Think Cog
v1.0.10AI brainstorming and strategic thinking powered by CellCog. Reasoning, problem-solving, ideation, strategic planning — then execution across every modality:...
⭐ 7· 2.7k·15 current·15 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
medium confidencePurpose & Capability
The name and description (brainstorming, strategic thinking, iterative conversation) match the SKILL.md instructions. The skill is instruction-only and delegates execution to the CellCog SDK (dependency listed), which is consistent with the claimed capabilities. The one minor mismatch: marketing language promises 'execution across every modality' but the skill provides no code or install to perform modality-specific actions itself — it expects the CellCog SDK/service to do that.
Instruction Scope
SKILL.md stays within the domain of collaborative thinking: it shows how to start and continue conversational sessions via the CellCog SDK, recommends chat_mode, and gives usage tips. It does not instruct the agent to read arbitrary host files, exfiltrate data, or access unrelated environment variables. It is conversational and scoped to the stated purpose.
Install Mechanism
There is no install spec and no code files (instruction-only), so nothing will be written to disk or fetched during install by this skill. This is a low-risk footprint and consistent with an SDK-dependent instruction skill.
Credentials
The skill declares no required environment variables or credentials, which is appropriate for an instruction-only wrapper. However, it relies on the CellCog SDK (dependency), and SKILL.md omits any guidance about authentication (API keys, tokens, account setup). If the underlying CellCog integration requires credentials, those will need to be provided elsewhere; the omission is a documentation gap that could lead to confusion or implicit credential handling by the CellCog dependency.
Persistence & Privilege
The skill does not request always: true, has no install step, and does not modify other skills or system configuration. Autonomous invocation is allowed by default (platform standard) and is not combined with any other broad privileges here.
Assessment
This skill appears to be a coherent instruction wrapper around the CellCog SDK and is reasonably safe as-is, but before enabling it you should: 1) confirm how the CellCog SDK is authenticated on your platform (are API keys or tokens required, and where would you store them?), 2) review CellCog's privacy and data handling (Think-Cog will process whatever context you feed it, possibly sensitive), 3) ensure you trust the CellCog provider for any modality work (visuals, prototypes) since the skill delegates execution to that service, and 4) if you need to enforce limits, check your agent's autonomy settings (this skill expects back-and-forth interaction rather than unsupervised deep work). If you want higher assurance, ask the publisher or check the 'cellcog' skill documentation for exact auth and permission requirements before use.Like a lobster shell, security has layers — review code before you run it.
latestvk972bvq41x9q0en1srgctwqncn84vc38
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
💭 Clawdis
OSmacOS · Linux · Windows