Loom

Loom — manage video recordings, transcripts, and folders via Developer API

Security Scan

The skill appears to implement a Loom API CLI and mostly matches its description, but the runtime script reads a workspace .env file (and the WORKSPACE env var) that SKILL.md doesn't declare, which is a proportionality/scope mismatch worth noting before install.

Purpose & Capability

Name/description, commands in SKILL.md, and the included Python script all align: the tool calls the Loom Developer API endpoints and requires a LOOM_ACCESS_TOKEN.

Instruction Scope

SKILL.md documents CLI operations against the Loom API only, but the script's get_env() will read a .env file under WORKSPACE (defaulting to ~/.openclaw/workspace/.env) to find LOOM_ACCESS_TOKEN. The README/metadata do not mention reading workspace files.

Install Mechanism

No install spec; this is an instruction-only skill with a small standalone Python script that uses only the standard library — low install risk.

Credentials

Declared requirement is a single LOOM_ACCESS_TOKEN (primary credential), which is appropriate. However, the script also reads the WORKSPACE environment variable (if present) and the .env file in that workspace directory to retrieve the token. That file may contain unrelated secrets; reading it is not declared in SKILL.md and increases the chance of accidental exposure of other variables.

Persistence & Privilege

No elevated privileges requested. always is false, the skill does not modify other skills or global agent config, and it does not request persistent installation.

What to consider before installing

This skill is a small CLI for the Loom Developer API and only needs LOOM_ACCESS_TOKEN. Before installing: (1) review the included scripts/loom.py (it is short and uses only stdlib); (2) be aware the script will look for LOOM_ACCESS_TOKEN in the environment or in a .env file under WORKSPACE (default ~/.openclaw/workspace/.env) — if that file contains other secrets, the script will read it (though it only extracts the named variable). If you keep other secrets in that .env, consider moving them or setting LOOM_ACCESS_TOKEN explicitly in the environment. Also limit the token's scope and rotate it if you become concerned. Overall the skill is coherent with its stated purpose, but the implicit .env file read is an undocumented behavior you should accept consciously before use.

Loom — manage video recordings, transcripts, and folders via Developer API

Requirements

Variable	Required	Description
LOOM_ACCESS_TOKEN	✅	Developer API access token

Quick Start

# List videos
python3 {{baseDir}}/scripts/loom.py videos --per_page <value>

# Get video
python3 {{baseDir}}/scripts/loom.py video-get id <value>

# Update video
python3 {{baseDir}}/scripts/loom.py video-update id <value> --title <value> --description <value>

# Delete video
python3 {{baseDir}}/scripts/loom.py video-delete id <value>

# Get transcript
python3 {{baseDir}}/scripts/loom.py video-transcript id <value>

# List comments
python3 {{baseDir}}/scripts/loom.py video-comments id <value>

# List folders
python3 {{baseDir}}/scripts/loom.py folders

# Get folder
python3 {{baseDir}}/scripts/loom.py folder-get id <value>

All Commands

Command	Description
videos	List videos
video-get	Get video
video-update	Update video
video-delete	Delete video
video-transcript	Get transcript
video-comments	List comments
folders	List folders
folder-get	Get folder
folder-videos	List folder videos
user	Get current user
members	List workspace members

Output Format

All commands output JSON by default. Add --human for readable formatted output.

python3 {{baseDir}}/scripts/loom.py <command> --human

Script Reference

Script	Description
{{baseDir}}/scripts/loom.py	Main CLI — all commands in one tool

Credits

Built by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.

📅 Need help setting up OpenClaw for your business? Book a free consultation