research Decision

对复杂问题进行联网调研，并基于高质量信源输出判断、建议、排查方向或下一步动作。适用于技术选型、方案对比、版本升级、兼容性判断、架构取舍、社区口碑调研、已知问题排查、疑难 bug 冲突分析，以及其他需要上网查证、多方比较、最后给出建议或方向的问题。优先进行中英文双语检索，重视官方文档、官方博客、GitHub iss...

This is an instruction-only research/triage skill that will make web queries and, when relevant, run lightweight local checks (version/dependency commands) to validate findings. It does not ask for credentials or install software. Before enabling: decide whether you are comfortable with the agent reading your local development environment (package lists, tool versions) and browsing the web; avoid entering secrets into prompts; review any links/results the agent returns before acting on them. If you need to prevent local commands, restrict the agent's execution rights or instruct it not to run commands.

Type: OpenClaw Skill Name: research-decision Version: 1.0.0 The `research-decision` skill bundle is designed to assist with technical research and troubleshooting by querying online sources and verifying the local environment. A specific instruction in `SKILL.md` directs the AI agent to autonomously execute shell commands (e.g., `npm list`, `pip list`, `--version`) to verify dependencies and environment states. While these actions are plausibly needed for the stated purpose of technical decision-making, the instruction to perform autonomous system-level checks constitutes a high-risk capability that warrants a suspicious classification under the provided security criteria.