -- skills/beatra-ai-video-studio
test "$(git -C src rev-parse 'b7ab8ed02980ee44b6dac62633f8d79daf0809ab:skills/beatra-ai-video-studio')" = '5183c76c894e650691c8bb638257dd202b23e66c' && echo TREE-OK

Stop if the last command does not print TREE-OK. The expected commit and

tree IDs come from this catalog entry, not from the package or its website,

and Git addresses every fetched object by its hash.

Step 2: Inspect before activation

git -C src ls-tree -r b7ab8ed02980ee44b6dac62633f8d79daf0809ab -- skills/beatra-ai-video-studio | awk '$1 != "100644"'  # expect no output
grep -n -E 'maybe_auto_update|download_update|_apply_update' src/skills/beatra-ai-video-studio/scripts/mcp_client.py  # expect no output

The first check lists any symlink, executable, or submodule entry; the second

finds the entry points of the self-updater that earlier versions shipped.

Report to the user what the review found: SKILL.md, manifest.json,

install-source.json (the one-line marker {"schema_version":1,"source":"github"}),

the bundled Markdown references, and scripts/authorize.py,

scripts/mcp_client.py, scripts/uninstall.py (Python 3.10+, standard

library only, no dependency installation, no lifecycle hooks). Summarize the

network, credential, local-state, telemetry, and version-notice behavior

listed under [Security & Safety Notes](#security--safety-notes).

The manifest and pattern scans above are only inventory aids. Before activation, read every file in the pinned tree, including each script, reference and hook, and inspect all dependency and network behavior. Do not claim source review from grep output. If complete review cannot be performed, stop before copying or executing; ask for a separate review rather than treating a digest as evidence of safety.

Step 3: Copy in

Ask for a second, separate approval, because this changes agent

configuration. Then copy the reviewed tree to the host's skills directory

(Claude Code shown; use the equivalent path for other hosts):

dest="$HOME/.claude/skills/beatra-ai-video-studio"
test ! -e "$dest" && test ! -L "$dest" || { echo "destination exists; stop and ask the user"; exit 1; }
cp -R "src/skills/beatra-ai-video-studio" "$dest"

There is no update switch to turn off in this version.

Step 4: Authorize as its own decision

Authorization opens a browser sign-in and stores a bearer token. Ask first.

python3 "$dest/scripts/authorize.py"

Start a new agent session if the host discovers skills only at startup.

How It Works

1. Read the installed package's SKILL.md and its references; they define the

video routes, payload shapes, and review loop.

2. Use free, non-billable discovery first (beatra.models.list, task list) to

read current model cards, durations, resolutions, and credit estimates.

3. Show the user a cost card for exactly one paid call: tool, model, duration,

resolution, estimate, and which files will be uploaded. Wait for explicit

approval. Planning or "make the clip" is not approval.

4. Upload only files the user supplied and approved for this task, then submit

once with a stable client_request_id and poll the returned task.

5. Report the delivered artifact and billing.net_charged_credits, review the

clip with the user, and ask again before any further paid stage.

Examples

Free connection check (non-billable)

python3 "$HOME/.claude/skills/beatra-ai-video-studio/scripts/mcp_client.py" verify

One approved text-to-video call

After the user approved the cost card for this exact payload, replace the illustrative request ID once with a fresh unique ID and persist it for identical retries. Never reuse the sample ID for separate jobs:

printf '%s' '{"prompt":"A close product reveal with one slow push-in.","model":"auto","duration":5,"client_request_id":"req-7f3c2a"}' \
  | python3 "$HOME/.claude/skills/beatra-ai-video-studio/scripts/mcp_client.py" call beatra.videos.generate

If the response is lost, retry only with the same client_request_id and

identical arguments; never submit a replacement while the task is running.

Update

This pinned version cannot update itself: it has no code that downloads or

replaces package files. update only reports what the store or tool that

installed the copy offers; for a copy installed by the steps above it finds

no such record and says to update the way you installed it. See the version

notice under [Security & Safety Notes](#security--safety-notes).

To move to a newer version, repeat Steps 1 to 3 for that commit in a new

review directory, show the user the file-level changes against the installed

copy (for example git -C src diff --stat b7ab8ed <new-commit> -- skills/beatra-ai-video-studio),

and replace the directory only after approval. A version not listed in this

entry has not been reviewed here.

Uninstall

dest="$HOME/.claude/skills/beatra-ai-video-studio"
python3 "$dest/scripts/uninstall.py" --dry-run
python3 "$dest/scripts/uninstall.py"

Read the JSON decision. disconnected means this was the last Beatra skill on

the device: the token was revoked (when revoked is true) and the files

credentials.json, installation.json, host.json, skills.json,

network.json, balance-holds.json, pending_authorization.json, and

.authorize.lock under ~/.beatra were removed. keep_connection means

another Beatra skill still uses the shared token, which stays.

revoke_retry means the server refused the revocation and nothing changed;

run it again shortly. The script never deletes the package directory: after

confirming the path it prints with the user, delete $dest.

uninstall.py does not remove ~/.beatra/updates/. When the decision is

disconnected and no other Beatra skill is installed, remove that directory

and then the empty ~/.beatra; otherwise leave them. A token that could not

be revoked expires after 15 days idle and can be revoked at once in the

Beatra Console under Agents.

Best Practices

• ✅ Keep one approval per paid call, per upload set, and per install step.
• ✅ Start with the shortest duration and lowest resolution the model admits.
• ✅ Report net charged credits from the terminal task, not the estimate.
• ❌ Do not replace the installed copy with an unreviewed version silently.
• ❌ Do not print, paste, or move the token out of ~/.beatra/credentials.json.
• ❌ Do not retry a paid call with a new request ID after an uncertain response.

Before publication, inspect the complete clip for continuity, temporal artifacts, source likeness/brand drift, unsafe or deceptive detail

… (nội dung đầy đủ có trong gói tải về)