AI DevKit · Supervise multi-agent workflows over repeated passes: poll progress, unblock waiting agents, coordinate dependencies, relay outputs, resolve conflicts, and verify completion. Use only for ongoing multi-agent coordination, not one-off list/detail/send/start/kill actions.
94%
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
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.
The required loop runs `ai-devkit agent detail --tail 10` on running agents and relays their output, which can carry text from external pages those agents fetched, so outsider text reaches the orchestrator only after an agent has actively searched or fetched it.
codeaholicguy/ai-devkit
47ffc9c
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.