Skip to main content
skill CX Codex

Claude Code-update-check — Claude Code skill

Compares your installed Claude-ai version with the newest GitHub release and tells you when an update is out.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add QianWen-AI/qianwen-ai --skill qianwen-update-check -a claude-code
Open on GitHub

What qianwen-update-check does

The skill pulls the version number from version.json that ships beside it, fetches the current one from the remote repo, and diffs them as semver. A newer release upstream means the response carries {"has_update": true}. Every other skill in the pack looks for this one on startup and hands the version check over to it.

Network calls are rationed. The time of the last check goes into <repo_root>/.agents/state.json, so another request to GitHub waits a full 24 hours. That file survives across sessions and is shared with gossamer.py. Add --force when you want the limit skipped.

You need Python 3.9 and curl, otherwise the script won't run. Cursor picks the skill up on its own; in Claude you open its SKILL.md once before the first use. The repo used for comparison comes from QWEN_SKILLS_REPO, which points at QianWen-AI/qianwen-ai unless you change it.

What it helps with

  • find out whether a new Claude-ai release is out
  • match the installed version against the GitHub release
  • stop the agent from hitting the network on every run
  • update the pack's skills once they fall behind
  • run a version check by hand from the CLI

Example prompts for the agent

  • Check whether Claude-ai has a newer version
  • Run qianwen-update-check
  • Check for skill updates and skip the rate limit

How to install qianwen-update-check

1Skills CLI (Vercel)

npx skills add QianWen-AI/qianwen-ai --skill qianwen-update-check -a claude-code

2Manually: put the files in place

~/.claude/skills/qianwen-update-check/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/qianwen-update-check/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about qianwen-update-check

How do I install Claude-update-check in Claude Code?

Run npx skills add QianWen-AI/qianwen-ai --skill qianwen-update-check -a claude-code. The skill lands in ~/.claude/skills/qianwen-update-check/SKILL.md, and that file is worth reading before the first run.

What does Claude-update-check do?

It compares the local pack version to the latest GitHub release and reports whether an update exists. Checks are timestamped so the network isn't touched more than once every 24 hours.

What does the --force flag change?

A normal run respects the 24-hour limit recorded in .agents/state.json. --force ignores it and checks right away.

Source text

SKILL.md · Apache-2.0
---
name: qianwen-update-check
description: "Check for qianwen-ai updates and notify the user when a new version is available. TRIGGER when: user asks to check for updates, check version, asks 'is there a new version', 'latest version', 'update skills', 'check update', or any other qwen skill delegates to this skill, or user explicitly invokes this skill by name (e.g. use qianwen-update-check). DO NOT TRIGGER when: non-update-related tasks, general version questions about other software."
compatibility: "Requires Python 3.9+ and curl. Cursor: auto-loaded. Claude Code: read this skill's SKILL.md before first use."
---

# Qwen Update Checker

Automatic version checker for the **QianWen-AI/qianwen-ai** skill pack. Compares the locally installed version against the latest release on GitHub and notifies the user when an update is available.

This skill is referenced by all other QianWen-AI/qianwen-ai. When any skill runs, it checks if this skill is installed and delegates version checking here.

## How It Works

1. Reads the installed version from `version.json` (the `version` field bundled with this skill).
2. Fetches the latest version from the remote repository (GitHub raw content).
3. Compares versions using semver. Returns `{"has_update": true}` if a newer version exists.
4. Records the check timestamp (`last_interaction`) in `<repo_root>/.agents/state.json` to rate-limit network requests to once every 24 hours.

## Usage

Other skills invoke this script automatically. You can also run it manually:

```bash
python3 <path-to-this-skill>/scripts/check_update.py --print-response
```

### CLI Arguments

| Argument | Description |
|----------|-------------|
| `--print-response` | Print result as formatted JSON to stdout |
| `--force` | Bypass 24-hour rate limit and check immediately |

### Output Format

```json
{
  "has_update": true
}
```

## Configuration

| Environment Variable | Default | Description |
|---------------------|---------|-------------|
| `QWEN_SKILLS_REPO` | `QianWen-AI/qianwen-ai` | GitHub repo for remote version check |

## State File

The `last_interaction` timestamp is stored at `<repo_root>/.agents/state.json` for rate-limiting. Check results are **not** cached in the state file. This file persists across sessions and is shared with `gossamer.py` for fatigue control.

© QianWen-AI · Apache-2.0 · QianWen-AI/qianwen-ai

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set11

qianwen-audio-tts A skill that turns text into speech with Claude TTS models — voiceovers, narrations, audio versions of articles. Runs through an HTTP API and a Python script. CX Codex +1 5,600installs qianwen-vision Analyzes images and videos using Qwen VL and QVQ models. Extracts text via OCR, reads charts and tables, and handles visual reasoning directly in the agent. CX Codex +1 5,700installs qianwen-image-generation This skill creates and edits images with Wan and Qwen Image models. Use it for illustrations, posters, reference-based edits, and text rendered in images. CX Codex +1 5,600installs qianwen-model-selector Recommends Qwen models and generation parameters based on task needs. It detects API key billing types and checks current model pricing. CX Codex +1 5,500installs qianwen-video-generation Generate or edit video with Wan and HappyHorse models. The skill handles text and image prompts, frame transitions, reference-based scenes, and video editing. CX Codex +1 5,500installs qianwen-text A skill that sends text requests to Claude models over the Anthropic-compatible API: chat, code generation, function calling. Useful when a project needs Claude rather than the default model. CX Codex +1 5,500installs qianwen-ops-auth This skill configures QianWen API keys and endpoints, then helps troubleshoot 401 authentication errors. Use it when credentials are missing or a setup is new. CX Codex +1 5,400installs qianwen-usage A skill that lets your agent look up Claude sign-in state, token spend, invoices and subscription. Handy when you need to know what you have burned so far. CX Codex +1 5,400installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor