Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agent-native-architecture
Build applications where agents are first-class citizens.
Passed 19 of 22 test cases with the skill, and 15 of 22 without it.
and 3 more in the full report
4 fixed15 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our desktop productivity app puts user documents in ~/Documents/User/ while saving agent outputs in a separate, isolated directory ~/AppData/AgentSandbox/. Is this directory isolation recommended in agent-native architecture?
| Checked | Without skill | With skill |
|---|---|---|
| Rejects sandbox isolation between user and agent data spaces | Missed | Passed |
| Recommends a shared workspace where user and agent operate directly on the same underlying files | Missed | Passed |
The instructions your model reads when the skill loads.
<essential_principles>
Agent native engineering inverts traditional software architecture. Instead of writing code that the agent executes, you define outcomes in prompts and let the agent figure out HOW to achieve them.
Whatever the user can do, the agent can do. Many things the developer can do, the agent can do.
Don't artificially limit the agent. If a user could read files, write code, browse the web, deploy an app—the agent should be able to do those things too. The agent figures out HOW to achieve an outcome; it doesn't just call your pre-written functions.
Each feature is a prompt that defines an outcome and gives the agent the tools it needs. The agent then figures out how to accomplish it.
Traditional: Feature = function in codebase that agent calls Prompt-native: Feature = prompt defining desired outcome + primitive tools
The agent doesn't execute your code. It uses primitives to achieve outcomes you describe.
Tools should be primitives that enable capability. The prompt defines what to do with that capability.
Wrong: generate_dashboard(data, layout, filters) — agent executes your workflow
Right: read_file, write_file, list_files — agent figures out how to build a dashboard
Pure primitives are better, but domain primitives (like store_feedback) are OK if they don't encode logic—just storage/retrieval.
The advanced tier: agents that can evolve their own code, prompts, and behavior. Not required for every app, but a big part of the future.
test cases passed, vs 15 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.