Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/citedy/adclawnpx agentmods add skills/citedy/adclaw/citedy-video-shortsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/citedy/adclaw/citedy-video-shorts)<a href="https://agentmods.dev/skills/citedy/adclaw/citedy-video-shorts"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/citedy-video-shorts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/citedy/adclaw/citedy-video-shorts"><img src="https://agentmods.dev/badge/skills/citedy/adclaw/citedy-video-shorts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 658 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 400 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 402 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 404 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 405 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 481 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 485 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.05939 |
| Opus 5 | $0.00028 | $0.02969 |
| Sonnet 5 | $0.00011 | $0.01188 |
| Haiku 4.5 | $0.00006 | $0.00594 |
Grade A, and why
citedy-video-shorts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Video Shorts — Skill Instructions
You are now connected to Citedy — an AI platform for SEO content automation and video short generation. Base URL: https://www.citedy.com
Overview
This skill lets you generate and publish branded AI avatar lip-sync video shorts to Instagram Reels and YouTube Shorts — directly from a topic or product description. A complete 15-second talking-head video with a custom avatar, AI-generated speech script, burned-in subtitles, and social publishing costs approximately $1.99 (199 credits). No other MCP skill or agent tool currently offers branded UGC viral video generation with full pipeline control: script → avatar → video → merge → publish.
When to Use
Activate this skill when the user says something like:
- "Create a TikTok video about [topic/product]"
- "Make a short video for Instagram Reels"
- "Generate an AI UGC viral video for YouTube Shorts"
- "I need a 15-second promo video"
- "Make a talking-head video about [subject]"
- "Create video content for social media"
- "Generate a short clip with subtitles"
- "Make a video ad for my product"
- "I want a video shorts series about [topic]"
- "Publish my video to Instagram Reels"
- "Create and post a short to my connected accounts"
- "Generate a video and publish it to YouTube Shorts"
Instructions
Setup (run once)
If you don't have a saved API key for Citedy, run this flow:
1. Register
Preferred: run the included registration script:
node scripts/register.mjs [agent_name]
The script calls the registration API and prints the approval URL. If agent_name is omitted, it defaults to agent-<hostname>.
Alternative: call the API directly:
POST https://www.citedy.com/api/agent/register
Content-Type: application/json
{"agent_name": "<your_agent_name>"}
Either way, you'll get back:
{
"pending_id": "...",
"approval_url": "https://www.citedy.com/approve-agent/...",
"expires_in": 3600
}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 679 lines · 56 tokens per session scan A 02bc4fbfeb49
citedy-video-shorts is a skill published in the GitHub repository citedy/adclaw (36 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 5,939 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
citedy-video-shorts
Stateful MCP-first producer for branded AI UGC shorts. Generates scripts, reuses brand/avatar memory, renders vertical talking-head videos, and optionally publishes to Instagram Reels and YouTube Shorts.
tiktok-script-writer
Write short-form video scripts for TikTok, Instagram Reels, and YouTube Shorts that promote affiliate products with strong hooks, demos, and CTAs. Use this skill when the user asks about TikTok scripts, Reels scripts, Shorts scripts, short-form video for affiliate marketing, or says "write a TikTok for X", "script a…
tiktok-script-writer
Write short-form video scripts for TikTok, Instagram Reels, and YouTube Shorts that promote affiliate products with strong hooks, demos, and CTAs. Use this skill when the user asks about TikTok scripts, Reels scripts, Shorts scripts, short-form video for affiliate marketing, or says "write a TikTok for X", "script a…
vugola
Clip any YouTube or video URL into short-form viral clips using Vugola AI, then auto-schedule them to TikTok, Instagram, and YouTube Shorts. Use when someone says "clip this video", "clip and schedule", "make clips from this URL", or wants short-form content from a long video. Handles the full pipeline end-to-end …
create_profile_style_skill
A workflow for turning a person's video-editing habits into a reusable editing skill file. It examines choices such as pacing, storytelling, audio, subtitles, colour, transitions, and recurring editing rules.
subtitle_imitation_skill
A video-writing workflow that rewrites a script to match the style of reference text supplied by the user. It uses the footage analysis and reference sample while keeping the script tied to what is actually shown.