Loading...
Loading...
Found 9 Skills
Apply whenever you write or review a command that decides whether work is done: a test invocation, an acceptance check, a CI gate, a shell assertion, a grep-based verify step. Names the failure signal, grounds paths, and catches the shapes that pass green while measuring nothing.
Repository structure methodology for maximum AI agent effectiveness. Three pillars — context engineering (repo as knowledge product), architectural constraints (deterministic enforcement), garbage collection (active entropy fighting). Use when setting up repos for AI development, diagnosing repeated agent failures, writing AGENTS.md, or designing CI gates and structural tests.
Audit a published API reference at the endpoint level against its spec surface - every operation, parameter, response code, and error documented, request/response examples present, per-language code snippets in parity, try-it affordances working - and install the source-of-truth gates that stop reference drift (spec-driven generation, OpenAPI lint, contract tests, snippet parity in CI). Use whenever the user mentions API reference docs, OpenAPI docs completeness, undocumented endpoints or error codes, stale or drifting docs, or docs CI gates - even if they never say "reference quality". Endpoint-level reference only. Do NOT use for portal IA and onboarding - use samber/developer-platform-skills@developer-portal-design instead.
The one definition of what each gate runs. Use to run a gate stage, to add or change a check, or to read why a step exists.
Use when hardening or auditing license evidence, SBOM generation, full Maven Reactor verification, commit and push proof, or CI completion across multiple maintenance branches.
Set up or run design QA gates — token + hardcoded-value lint, automated a11y (axe), contrast, visual regression across variants/states/themes/RTL, and the manual a11y checklist. Use when the user wants CI quality gates, to prevent design regressions, or to QA a component/screen before shipping.
Runs the golden re-baselining ritual — the one sanctioned way committed reference images are overwritten. Enforces the order: land and green the non-golden geometry, contrast and a11y tests FIRST, re-baseline only in the pinned blessing environment that produced the committed images, with loadAppFonts() so nothing renders in Ahem, via `flutter test --update-goldens --tags golden` (never in CI, never to make a red pipeline green), then inspect every changed PNG by eye, delete the orphans left by renamed or removed tests, land the images as their own commit naming why they moved, and prove it by re-running the suite WITHOUT the flag. Manual, side-effecting workflow. Use when a deliberate visual change breaks matchesGoldenFile, when adding or renaming a golden test, or when someone reaches for --update-goldens.
Enforces a deterministic build_runner codegen discipline: run one pinned `dart run build_runner build --delete-conflicting-outputs` pass BEFORE `flutter analyze` (never after), fence every builder with `generate_for:` globs in a per-package `build.yaml`, make one deliberate commit-vs-gitignore decision for `*.g.dart`/`*.freezed.dart`/`*.drift.dart` and back it with the matching CI gate (freshness diff if committed, codegen-first if gitignored), mirror the generated-file globs into the analyzer AND coverage excludes, pin the SDK, and never hand-edit generated output. Use when editing build.yaml, analysis_options.yaml, pubspec.yaml, .gitignore, .gitattributes, or CI workflows; wiring drift_dev/freezed/json_serializable/riverpod_generator/ gen-l10n/mockito codegen; fixing "missing part file", "undefined class _$Foo", or "conflicting outputs" errors; deciding whether to commit generated code; or scoping builders so one edit does not regenerate everything.
Workflow chốt PUSH/RELEASE/PR/MR — gọi khi user nhắc 'release'/'push'/'ship'/'lên release'/'mở PR'/'tạo MR'. Chạy CHECKLIST điều kiện TRƯỚC khi đẩy: (1) medic --ci (cổng sức khoẻ: luật cắn/drift/docs/code/eval), (2) UAT /fdk-uat qua remote thật nếu diff có năng lực mới (chỉ release/pr/mr, medic --ci không chứng minh được đường curl), (3) git sạch (scratchpad/ephemeral không track), (4) selftest, (5) version x.x.x+1 từ tag gần nhất (chỉ mức release), (6) patch note/PR-body trung thực (Added/Fixed/Removed/Known-limitations, KHÔNG phóng đại). Hỗ trợ 5 mức: 'ship push' = chỉ push không tag; 'ship release' = push + tag vX.Y.Z + release notes; 'ship pr' = push nhánh + gh pr create (GitHub); 'ship mr' = push nhánh + glab mr create (GitLab); 'ship merge' = liệt kê PR/MR ĐẾN của repo theo remote, kéo nhánh về, chạy gate+test, chỉ merge nếu XANH. STOP chờ duyệt trước bước side-effect. Trigger: /ship, 'release', 'push', 'ship', 'mở PR', 'tạo MR', 'ship pr', 'ship mr', 'ship merge', 'gom PR về merge', 'merge PR nếu test xanh', 'chuẩn bị push', 'lên release', 'checklist trước push', 'đủ điều kiện push chưa'.