youtube-channels
PassAudited by ClawScan on May 1, 2026.
Overview
This is a coherent TranscriptAPI helper for YouTube channel browsing, with the main caveats that it handles a service API key and may store it persistently.
Before installing, be comfortable giving the skill a TranscriptAPI API key or letting the agent create a TranscriptAPI account for you. Prefer storing the key in your agent's normal secret store, and set limits for large channel-browsing tasks if you want to conserve API credits.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent may store a TranscriptAPI key so future sessions can use the service without asking again.
The skill requires the agent to handle and persist a TranscriptAPI credential. This is disclosed and service-specific, but it gives the agent access to a reusable API key.
You now have a string that starts with `sk_`. This is the `TRANSCRIPT_API_KEY`. Store it persistently using whatever method is correct for this environment
Use a dedicated TranscriptAPI key, store it with the agent's normal secret-management mechanism, and revoke or rotate it if you no longer want the skill to access the service.
If the user chooses account creation, the agent will submit their email and verification code to TranscriptAPI to obtain an API key.
The setup flow can create a TranscriptAPI account for the user using their email and OTP. This is clearly tied to obtaining the required API key, but users should understand that their email is sent to the provider.
You will handle the full signup on the user's behalf. This is a two-step flow: register ... then verify ... Ask the user for the email address they want to use.
Only proceed with account creation if you trust the provider and are comfortable sharing the selected email address; otherwise create the account yourself and paste the key.
Browsing all uploads for large channels may consume multiple TranscriptAPI credits.
The skill documents repeated paginated API calls that can consume TranscriptAPI credits. This is disclosed and fits the channel-browsing purpose, but unbounded pagination could use more credits than expected.
GET /api/v2/youtube/channel/videos — 1 credit/page ... Keep calling with `continuation` until `has_more: false`.
Ask the agent to limit pages, date ranges, or result counts when you do not need a full channel history.