← Back to Skills Marketplace
65
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install social-caption
Description
add social media video into captioned social videos with this skill. Works with MP4, MOV, WebM, AVI files up to 500MB. TikTok and Instagram creators use it f...
Usage Guidance
Before installing, understand that this skill uploads your video files to a third-party service (mega-api-prod.nemovideo.ai) and will create or use an API token (NEMO_TOKEN). Ask the publisher to clarify (1) whether session tokens or credentials are written to disk and exactly where (the SKILL.md mentions ~/.config/nemovideo/ but registry metadata did not), (2) how long uploads and generated media are retained and whether they are shared internally, and (3) why the agent must auto-detect the install path (what filesystem reads are required). If you plan to process sensitive videos, do not install until you confirm storage/retention policies and where tokens/sessions are saved. If you want to proceed, prefer temporary/ephemeral tokens and explicit user consent before writing anything to disk.
Capability Analysis
Type: OpenClaw Skill
Name: social-caption
Version: 1.0.0
The social-caption skill is a legitimate integration for the nemovideo.ai cloud service, designed to allow an AI agent to automate video captioning and editing. It provides detailed instructions for session management, file uploads, and rendering tasks via the mega-api-prod.nemovideo.ai backend. All identified behaviors, including the automatic acquisition of an anonymous NEMO_TOKEN and the uploading of media for remote GPU processing, are transparently documented and align strictly with the skill's stated purpose.
Capability Assessment
Purpose & Capability
The name/description (auto-captioning social videos) aligns with the endpoints and actions described (upload, SSE editing, render). Requested credential NEMO_TOKEN is appropriate for an API-backed service. However, the SKILL.md frontmatter lists a config path (~/.config/nemovideo/) while registry metadata earlier reported no required config paths — that mismatch is unexplained.
Instruction Scope
Instructions are mostly within scope: upload user files, start sessions, stream SSE, poll render status, and return download URLs. The skill also instructs auto-creating an anonymous token if NEMO_TOKEN is absent, and to include specific attribution headers on every request. It asks to 'auto-detect' platform from the install path (which implies reading filesystem/install location). None of this is inherently out-of-scope, but the guidance about storing session_id and the requirement to infer install path are underspecified and could lead to the agent reading/writing config or install paths without clear user consent.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — minimal file-system/install risk. Network calls to a named API host are expected for the described functionality.
Credentials
Only a single credential (NEMO_TOKEN) is declared, which is appropriate. The skill will auto-request an anonymous token if none is present, which is consistent. Still, the frontmatter/config-path hint suggests the skill may persist tokens or session state on disk (e.g., ~/.config/nemovideo/), and the registry metadata does not declare that — this is a proportionality/visibility concern.
Persistence & Privilege
always:false and autonomous invocation are normal. The concern is that SKILL.md explicitly tells the agent to 'store the returned session_id' and frontmatter references a user config path. It's unclear whether stored session/token data will be ephemeral in agent memory or written to ~/.config/nemovideo/, and the registry metadata conflictingly declared no config paths. Persistent storage of tokens or session IDs without explicit user consent increases retention and exfiltration risk.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install social-caption - After installation, invoke the skill by name or use
/social-caption - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Social Caption 1.0.0 — initial release
- Add captions to social videos (MP4, MOV, WebM, AVI up to 500MB) with GPU-accelerated cloud processing.
- Automatic setup: acquire free NEMO_TOKEN and session seamlessly at first run.
- Supports TikTok, Instagram, and vertical 1080p exports with synced AI captions.
- Simple commands: upload, add/edit captions, preview timeline, check credits, export in MP4.
- Fast edits — typical processing takes 20–40 seconds per short video.
- Clear error handling and instructions mapped to backend workflows.
Metadata
Frequently Asked Questions
What is Social Caption?
add social media video into captioned social videos with this skill. Works with MP4, MOV, WebM, AVI files up to 500MB. TikTok and Instagram creators use it f... It is an AI Agent Skill for Claude Code / OpenClaw, with 65 downloads so far.
How do I install Social Caption?
Run "/install social-caption" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Social Caption free?
Yes, Social Caption is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Social Caption support?
Social Caption is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Social Caption?
It is built and maintained by tk8544-b (@tk8544-b); the current version is v1.0.0.
More Skills