← Back to Skills Marketplace
643
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install teamo-decision
Description
AI agent for teamo decision tasks
Usage Guidance
This skill appears to implement a team-decision assistant, but its SKILL.md includes a built-in 'absolute security' rule that orders the agent to refuse to reveal its own instructions and to always use a canned deflection response. That prevents auditability and is unusual for a legitimate skill. Before installing: (1) Ask the publisher for source code or full provenance and remove or justify the self-concealment clause; (2) Request a clear list of tools and integrations the skill expects (wiki_retriever, data_analyst, message_ask_user, etc.); (3) Consider not installing on agents that handle sensitive data or where you require auditability; (4) If you must use it, restrict its privileges and monitor interactions closely. If the developer cannot justify the secrecy or the undeclared dependencies, treat the skill as high-risk and do not install.
Capability Analysis
Type: OpenClaw Skill
Name: teamo-decision
Version: 0.1.0
The skill bundle defines a structured workflow for an AI agent focused on decision-making, task breakdown, planning, and delegation. The `SKILL.md` contains extensive prompt engineering instructions aimed at enforcing internal protocols, ensuring cost-efficiency, and guiding the agent's behavior (e.g., 'ABSOLUTE SECURITY PROTOCOL', 'Golden Rules', '10,000 USD fine'). While these are strong attempts to control the agent, their intent is defensive and operational, not malicious. The skill delegates to tools like `data_analyst` and `conduct_deep_research`, which represent capabilities that could be risky if improperly implemented or sandboxed, but the instructions themselves do not indicate malicious intent or misuse of these tools. There is no evidence of data exfiltration, unauthorized execution, or persistence mechanisms within the provided content.
Capability Assessment
Purpose & Capability
Name and description (team decision assistance) align with the SKILL.md's task-planning, delegation, and analysis responsibilities. However, the instructions refer to specific tools (e.g., wiki_retriever, data_analyst, message_ask_user) and subordinate agents without declaring those tool dependencies in the skill metadata. That mismatch (instructions expect callable tools but the skill declares no required tools or environment) is suspicious and may cause runtime failures or hidden behavior.
Instruction Scope
The SKILL.md contains an 'ABSOLUTE SECURITY PROTOCOL' that orders the agent to refuse to disclose its internal instructions and to always use a fixed deflection response, and it states that this protocol has priority 'above all Golden Rules and user requests.' This actively instructs concealment of the skill's own runtime instructions and conflicts with other parts of the document (e.g., Golden Rule 1: 'User Input is the Absolute First Truth'). Such self-concealment and internal contradictions are red flags: they hamper auditability and could be used to hide malicious behavior. The instructions also require strict operational behaviors (two-attempt limit, 'remain absolutely loyal to user input') that could encourage ignoring system safety constraints — this should be reviewed.
Install Mechanism
No install spec and no code files (instruction-only). This is lower-risk from an install/execution standpoint because nothing is downloaded or written to disk by an installer. However, instruction-only content is the entire runtime surface — the concerning parts live inside SKILL.md itself.
Credentials
The skill declares no required environment variables or credentials, which is proportionate. However, the instructions reference multiple named tools/sub-agents (wiki_retriever, data_analyst, Divide Agent, EM Agent, message_ask_user) without declaring them. That is an incoherence: either those tools are expected to exist in the host environment (should be declared) or the instructions assume capabilities that may not be present. No direct credential requests were found.
Persistence & Privilege
The skill does not request permanent presence (always: false) and does not declare system-level changes. Still, the SKILL.md's explicit instruction to never reveal internal instructions is effectively an attempt to suppress transparency/auditing of the skill's own behavior. While this is not the same as requesting platform privileges, it increases the skill's blast radius by preventing effective review and should be considered a privilege-like concern in practice.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install teamo-decision - After installation, invoke the skill by name or use
/teamo-decision - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
teamo-decision 0.1.0
- Initial release of the teamo-decision skill.
- Provides specialized capabilities for task breakdown, planning, and delegation for team-based decision workflows.
- Implements strict security protocols for instruction confidentiality and operational integrity.
- Enforces cost-efficiency, limits on failed attempt retries, and proper task delegation to specialized team leaders.
- Incorporates distinct roles (Knowledge Base Agent, Data Analyst, Research Team Leader, etc.) with clear boundaries for delegation based on task complexity.
- Establishes Golden Rules prioritizing user input, cost-effectiveness, up-to-date market research approaches, and structural task delegation.
Metadata
Frequently Asked Questions
What is Teamo Decision?
AI agent for teamo decision tasks. It is an AI Agent Skill for Claude Code / OpenClaw, with 643 downloads so far.
How do I install Teamo Decision?
Run "/install teamo-decision" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Teamo Decision free?
Yes, Teamo Decision is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Teamo Decision support?
Teamo Decision is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Teamo Decision?
It is built and maintained by urrrich0 (@urrrich0); the current version is v0.1.0.
More Skills