Research Cog
v1.0.13AI deep research powered by CellCog. Market research, competitive analysis, investment research, academic research, due diligence, literature reviews with ci...
⭐ 7· 4.9k·29 current·30 all-time
byCellCog@nitishgargiitd
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
The name/description align with the SKILL.md instructions: it delegates research tasks to the CellCog SDK and documents research modes, output formats, and prompts. Minor mismatch: registry metadata lists no dependencies, but SKILL.md metadata lists dependencies: [cellcog] and repeatedly instructs the user/agent to use the 'cellcog' SDK/skill. This implies the 'cellcog' integration must exist for full functionality.
Instruction Scope
All runtime instructions stay within the stated research purpose (how to call CellCog, chat modes, citation behavior, output formats). The instructions do not request unrelated files, system credentials, or to post data to unexpected endpoints. They do reference session keys and agent chat modes (normal for agent integrations).
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so nothing is written to disk or downloaded by the skill itself.
Credentials
The skill declares no required environment variables or credentials. The SKILL.md does reference a separate 'cellcog' dependency which may itself require API keys — verify that before use, but this skill does not directly request secrets.
Persistence & Privilege
The skill does not request always:true and uses default agent invocation semantics. It does reference notify_session_key usage for OpenClaw 'fire-and-forget' calls, which is normal for agent integrations.
Assessment
This skill appears internally consistent and does what it says: it is a front-end that instructs agents how to call the CellCog research SDK. Before installing, verify that the separate 'cellcog' SDK/skill or package is available and review its required credentials, pricing/credits (the SKILL.md mentions costs for 'agent team max'), and privacy/data-handling policies at https://cellcog.ai. Because citations are not automatic, explicitly request them when you need source links. If you plan to run high-stakes analyses, confirm where research data and prompts will be sent/stored and whether the CellCog integration requires API keys or account access.Like a lobster shell, security has layers — review code before you run it.
latestvk97aa3e2dvw0e73r30nx7h9ehn84v448
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔬 Clawdis
OSmacOS · Linux · Windows
