Deep Research Report
v1.0.0根据用户提供的研究材料，生成结构完整、逻辑严密、观点清晰的正式深度研究报告，适用行业、公司、策略与政策分析。
⭐ 0· 92·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (深度研究报告) align with the included code and SKILL.md: both generate structured research reports from user-provided materials and save them to an Obsidian vault. There are no unrelated env vars, binaries, or external services required.
Instruction Scope
SKILL.md instructs automated triggering on specific Chinese keywords and specifies automatic saving to an Obsidian path. The included Python implements report generation and writes to a local workspace. This stays within the stated purpose, but the auto-trigger behavior and automatic file write are notable (may run/save without an explicit 'save' confirmation).
Install Mechanism
No install spec and no external downloads; the skill is instruction-only with a benign bundled script. Nothing is written to system locations beyond the skill's workspace path.
Credentials
No environment variables, credentials, or external config paths are requested. The code writes to a local path under the agent workspace but does not access secrets or other system configs.
Persistence & Privilege
always:false and normal model invocation settings. The skill can be invoked automatically based on keyword triggers (as declared); it does not request permanent system-wide privileges or modify other skills' configs.
Assessment
This skill appears coherent and limited in scope, but consider: 1) It will automatically trigger on messages containing the listed keywords and will save generated reports to /root/.openclaw/workspace/Obsidian-Vault/10_投资金融/12_行业研究/ (check that this path is appropriate and that sensitive material is acceptable to be written there). 2) If you want to avoid automatic saves, edit SKILL.md or the script to require explicit confirmation before writing files. 3) Review the bundled generate_report.py if you need different naming, location, or to remove the default '内部参考' confidentiality label. 4) No network calls or credentials are used by the skill as provided.Like a lobster shell, security has layers — review code before you run it.
latestvk9740x10b0pe6cgbdrc4ab5m018497vm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.