WeryAI video tool — upscaler

Upscale an existing HTTPS video via WeryAI (video-upscaler). Use when the user wants higher resolution output, not text-to-video.

Security Scan

The skill's code, runtime instructions, and requested environment variable align with its stated purpose (upscaling an HTTPS video via WeryAI) and there are no disproportionate installs, extra credentials, or unexpected endpoints.

Purpose & Capability

Name and description claim an upscaler; the script implements an /v1/generation/video-upscaler endpoint call to https://api.weryai.com and requires only WERYAI_API_KEY and Node.js — these are appropriate and expected for the stated purpose.

Instruction Scope

SKILL.md and the CLI usage limit inputs to a public https:// video_url and optional resolution; the script validates https URLs, reads only WERYAI_API_KEY, and documents a mandatory pre-submit confirmation for paid runs. The instructions do not request reading local files or unrelated credentials.

Install Mechanism

No install spec (instruction-only invocation plus a single JS script). Required binary is only node (Node >=18 for built-in fetch). No downloads or archive extraction are present in the package.

Credentials

Only WERYAI_API_KEY is declared and used (getApiKey reads process.env.WERYAI_API_KEY). No other env vars or credentials are required or referenced in the script. The primaryEnv is proportionate to the service integration.

Persistence & Privilege

always is false; the skill does not request permanent presence or modify other skills or system-wide settings. It does network calls to the documented API endpoint, which is expected for this workflow.

Assessment

This package appears to do exactly what it says: call WeryAI's video-upscaler for a public HTTPS video using your WERYAI_API_KEY. Before running: (1) confirm the video URL and desired resolution with the user (SKILL.md already mandates that for paid runs), (2) keep your WERYAI_API_KEY secret and avoid writing it to disk, (3) ensure you trust https://api.weryai.com and your API key’s permissions/ billing impact (this is a paid workflow), (4) run the CLI from the skill root and avoid running any sibling scripts you didn't inspect, and (5) use --dry-run first to validate JSON. If you want higher assurance, review the full script (scripts/video_upscaler.js) locally to confirm there are no additional hidden endpoints or behaviors.

This skill is self-contained: it documents and runs only the upscaler workflow on an existing video given by URL. It is not text-to-video or image-to-video generation from scratch.

Entry script: scripts/video_upscaler.js (alongside this SKILL.md).

Runtime: WERYAI_API_KEY, Node.js 18+.

Inputs: video_url must be a public https:// URL. This script does not read local files and does not perform upload-file flows.

What this package ships (verify before trust)

Canonical layout for this skill only:

• SKILL.md, eval.yaml
• scripts/video_upscaler.js (the only runnable script in scope)

If your copy also contains scripts/video_gen.js, scripts/video_toolkits.js, references/WERYAI_VIDEO_API.md, or other CLIs, those files are not part of this skill’s contract — they may come from another repo sync or an over-broad install. Do not run them when you only want upscaler; remove them or reinstall from a clean source. Inspect what you run: node scripts/video_upscaler.js spec.

Other tools (multi-endpoint CLIs, local-file upload to growth/upload-file APIs, extra environment variables in those CLIs) are out of scope for this package. This skill’s script uses only WERYAI_API_KEY and public https:// URLs.

API surface (this tool only)

• Required: video_url (public https:// URL)
• Optional: resolution — 1080p, 2k, 4k
• Default: resolution=1080p

From this skill root, run node scripts/video_upscaler.js spec to print the full tool schema (endpoint, required fields, defaults, enums) as JSON.

Pre-submit gate (mandatory)

Do not run submit / wait until the user explicitly confirms the video URL and any non-default resolution. Paid runs are not idempotent.

Workflow

Prefer --dry-run to validate JSON. Use wait to submit and poll until the task finishes; use submit only when the user wants a task_id without blocking, then status for later checks. Share final URLs as Markdown links [Video](https://…).

CLI

From this skill root:

node scripts/video_upscaler.js wait \
  --json '{"video_url":"https://example.com/video.mp4"}'

node scripts/video_upscaler.js submit \
  --json '{"video_url":"https://example.com/video.mp4","resolution":"1080p"}'

node scripts/video_upscaler.js status --task-id <task-id>

Dry-run:

node scripts/video_upscaler.js wait \
  --json '{"video_url":"https://example.com/video.mp4"}' \
  --dry-run

Security

Never write WERYAI_API_KEY into files. Keep only WERYAI_API_KEY set for this workflow; do not rely on undocumented env vars in sibling scripts if any were mistakenly present. The in-scope script reads only WERYAI_API_KEY (no other env keys). video_upscaler.js accepts only https:// media URLs (no disk read / no upload-file). Base URL and poll intervals are constants in the script, not env-driven.

Do not pass local filesystem paths or run tools that accept them unless you have explicitly reviewed and consented to their upload behavior — that is never required for this skill.

Out of scope

• Global style transfer presets (different tool)
• New video generation from text only

References

• WeryAI llms.txt