Skill
design-ai-agent-skills
Agent Skill that makes Claude design and review AI agent architectures for any LLM: agent-vs-workflow decisions, pattern selection, tools/ACI, context and memory, stopping conditions, guardrails, evals (pass^k) and MAST failure-mode reviews, with every rule traced to a cited source.
- VersionThe latest version we analysed. Everything on this page describes this version.
- main
- Last observedThe last time we saw this tool listed where it is published.
CoverageHow much of the tool we could inspect: listed only, downloaded, partly analysed, or fully analysed. Less coverage means fewer findings can be trusted to be complete.
Not analyzed
Detailed reportThe full report lists every finding with the file it came from, and every change we observed between versions.
Detailed report not available for this asset yet.
This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.
Using this tool with others? See how it fits with the rest of your setup.
Check every tool your agent uses