What makes QQBot Send notable?

1K downloads. Trust evidence available

How should QQBot Send be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

QQBot Send

Send local files, images, audio, video, and other media through QQBot end to end. Use when the user asks to send a file to QQ, send a desktop/downloads/local...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed Apr 21, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dhbns457gbvxk91djp930hx859wev:qqbot-send

Install using `clawhub skill install s17dhbns457gbvxk91djp930hx859wev:qqbot-send` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/zykkk-power/qqbot-send before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-zykkk-power-qqbot-send/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

7,337 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: qqbot-send
description: Send local files, images, audio, video, and other media through QQBot end to end. Use when the user asks to send a file to QQ, send a desktop/downloads/local absolute-path file, resend a local attachment, or when QQBot file sending should automatically stage the file into the QQ media relay directory and then deliver it with qqmedia tagging.
---

# QQBot Send

Use this skill for QQ file sending end to end.

## Core rule

When the user wants a file sent through QQ, complete the full send flow instead of only returning a path.

## Built-in staging flow

This skill includes the old `qqbot-local-media` behavior.

For local files that are not already in the QQ media relay directory:

1. Run:
   - `python scripts/stage_media.py <source_path>`
2. The script copies the file into:
   - `~/.openclaw/media/qqbot/`
3. Use the returned absolute path in:
   - `<qqmedia>absolute-path</qqmedia>`

## Decision flow

1. Identify the source.
   - If the source is a local absolute path outside the QQ media relay area, stage it first.
   - If the source is already inside the OpenClaw QQ media relay directory, use it directly.
   - If the source is an HTTP(S) URL, send it directly with `<qqmedia>...</qqmedia>`.
   - If the source is a local attachment path already provided in context and QQBot can send it directly, send it directly.

2. For local files that need staging, use the bundled script in this skill.

3. Then send with QQ rich media.
   - Use `<qqmedia>absolute-path-or-url</qqmedia>`
   - One file per tag.

## Default practical flow

For most local desktop/downloads/workspace-external files:

1. Stage into `~/.openclaw/media/qqbot/`
2. Send with `<qqmedia>...</qqmedia>`

## Size and path rules

- Absolute local paths only
- File size limit is 10 MB
- Preserve the original file extension
- Copy the file, do not modify the original
- Do not claim you cannot send local files when the path is readable and within the size limit

## Response behavior

- If the user asked to send the file, actually send it.
- Do not only explain the flow unless the user asked a conceptual question.
- If staging fails because the file does not exist, say that directly.
- If staging fails because the file is too large, say that directly.

## Examples

### Example 1: Desktop PDF
- User asks: send `C:\Users\name\Desktop\resume.pdf` to QQ
- Action:
  1. `python scripts/stage_media.py "C:\Users\name\Desktop\resume.pdf"`
  2. send `<qqmedia>staged-absolute-path</qqmedia>`

### Example 2: Already staged file
- User asks to send `C:\Users\name\.openclaw\media\qqbot\abc.pdf`
- Action:
  1. send `<qqmedia>C:\Users\name\.openclaw\media\qqbot\abc.pdf</qqmedia>` directly

### Example 3: URL image
- User asks to send an image URL to QQ
- Action:
  1. send `<qqmedia>https://example.com/image.png</qqmedia>` directly

## Notes

- Prefer completing the send in one turn.
- Use the bundled staging script whenever the file is local and not already staged.
- Use `<qqmedia>.

README.md

# qqbot-send

An OpenClaw skill for sending files through QQBot end to end.

It combines two responsibilities into one skill:

1. stage local files into the QQBot media relay directory
2. send the staged path with QQ rich-media tagging

## What this skill does

When a user asks to send a local file to QQ, this skill decides the safest path automatically.

### Local absolute-path file
For files like desktop files, downloads, and workspace-external files, the skill:

1. runs `python scripts/stage_media.py <source_path>`
2. copies the file into:
   - `~/.openclaw/media/qqbot/`
3. uses the returned path with:
   - `<qqmedia>...</qqmedia>`

### Already staged file
If the file is already inside the QQBot relay directory, it sends it directly.

### URL media
If the source is an HTTP(S) URL, it can be sent directly with `<qqmedia>...</qqmedia>`.

## Repository layout

```text
qqbot-send/
├─ SKILL.md
├─ README.md
├─ LICENSE
├─ .gitignore
└─ scripts/
   └─ stage_media.py
```

## Script behavior

The bundled script:

- accepts a single file path argument
- checks that the file exists
- rejects files larger than 10 MB
- preserves the file extension
- copies the file instead of changing the original
- writes to `~/.openclaw/media/qqbot/`
- prints the staged absolute path

## Example

```bash
python scripts/stage_media.py "C:\Users\zyk\Desktop\resume.pdf"
```

Example output:

```text
C:\Users\zyk\.openclaw\media\qqbot\9b0f3b80-19b2-410b-adfc-438d6028b93a.pdf
```

Then send:

```xml
<qqmedia>C:\Users\zyk\.openclaw\media\qqbot\9b0f3b80-19b2-410b-adfc-438d6028b93a.pdf</qqmedia>
```

## Notes

- This skill replaces the old split flow where staging and sending were handled by separate skills
- The final delivery format still uses QQBot rich-media tagging
- Staged media output is not part of this repository

_meta.json

{
  "ownerId": "kn73h1njdkpka5wxkgyrjpgb2d8586vm",
  "slug": "qqbot-send",
  "version": "1.0.0",
  "publishedAt": 1776780326383
}

skill-card.md

## Description:

Send local files, images, audio, video, and other media through QQBot end to end.

This skill is ready for commercial/non-commercial use.

## Publisher:

[zykkk-power](https://clawhub.ai/user/zykkk-power)

### License/Terms of Use:

MIT-0

## Use Case:

External users and developers use this skill to send user-requested local files or URL media through QQBot. It stages readable local files into the QQBot media relay directory when needed, then delivers them with QQ rich-media tagging.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Sensitive files could be sent to QQBot if the path or recipient is not confirmed.

Mitigation: Confirm the file path and intended recipient before sending sensitive files.

Risk: Staged file copies may remain in the local QQBot media relay directory after delivery.

Mitigation: Periodically clean ~/.openclaw/media/qqbot/ when retained staged copies are no longer needed.

## Reference(s):

- [QQBot Send ClawHub Page](https://clawhub.ai/zykkk-power/skills/qqbot-send)

## Skill Output:

**Output Type(s):** [text, shell commands, configuration, guidance]

**Output Format:** [Markdown with inline shell commands and QQ media tags]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Stages local files up to 10 MB into ~/.openclaw/media/qqbot/ and preserves the original file extension.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular