skills/core/engineering/aoa-engineering-shape/SKILL.md
Shape one software responsibility boundary through bounded-context, core-boundary, or port-adapter mode. Use when responsibilities, reusable rules, orchestration, or concrete dependencies are entangled and a small owner-aware boundary is needed before implementation. Do not use for source-authority lookup, ordinary edits, test design, or a boundary that is already clear.
npx skillsauth add 8Dionysus/aoa-skills aoa-engineering-shapeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Choose one shaping lens and return the smallest target-bound responsibility boundary without installing an architecture framework by default.
Use this skill when:
Do not use this skill when:
Read references/contract.yaml and choose exactly one mode:
| Mode | Select when | Required procedure |
|---|---|---|
| contexts | Meanings, responsibilities, owners, or dual postures are overloaded. | references/contexts.md |
| core | A stable rule is mixed with loading, rendering, orchestration, or infrastructure. | references/core.md |
| port-adapter | A concrete database, API, filesystem, CLI, provider, or runtime detail leaks inward. | references/port-adapter.md |
Read the selected reference completely. Do not load the other mode procedures merely because their vocabulary appears nearby.
Bind owner only from a declaration that governs the target slice. An
unrelated authored surface, sibling route, recent file, or generated index
cannot supply the target owner. Keep owner: unresolved when that binding is
missing; never borrow a plausible owner.
Execute only the selected procedure. If another shaping mode is materially necessary, finish the upstream result and hand its typed output to a later task-local DAG node instead of blending modes.
Stop after one reviewable boundary and next-owner question. Do not implement or multiply abstractions unless the request separately authorizes that effect.
Owners provide local vocabulary, interfaces, compatibility windows, and validation commands. Those facts remain owner data, not forks of this skill.
development
Sanitize private technical material into a public-safe owner-bounded derivative, or resolve authority among authored, generated, runtime, and installed sources. Use for governed incidents, logs, configs, diagnostics, or conflicting source roles. Do not use for ordinary editing, memo/session work, direct publication, or durable-memory authority.
tools
Diagnose a reviewed recurring session/workflow failure, or carry one bounded owner repair through checkpoint, rollback, and real health verification. Use for reviewed contamination, drift, repeated route/tool failure, or an established diagnosis ready for repair. Do not use on live evidence, for vague self-improvement, or to call a proposed or merely executed change verified.
tools
Use only when a literal ref to a closed/reviewed session packet is supplied, to extract, classify, propose promotion or branching, or identify an automation opportunity. Missing, live, or unreviewed evidence must fail closed without inventing a ref. Natural closeout preservation belongs to aoa-memo-writeback. Do not use for generic summaries, progression, direct owner writes, scheduling, mutation, or telemetry authority.
testing
Turn one stable technical truth into bounded evidence through contract, coverage-audit, or property mode. Use to define a named consumer seam, audit what existing checks really constrain, or express a broad invariant after manual cases establish meaning. Compose with aoa-eval when an evaluation surface must first be found or applied. Do not use for undefined behavior, generic test plans, or green checks as whole-system proof.