Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
SkillScore96Maintained
Automatic
◆Coding pack
Last verified 10/10/2026
What it changes
Passed 23 of 24 test cases with the skill, and 18 of 24 without it.
Without skill75%
With skill96%
Checks it passed that the model alone missed
The refactored code extracts business logic into pure functions.
The analytics engine accepts typed record objects without parsing string lines.
The Express controller catches domain errors and maps them to HTTP status codes.
and 2 more in the full report
5 fixed18 passed either way1 still failing0 broke
Pass-rate lift
+21 pp
Tokens
+1%
Agent turns
0%
Response time
-10%
Model gemini-3.6-flashMeasured 10/10/2026v123 of 24 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
I have a TypeScript service handling user registration where request body parsing, database checks, and string validation logic are scattered across multiple nested helper functions. Please refactor this code to make it cleaner and easier to unit test. I need you to provide the rewritten TypeScript code along with a bulleted list explaining how the code was restructured.
What was checked, without and with the skill
Checked
Without skill
With skill
The refactored code performs raw input validation at the HTTP boundary.
Passed
Passed
The refactored code extracts business logic into pure functions.
Missed
Passed
case-01 · gemini-3.6-flash · 10/10/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md28 linessingle file
Boundary Discipline
Place validation, type narrowing, and error handling at system boundaries. Trust internal code unconditionally. Business logic lives in pure functions; the shell is thin and mechanical.
Why: Scattered validation is noisy, redundant, and gives a false sense of safety. Keep logic out of framework wiring so it can be tested without the framework.
Inside the system: typed data, error propagation, no re-validation. Trust the types.
Across the boundary. Expose domain concepts, not the boundary's private representation. Keep general-purpose mechanism inside and special-purpose policy at the edge.
Applications:
Validation and error handling:
Validate config at parse time (the boundary), not inside business logic
Parse raw data into domain types at the boundary
Do not re-export transport, storage, framework, or wire types through the public surface
No redundant nil checks deep in call chains if the boundary already validated
Code organization:
Business logic in pure functions with no framework dependencies
Parse functions: pure transforms from raw bytes to typed state
Prompt construction: structured state in, string out
Scoring and assessment: pure transforms from state to results
The tests:
"Is this data crossing a system boundary right now?" If not, validation is redundant.
"Can this be a pure function that the shell just calls?" If yes, extract it.