QClaw

Summarize noisy WeChat group chats into decisions, action items, mentions, risks, and tracked keywords for OpenClaw workflows.

Security Scan

QClaw's requested inputs and runtime instructions match its description: it is an instruction-only chat-summarization skill that processes pasted WeChat group transcripts and does not request credentials or install anything.

Purpose & Capability

The name and description (WeChat group summarization, decisions, action items, keyword tracking) align with the skill's inputs and outputs. It requires only a pasted/exported chat log and optional keywords—no unrelated resources are requested.

Instruction Scope

SKILL.md and prompts restrict the agent to processing provided chat logs, extracting decisions/action items/keyword hits, and producing a structured summary. The instructions do not ask the agent to read system files, environment variables, or contact external endpoints.

Install Mechanism

No install spec and no code files are included (instruction-only). This is the lowest-risk model: nothing gets written to disk and there are no external installers or downloads.

Credentials

The skill declares no required environment variables, credentials, or config paths. There is no apparent need for secrets or external service access, which is proportional to the stated function.

Persistence & Privilege

always is false (normal). disable-model-invocation is false (agent may invoke autonomously), which is the platform default and not a problem by itself; the skill does not request persistent system privileges or modify other skills/configurations.

Assessment

QClaw appears internally consistent and low-risk: it only processes chat text you paste and asks for no credentials or installs. Before using, avoid pasting sensitive or legally privileged transcripts (redact personal data), don't use it for verbatim legal/compliance records, and verify anonymization if needed. Note the skill's source/homepage are missing—if provenance matters to you, prefer skills from known maintainers or ask the publisher for more information. If you are uncomfortable with autonomous invocation, disable model-initiated skill use in your agent settings.

QClaw is a WeChat group chat signal extraction skill.

Use this skill when the user wants to:

• summarize a WeChat group chat
• extract decisions and action items
• track keywords such as project names, clients, or deadlines
• identify direct or implicit mentions that may need attention
• detect conflict, urgency, or risk in busy group discussions

What this skill does

• compresses long group conversations into short, useful summaries
• separates signal from noise
• extracts decisions, tasks, blockers, and next steps
• highlights mentions of tracked keywords
• identifies messages that likely require the user's attention

How to use

Prerequisites

• OpenClaw installed
• A WeChat group chat log pasted as text, or exported as txt/json
• Optional tracked keywords supplied by the user

Accepted input

• plain text chat log
• JSON array of messages with timestamp, sender, and content
• copied chat transcript

Best output structure

1. Executive summary
2. Decisions made
3. Action items
4. Mentions and keyword hits
5. Risks / conflicts / urgency
6. Suggested follow-up

Privacy & Security

• Prefer anonymized or redacted chat logs when possible
• Do not retain chat content longer than needed for the current workflow
• Mark uncertainty clearly
• Never fabricate missing context

When NOT to use QClaw

• personal 1-on-1 chats
• groups with very few messages
• real-time alerting workflows
• legal or compliance workflows requiring verbatim records