Installs into .claude/skills of the current project.
Are you the author of Ztx10 Agent Team Orchestrator?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/realjustawall-ztx10-agent-team-orchestrator)
---
name: ztx10-agent-team-orchestrator
description: "Choose core and website-specific agents, cap cost, provide isolated evidence and independent read-only reviews."
---
# Agent Team Orchestrator
**Intent:** Choose core and website-specific agents, cap cost, provide isolated evidence and independent read-only reviews.
## Execution protocol
1. Load approved brand identity and site-profile selection. Require tangible evidence, a clear owner, and a pass/fail check.
2. Separate audit dimensions and avoid duplicates. Require tangible evidence, a clear owner, and a pass/fail check.
3. Dispatch independent reviews with max concurrency and timeout. Require tangible evidence, a clear owner, and a pass/fail check.
4. Collect all structured outputs and classify unverified checks. Require tangible evidence, a clear owner, and a pass/fail check.
5. Hand adjudicated tasks to an opt-in fixer only. Require tangible evidence, a clear owner, and a pass/fail check.
## Inputs/Outputs
Input: site profile, approved brand, evidence path, task brief and allowed capabilities. Output: strict machine-readable report or orchestration plan with selected roles and reasons.
## Safety and correctness
- No existing skills may be removed. No third-party repository is executed by default.
- No edits until a human explicitly authorizes a separate fix flow.
- Always report not-run tests and confidence. Do not inflate the number of independent agents from identical prompts.
- Verify the implementation and its regression tests before completion.
