What is remote-input?

A download-and-routing skill for remote sources such as arXiv papers, YouTube videos, and Bilibili videos. It saves the content locally and sends it to the appropriate grounding skill.

Use it when the input is a supported URL instead of a local file: arXiv links become PDFs, while YouTube and Bilibili links become video files for further processing.

It removes the manual work of downloading online material and choosing the next processing step. The downstream workflow can then work from a local file.

How gaotiexinqu/OneResearchClaw configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to gaotiexinqu/OneResearchClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gaotiexinqu/OneResearchClaw/main/.cursor/skills/remote-input/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/gaotiexinqu/OneResearchClaw

Made for: Cursor.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/remote-input/github.svg)](https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/remote-input)

Your own site

<a href="https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/remote-input"><img src="https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/remote-input/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/remote-input"><img src="https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/remote-input.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,271 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

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 →

high YARA Match · line 167
YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00043	$0.03271
Opus 5.5	$0.00017	$0.01308
Sonnet 5.5	$0.00009	$0.00654
Haiku 4.5	$0.00004	$0.00327

Measured 2mo ago against content hash a101c8aa21b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

remote-input 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/download_arxiv.py, scripts/download_video.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.cursor/skills/remote-input/SKILL.md · 395 lines

How it starts

The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Remote Input

Download remote content (arxiv papers, YouTube videos, Bilibili videos) to local storage and seamlessly integrate into the downstream pipeline.

What This Skill Does

This skill acts as a pre-processing layer for the pipeline:

Detects URL type (arxiv, YouTube, or Bilibili)
Downloads content to data/raw_inputs/remote/
Returns the local file path
Triggers the next pipeline stage

Supported URL Types

URL Type	Download Target	Local Extension	Downstream Routing
`https://arxiv.org/abs/...`	PDF	`.pdf`	`document-grounding`
`https://arxiv.org/pdf/...`	PDF	`.pdf`	`document-grounding`
`https://www.youtube.com/watch?v=...`	Video	`.mp4`/`.mkv`	`meeting-video-grounding`
`https://youtu.be/...`	Video	`.mp4`/`.mkv`	`meeting-video-grounding`
`https://www.youtube.com/shorts/...`	Video	`.mp4`/`.mkv`	`meeting-video-grounding`
`https://bilibili.com/video/BV...`	Video	`.mp4`/`.mkv`	`meeting-video-grounding`
`https://www.bilibili.com/video/av...`	Video	`.mp4`/`.mkv`	`meeting-video-grounding`
`https://b23.tv/...`	Video	`.mp4`/`.mkv`	`meeting-video-grounding`

Note on merge failure: When video download produces separate video and audio files (merge failure), the downloader returns merge_failed: true with audio_path pointing to the audio file. The downstream routing switches to meeting-audio-grounding instead of meeting-video-grounding.

Directory Structure

data/raw_inputs/remote/
├── arxiv/
│   └── <paper_id>.pdf          # e.g., 2301.07041.pdf
├── youtube/
│   └── <video_title>.mp4       # e.g., "Introduction to Transformers.mp4"
├── bilibili/
│   └── <video_title>.mp4       # e.g., "教程视频.mp4"
└── metadata/
    └── <ground_id>.json        # Download metadata

Workflow

Step 1. Parse Input URL

Detect the URL type:

If URL contains "arxiv.org":
    → Use arxiv downloader
    → Ground ID = arxiv paper ID (e.g., "2301.07041")

If URL contains "youtube.com" or "youtu.be":
    → Use YouTube downloader
    → Ground ID = sanitized video title or video ID

If URL contains "bilibili.com" or "b23.tv":
    → Use Bilibili downloader
    → Ground ID = BV ID (e.g., "BV1xx411c7JZ")

Read the full file on GitHub · 395 lines

Files

What ships with it

2 files 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.

Changes

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.

2mo ago First seen · 395 lines · 43 tokens per session scan A a101c8aa21b1

Subscribe to this mod's changes

remote-input is a skill published in the GitHub repository gaotiexinqu/OneResearchClaw (451 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 3,271 once invoked, about $0.0002 per session on Opus 5.5. 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.

Research agentic-systems ai-agents ai-for-science autonomous-research cursor-ai llm-agents

remote-input next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
remote-inputgaotiexinqu/OneResearchClaw	Skill	451	6mo ago	MIT	A	43	Cursor
quantum-qiskitaiming-lab/AutoResearchClaw	Skill	15k	2mo ago	MIT	A	102	Claude Code, Codex
fba-simulatoraiming-lab/AutoResearchClaw	Skill	15k	2mo ago	MIT	A	69	Claude Code, Codex
flux-analyzeraiming-lab/AutoResearchClaw	Skill	15k	2mo ago	MIT	A	44	Claude Code, Codex
gsmm-validatoraiming-lab/AutoResearchClaw	Skill	15k	2mo ago	MIT	A	52	Claude Code, Codex
metabolic-study-planneraiming-lab/AutoResearchClaw	Skill	15k	2mo ago	MIT	A	69	Claude Code, Codex
stat-research-orchestratoraiming-lab/AutoResearchClaw	Skill	15k	2mo ago	MIT	A	36	Claude Code, Codex

OneResearchClaw: Skill for Cursor