Conversation Summary

Generate summaries for conversation content. Helps users quickly get a summary of their chat history with support for incremental updates.

Security Scan

The skill instructs the agent to POST full conversation content to an external third‑party API (iautomark.sdm.qq.com) without declaring credentials, privacy guidance, or provenance — this is a potential data‑exfiltration/privacy risk and is incoherent with the lack of declared env/config requirements.

Purpose & Capability

Generating summaries by calling a summary API is coherent with the skill's stated purpose. However, the API endpoint is an external Tencent/qq.com host with no homepage or author provenance provided; the SKILL.md does not explain ownership, privacy practices, or why no auth is needed.

Instruction Scope

Runtime instructions explicitly tell the agent to send the complete chatList (conversation history) to https://iautomark.sdm.qq.com/assistant-analyse/... . There is no guidance on minimization, consent, or redaction of sensitive content, and no note that data will leave the user's environment.

Install Mechanism

Instruction-only skill with no install spec or code files; this is low risk from an installation/execution standpoint.

Credentials

requires.env lists no credentials, yet the API call may reasonably require authentication or at least documentation of data handling. The absence of any declared API key or privacy/auth guidance is disproportionate given the skill sends potentially sensitive conversation data to a third party.

Persistence & Privilege

The skill does not request always:true, does not modify other skills, and does not request persistent system privileges.

What to consider before installing

This skill will POST your chat history to an external endpoint (iautomark.sdm.qq.com) whenever invoked. Before installing or using it: 1) Verify who operates that endpoint and read their privacy/data retention policy — do not send sensitive or regulated data until you confirm it's acceptable. 2) Ask the author whether the API requires authentication and why no API key/env var is declared. 3) Prefer a variant that performs summarization locally or on a verified trusted service. 4) Test with non-sensitive sample conversations first, and monitor outbound network traffic. If the author cannot provide ownership and data‑handling details, treat the skill as risky and avoid using it with private conversations.

A skill that generates summaries for conversation content. Call the summary API to create concise overviews of chat histories.

What This Skill Does

• Generates summaries for conversation content
• Supports incremental updates with previous summary context
• Returns structured JSON response with the summary

When to Use This Skill

Activate this skill when the user:

• Asks for a summary of the conversation
• Wants to know what was discussed
• Needs a recap of the chat history
• Requests to summarize messages

Trigger phrases:

• "Summarize this conversation"
• "What did we talk about?"
• "Give me a summary"
• "Recap our discussion"
• "总结一下对话"
• "帮我生成摘要"

How to Call the API

Use the following curl command to call the summary API:

curl -X POST "https://iautomark.sdm.qq.com/assistant-analyse/v1/assistant/poc/summary/trigger" \
  -H "Content-Type: application/json" \
  -d '{
    "chatList": "<JSON formatted conversation list>",
    "historySummary": "<previous summary for incremental update, optional>"
  }'

Parameters

Parameter	Type	Required	Description
chatList	string	Yes	JSON formatted conversation content
historySummary	string	No	Previous summary for incremental update

chatList Format Example

[
  {"role": "user", "content": "How is the weather today?"},
  {"role": "assistant", "content": "It is sunny, 25 degrees."}
]

Response

The API returns JSON with:

• code: Status code, 0 means success
• message: Status message
• data.summary: Generated conversation summary

Error Handling

• If the API returns a non-zero code, report the error message to the user
• If the request fails, check network connectivity
• Ensure chatList is valid JSON format before calling