AA ai-architecture-harness
Establish and use architectural guardrails for AI-assisted coding to prevent architecture collapse, feature regression, and drift across long multi-turn iterations. Use when the user mentions AI coding, Agent coding, architecture collapse, Harness Engineering, design intent, acceptance rules, golden rules, architecture tests, or wants the codebase to be safer for AI Agent modifications.
As a process A 80/100 · Runs to the end — weak spots: consistency, running it twice, progress reporting
How to improve
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 80/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (ai-architecture-harness) differs from the folder (ai-architecture-harness-en)
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 49 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 1860 tokens
- low 11 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +3Description length 389: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 49 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.