Investigation First
v1.0.0触发：当你准备下判断、做决策或提出建议，但事实、上下文或一手信息还不充分时优先调用；常见信号包括 unknowns、信息缺口、证据不足、领域陌生、需要先摸清现状。 English: Trigger before making claims or decisions when context is incomple...
⭐ 0· 85·1 current·1 all-time
by@arg0
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill's name and description (investigate before drawing conclusions) match the instructions and helper agent prompt: both explicitly direct systematic fact‑finding, reading sources, and running verification. There are no unrelated dependencies or credential requests.
Instruction Scope
The SKILL.md and investigation-agent prompt direct the agent to 'use all available tools', read relevant files and code, view history (git log/blame), and run code/tests. This is coherent with investigation tasks but means the agent may access local repository files, logs, and execute code to verify behavior — users should be aware the skill's operating model expects access to project/workspace artifacts.
Install Mechanism
No install spec and no code files with executable install steps — instruction-only skill. Nothing is downloaded or written to disk by the skill package itself.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. There are no disproportionate secret requests.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request elevated or persistent platform privileges and does not modify other skills or system-wide settings.
Assessment
This skill is coherent and low-risk as a bundle of instructions: it only provides guidance for performing investigations and does not ship code or request secrets. However, it explicitly instructs agents to read local files, inspect git history, and run code/tests when investigating — so only enable or invoke it in agents/environments where you are comfortable allowing those actions against your workspace or repositories. If you want to restrict execution, limit the agent's runtime permissions or review which files the agent can access before use.Like a lobster shell, security has layers — review code before you run it.
latestvk9704c2d550rm4pva3t1nyakkn83r6t2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.