← Back to Skills Marketplace
158
Downloads
1
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install qinglong-skills
Description
Manage QingLong (青龙) panel via REST API — cron jobs, environment variables, scripts, dependencies, subscriptions, logs and system operations. Use this skill...
Usage Guidance
This skill appears to do exactly what it says: it calls your self-hosted QingLong panel using the panel URL and the client credentials you provide. Before installing or enabling it: 1) Only grant the minimum Open API scopes in QingLong (avoid full 'system' scope unless you need system-level actions). 2) Be aware that the script caches an auth token in $XDG_CACHE_HOME or $HOME/.cache/qinglong/token and that you must store the client secret somewhere (the README suggests openclaw.json); protect those files with appropriate filesystem permissions. 3) Review scripts/ql.sh locally (it’s included) so you’re comfortable with the exact API calls made. 4) If you will let an autonomous agent call skills, remember this skill can perform destructive/system operations on the panel (delete cron jobs, reset auth, run arbitrary commands) — require explicit confirmation before performing such actions. If any of those concerns are unacceptable, do not install or limit the app scopes/credentials you provide.
Capability Analysis
Type: OpenClaw Skill
Name: qinglong-skills
Version: 1.0.2
The skill bundle is a comprehensive CLI wrapper for the QingLong panel REST API, allowing users to manage tasks, environment variables, and system settings. While the script (`scripts/ql.sh`) includes high-risk capabilities such as remote command execution and authentication resets, these are standard features of the QingLong API and are clearly documented for the user's own panel management. No evidence of malicious intent, data exfiltration to external endpoints, or obfuscation was found.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description match the requested resources and behavior. Required binaries (curl, jq), required env vars (QINGLONG_URL, QINGLONG_CLIENT_ID, QINGLONG_CLIENT_SECRET), included API reference and a CLI wrapper script (scripts/ql.sh) are all appropriate and expected for a QingLong panel management skill.
Instruction Scope
SKILL.md limits runtime behavior to calling scripts/ql.sh against the user's QINGLONG_URL. The instructions instruct listing before changes and confirming destructive actions, which is appropriate. Note: the skill and script expose APIs that permit system-level operations (e.g., system command-run, auth reset), so callers should grant only the scopes they actually want the skill to exercise and confirm destructive/system actions before running them.
Install Mechanism
No install spec; skill is instruction-only with a bundled shell script. No third-party downloads or archive extraction. This is low-risk from an installation perspective, though the included script will be stored and executed on the host.
Credentials
Requested environment variables (panel URL, client id, client secret) are exactly what the QingLong Open API requires. The script also uses XDG_CACHE_HOME/HOME to store a token cache, which is expected. No unrelated credentials or extraneous env vars are requested.
Persistence & Privilege
always: false (normal). The skill writes a token cache file under $XDG_CACHE_HOME or $HOME/.cache/qinglong and recommends placing credentials into openclaw.json (user-managed). Those are expected behaviors, but users should be aware that credentials and tokens will be stored on-disk and that the skill can call system-level QingLong endpoints if the configured app has those scopes.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qinglong-skills - After installation, invoke the skill by name or use
/qinglong-skills - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Added explicit usage guidance in SKILL.md, including patterns for handling user requests and best practices before modifying resources.
- Added a "How to approach user requests" section with safety and workflow tips.
- Clarified security posture: skill only connects to user-provided, self-hosted QingLong panel.
- Moved installation and setup instructions to a new references/setup.md file and referenced it from SKILL.md.
- Improved troubleshooting section and reformatted quick reference commands for greater clarity.
- Minor metadata updates (added version, expanded trigger description) to assist with skill invocation.
v1.0.1
Refactor SKILL.md: separate OpenClaw/Claude Code setup, add ClawHub link, add npx install method
v1.0.0
Initial release: cron jobs, envs, scripts, deps, subscriptions, logs, system management. Supports OpenClaw and Claude Code CLI.
Metadata
Frequently Asked Questions
What is Qinglong Skills?
Manage QingLong (青龙) panel via REST API — cron jobs, environment variables, scripts, dependencies, subscriptions, logs and system operations. Use this skill... It is an AI Agent Skill for Claude Code / OpenClaw, with 158 downloads so far.
How do I install Qinglong Skills?
Run "/install qinglong-skills" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Qinglong Skills free?
Yes, Qinglong Skills is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Qinglong Skills support?
Qinglong Skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Qinglong Skills?
It is built and maintained by NNNNzs (@nnnnzs); the current version is v1.0.2.
More Skills