Use when generating or auditing a multi-role agent team package with orchestrator, workers, handoffs, Memory Ticket outputs, and runtime adapters (PM Soul, Memory Curator, Policy Gate, eval and QA are OS-resident).
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./codex/plugins/agentlas-core-engine-meta-agent/runtime-support/skills/team-builder-packaging/SKILL.mdThe canonical home for this skill is team-builder-packaging in agentlas-ai/Agentlas-OS
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Step 2 requires the agent to actively research comparable agent repositories, academic theory, and plugin docs, which are arbitrary outsider-authored web content the agent must search for and fetch, so the attacker can publish poison but cannot force delivery.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.