QQ Bot Channel Access

Trust Score 84/100

Manage QQ bot channel access: approve pairings, edit allowlists, and configure DM policy safely from a local terminal session.

triggers:approve pairingqq bot accessallowlistpair <code>dm policy

GitHub SKILL.md

What it does

QQ Bot Channel Access is a utility skill for managing access control for a QQ channel backed by a local JSON store. It lets an operator approve pairing codes, deny pending requests, add or remove allowlist entries, and change DM policy — all while enforcing safety rules (only act on terminal-invoked commands, never on upstream channel notifications).

When to use it

To approve a user pairing code received out-of-band
To deny or expire pending pairing entries
To add or remove OpenIDs from the allowlist
To change DM policy (pairing, allowlist, disabled) from a trusted terminal session

What's included

Scripts: none detected (has_scripts=false)
References: none detected (has_references=false)
Instructions: Detailed dispatch rules for commands (status, pair <code>, deny <code>, allow <openid>, remove <openid>, policy <mode>), state shape for access.json, and implementation notes emphasizing read-before-write and safe operation.

Compatible agents

Designed for local agent integrations and CLI-driven agent runtimes (Copilot, Claude Code, Cursor). It assumes file-system access and is intended as a terminal-invoked operation rather than an automated downstream mutation.

Audit Summary

Manages QQ Bot channel access control via local JSON file edits — approve pairings, edit allowlists, set DM policy. No bundled scripts; the skill is pure SKILL.md instructions for the agent. Strongly security-conscious design with explicit prompt-injection guards and refusal to auto-approve pending entries. Well-structured dispatch on arguments with clear step-by-step instructions for each subcommand.

Watch Out

Operates on ~/.claude/channels/qqbot/access.json — requires QQ bot channel setup
Refuses channel-originated requests by design — user must type commands in terminal

Notes

Good example of a security-first skill design. The explicit prompt injection warnings and refusal to auto-pick pending entries are notable best practices.

Information

Repository: claude-qq-channel
Stars: 10
Installs: 0

Trust Score

Overall84

Security93

Code Quality78

Architecture72

Usefulness42

Related Skills

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

TradeOS

Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Tmux Bridge

Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.

Java 25 & Spring Boot 4 Code Reviewer

Run focused, evidence-based code reviews for Java 25 and Spring Boot 4 projects — migration risks, architecture boundaries, null-safety (JSpecify), security, an

ArcKit — French Public Procurement (fr-marche-public)

Generates French public procurement (Dossier de Consultation des Entreprises) drafts aligned with the Code de la Commande Publique, UGAP frameworks, and DINUM d

SourceSage CLI

Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.

Nit (Nitter CLI)

Terminal client to browse tweets, view profiles, and search posts via Nitter instances without opening a browser.

Back to Skills