BA aomi-build
Scaffold new Aomi apps and plugins from API docs, OpenAPI/Swagger specs, or SDK references. aomi-build generates production-ready Rust SDK crates (lib.rs, client.rs, tool.rs) with tool schemas, preambles, host-interop flows, and validation — turning a vendor's API surface into AI-agent-callable tools. It covers the current `aomi-build` OpenAPI pipeline (`gen-specs` → `gen-client` → `gen-tool` → curate → compile/test) as well as greenfield apps. Use when the user wants to scaffold a new Aomi app from a spec, wrap a REST API as agent-callable tools, port an existing SDK, or extend an Aomi runtime with new integrations. Trigger with prompts about wrapping APIs, scaffolding Rust crates from specs, or adding protocol integrations that aomi-transact can drive. Output crates support progenitor-generated OpenAPI clients, curated tool layers, sync HTTP, async tools (DynAsyncSink), typed secrets, route plans (ToolReturn/RouteStep), EVM and SVM host handoffs, and multi-step quote→approval→swap flows. Same runtime that aomi-transact drives.
As a process A 87/100 · Runs to the end — weak spots: progress reporting
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1045 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5131 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "permissions" - note
frontmatter-keyunknown frontmatter key "risk_tier" - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 87/100
- 0Progress reporting. Says nothing while it works
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5131 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 144 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (10 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1044: 120–800 characters recommended
- +2Single-language instructions
- +4Structure: 22 headings
- +3Step-by-step instructions: 144 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.