Academic Deep Research Pro
v1.0.0Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per t...
⭐ 1· 819·6 current·6 all-time
by@nancliu
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill declares it is self-contained and 'works offline / no API keys', yet its runtime instructions explicitly require platform web access via web_search and web_fetch and use sessions_spawn for parallel sub-agents. This is coherent for a web-based research skill, but the README wording ('works offline') is misleading and should be clarified. Otherwise, required capabilities (search, fetch, spawn sessions) match the stated purpose of exhaustive research.
Instruction Scope
SKILL.md restricts activity to web_search, web_fetch, and sessions_spawn and mandates analysis between tool calls and explicit user stop points; it does not instruct reading local files, environment variables, or contacting unrelated endpoints. Note: web_fetch/web_search will make many external network requests (count=20 per query) and sessions_spawn spawns sub-agents that will also fetch data — this increases surface area for retrieved content and should be considered when researching sensitive or regulated data (e.g., PHI).
Install Mechanism
Instruction-only skill with no install spec and no code files. No binaries, downloads, or package installs are declared. This is the lowest-risk install profile.
Credentials
The skill requests no environment variables, no credentials, and no config paths. That is proportionate for a research tool that uses platform-provided web_search/web_fetch capabilities.
Persistence & Privilege
The skill does not request always:true and uses default invocation settings. It can be invoked autonomously (platform default), and it uses sessions_spawn for parallel work — reasonable for its purpose. There is no indication it modifies other skills or system-wide settings.
Assessment
This skill appears to do what it says: disciplined, multi-cycle web research using OpenClaw native tools and explicit user checkpoints. Before installing or using it, consider the following: (1) Clarify the README claim that it 'works offline' — in practice it uses web_search/web_fetch and will perform many external web requests; it does not require external API keys, but it is not truly offline. (2) If you plan to research sensitive or regulated material (PHI, proprietary code, non-public documents), verify your organization’s policies: web_fetching external sites can transmit query strings and retrieved content back into the agent and possibly logs. (3) sessions_spawn spawns parallel sub-agents that will also perform searches/fetches; confirm what permissions those sub-agents inherit and how their network activity is logged. (4) Expect high volume of web requests (many searches and fetches per theme); test first on non-sensitive topics to observe behavior and resource usage. (5) If you need absolute assurance about data jurisdiction or on-prem processing, validate vendor/platform documentation about where web_search/web_fetch endpoints operate and whether any content is retained. If these operational details are acceptable, the skill is coherent and proportionate to its stated purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk978mksh2m0jk1nf6zwsaffgdx83ckad
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔬 Clawdis