| name | standards |
| description | Load only the standards relevant to a |
Standards — focused engineering guidance
Load the smallest set of standards justified by the caller's files, language,
and risks. Do not preload the entire reference corpus.
Procedure
- Record the supplied paths, language, change type, and risk cues.
- Load
common-standards.md plus only the matching language or checklist
references.
- Compare the supplied artifact to those sources.
- Return cited findings with path and line when possible, plus checked and
not-checked scope.
- Stop.
This skill provides context and findings. It does not edit, validate, retry,
approve, commit, release, deliver, or decide continuation.
Load-bearing conventions for produced code (MEASURED)
When the caller is about to WRITE code (not only review it), surface the
matching language rules INLINE in the working context — a behind-the-link
reference does not change behavior; an inline imperative does. The Go core:
- Wrap every propagated error with context:
fmt.Errorf("doing X: %w", err)
— never return a bare inner error.
- Multi-case functions get TABLE-DRIVEN tests (
[]struct cases + t.Run per
case), asserting exact expected values including the error cases.
For other languages, pull the matching reference below and inline its top
rules the same way.
Measured 2026-08-04, probe standards-go-conventions (gpt-5.6-luna, N=2,
directional): control produced the %w-wrapped + table-driven shape in 1/2
runs; with these rules inline, 2/2. Inline-imperative beats reference-link —
the graphify probe measured a linked doc instruction obeyed 0/2. Ledger:
evals/skill-probes/LEDGER.md.
Mutation-safety standards
When the supplied change rewrites existing files in bulk — formatters,
codemods, migration scripts, generators pointed at hand-written sources —
check it against three standards and report each as a finding when absent: