openclaw - 💡(How to fix) Fix [Feature Request] 自动检查 Skill 再处理链接,而不是默认使用浏览器 [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#61819Fetched 2026-04-08 02:54:05
View on GitHub
Comments
0
Participants
1
Timeline
0
Reactions
0
Participants
RAW_BUFFERClick to expand / collapse

问题描述

目前 AI 收到抖音、小红书等平台链接时,默认行为是使用浏览器打开页面内容,而不是先检查是否有对应的 Skill 可用。

这导致:

  1. 用户需要手动加指令「用 Skill 处理」才能触发正确的处理流程
  2. 没有 Skill 的平台才应该降级到浏览器,而不是默认浏览器

期望行为

AI 在收到任何链接时,应该:

  1. 先检查 available_skills 中是否有处理该平台链接的 Skill
  2. 若有 Skill → 调用 Skill 处理
  3. 若无 Skill → 降级到浏览器或 Tavily 等工具

使用场景

  • 抖音链接 → 应默认走 Skill 流程(当前需要手动说「用 Skill 处理」)
  • 小红书链接 → 同上

相关约定

用户已将此约定写入 MEMORY.md:

收到链接 → 用已安装的 skill 处理,不试网页端

但当前问题是:规则写在文件里,AI 不会自动检索和应用,而是走「下意识」的直接打开浏览器流程。

技术背景

这可能是 LLM agentic 执行的共同限制,而非某家模型的问题。可能的解决方向:

  • 在消息处理 pipeline 层面硬编码「收到链接 → 先查 Skill」的检查步骤
  • 将 Skill 检查从「可选检索」变为「强制前置步骤」

extent analysis

TL;DR

Modify the message processing pipeline to prioritize checking for available skills before defaulting to browser opening.

Guidance

  • Review the available_skills checking mechanism to ensure it is correctly integrated into the message processing pipeline.
  • Consider hardcoding a "check for skill" step before the default browser opening action to enforce the desired behavior.
  • Verify that the MEMORY.md conventions are properly applied and synced with the AI's decision-making process.
  • Investigate the possibility of elevating skill checking from an optional to a mandatory step in the processing pipeline.

Example

No specific code example can be provided without more context, but the solution likely involves modifying the pipeline to include a conditional check for available skills before proceeding with the default action.

Notes

The solution may require adjustments to the underlying LLM agentic execution framework, and careful consideration should be given to potential limitations and interactions with other system components.

Recommendation

Apply workaround: Modify the message processing pipeline to prioritize skill checking, as this approach directly addresses the described issue and aligns with the expected behavior outlined in the MEMORY.md conventions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING