Claude Skills by machenjie

`analysis-agent`/`task-agent`/`review-agent`: use when Protobuf schemas, parsers, or old-reader/new-writer compatibility changes; skip work without a data-format contract.

`analysis-agent`/`task-agent`/`review-agent`: use when migration, backfill, deployment order, rollback, or live-data safety needs design; skip when no data migration exists.

`analysis-agent`/`task-agent`: use for persisted identity, relationship, ownership, lifecycle, cardinality, or invariants; skip repository, migration, and mapping-only work.

`analysis-agent`/`task-agent`/`review-agent`: use when persistence, cache, events, external I/O, or compensation may hide or misorder side effects; skip unchanged flows.

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for timeout, fallback, bulkhead, or circuit recovery; never task owner; skip without dependency-failure impact.

`analysis-agent`/`task-agent`/`review-agent`: use when dependencies change or vulnerability, license, transitive, lockfile, or SBOM risk needs review; skip unrelated work.

`analysis-agent`/`task-agent`/`review-agent`: use when construction, injection, lifecycle scope, clients, overrides, or shutdown ownership changes; skip unaffected wiring.

`analysis-agent`/`task-agent`/`review-agent`: use when a current variation, lifecycle, protocol, or concurrency force may justify a pattern; skip pattern-name or placement work.

`analysis-agent`/`task-agent`: use when tokens, components, responsive behavior, accessibility, or variants need consistency rules; skip when UI system rules are unaffected.

Use for distributed workflow consistency, unknown effects, compensation, reconciliation, repair, or evolution. Skip atomic transactions, local retry, schema-only, and engine work.

`task-agent`: change source-owned documentation; `review-agent`: assess documentation without mutation. Skip tasks requiring neither documentation change nor review.

`analysis-agent`/`task-agent`: use when commit timing, payloads, schema, ordering, idempotency, or retry changes; skip when no domain-event decision is required.

`analysis-agent`/`task-agent`: use when an invariant, transition, calculation, or policy needs one domain authority; skip orchestration, storage, mapping, and unchanged-rule work.

`analysis-agent`/`task-agent`/`review-agent`: classify domain identity, values, aggregates, lifecycle, invariants, writers, and relationships; skip layer-derived nouns.

`task-agent`: use when DTO fields, validation, nullability, defaults, serialization, or compatibility change; skip persistence/domain-only work without an external schema.

`analysis-agent`/`task-agent`/`review-agent`: use when a critical assembled journey needs proof unavailable below E2E; skip risks proved by component, seam, or contract tests.

`task-agent`: use when error codes, safe messages, retryability, remediation, status mapping, or client behavior needs a stable contract; skip when no error contract changes.

`analysis-agent`/`task-agent`: use when event flow, ordering, idempotency, replay, backpressure, or eventual consistency changes; skip when no event-driven decision is needed.

`analysis-agent`/`review-agent`: use when proven variation needs extension points, plugins, policy hooks, compatibility, or deprecation; skip when no extension decision exists.

`analysis-agent`/`task-agent`/`review-agent`: use when retryable, terminal, timeout, partial-failure, or fallback semantics change across boundaries; skip unchanged failures.

`analysis-agent`/`task-agent`/`review-agent`: use when symptoms, logs, metrics, regressions, or incidents need cause analysis; skip when no diagnosis decision exists.

`analysis-agent`/`task-agent`/`review-agent`: use when uploads, object storage, streaming, MIME, scanning, access, retention, or cleanup changes; skip without file/storage impact.

Use when code mutates files, resolves paths, applies file protection, or controls child processes. Skip uploads, shell syntax, build graphs, services, and host administration.

`analysis-agent`/`task-agent`/`review-agent`: use when form fields, validation, async checks, submit states, or recovery change; skip when form behavior is unaffected.

`task-agent`: use when frontend API loading, cancellation, retries, auth expiry, pagination, stale data, errors, or optimistic updates change; skip when no integration changes.

`analysis-agent`/`task-agent`/`review-agent`: use for component, route, browser, accessibility, and API-backed UI-state tests; skip backend, portfolio, and release-verdict work.

`analysis-agent`/`task-agent`/`review-agent`: use when merges, rebases, conflicts, history rewrite, generated files, or recovery need evidence; skip when Git is irrelevant.

`analysis-agent`/`task-agent`/`review-agent`: use when Go context, goroutine, channel, error, interface, or resource semantics affect behavior; skip generic or non-Go work.

`analysis-agent`/`task-agent`/`review-agent`: use when locale, timezone, date/time, currency, formatting, plurals, fallback, or rounding changes; skip unaffected semantics.

`analysis-agent`/`task-agent`/`review-agent`: use when retries, idempotency, deduplication, timeout, or replay safety affects side effects; skip when operations cannot repeat.

`analysis-agent`/`task-agent`/`review-agent`: use when reuse or method/class/file placement inside one owner is disputed; skip fixed placement or cross-module ownership.

`task-agent`/`review-agent`: use when predicates, sorting, cardinality, query plans, pagination, indexes, or write cost change; skip when no query/index decision exists.

`analysis-agent`/`task-agent`: use when hierarchy, labels, findability, ownership, visibility, lifecycle, or cross-module discovery changes; skip route/state-only work.

`analysis-agent`/`task-agent`/`review-agent`: use for infrastructure state, identity, drift, replacement, destruction, or recovery; skip docs, live apply, and provider-only policy.

`analysis-agent`/`task-agent`/`review-agent`: use for input authority, parsing, canonicalization, bounds, state checks, writable fields, rejection, or external-response changes.

`analysis-agent`/`task-agent`/`review-agent`: use for database, broker, cache, HTTP, framework, process, or transaction seam proof; skip local, portfolio, and release-verdict work.

`analysis-agent`/`task-agent`/`review-agent`: use when loading, empty, error, success, disabled, timeout, or permission states change; skip when visible state is unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when JVM transactions, interruption, executors, classloaders, serialization, or null semantics change; skip generic work.

`analysis-agent`/`task-agent`/`review-agent`: use for Kotlin coroutine, Flow, type, interop, DSL, or Compose-state decisions; skip incidental Kotlin text.

`task-agent`/`review-agent`: use when a Kubernetes workload, route, identity, health, capacity, or rollout boundary changes; skip image-only, pipeline-only, and non-cluster work.

`analysis-agent`/`task-agent`/`review-agent`: use when idioms for errors, types, resources, modules, naming, concurrency, or APIs need enforcement; skip when idioms are unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when allocation, GC, concurrency, async/blocking, FFI, or unsafe/native behavior changes; skip when runtime safety is unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use when language/runtime choice changes semantics, concurrency, memory, deployment, or FFI; skip when runtime is fixed.

`analysis-agent`/`task-agent`/`review-agent`: use when test results depend on runner, concurrency, timeout, cache, or isolation semantics; skip test-portfolio work.

`analysis-agent`/`task-agent`: use when presentation, application, domain, or infrastructure ownership/dependencies change; skip without a layering decision.

`analysis-agent`/`task-agent`/`review-agent`: use when Linux processes, signals, files, permissions, cgroups, namespaces, kernel, or host runtime changes; skip non-Linux work.

`task-agent`/`review-agent`: use when structured errors, logs, correlation, redaction, propagation, or safe diagnostics change; skip when logging/error handling is unaffected.

`task-agent`/`review-agent`: use when broker delivery, ordering, acknowledgement, DLQ, backpressure, or replay changes; skip synchronous retry without message semantics.

`analysis-agent`/`task-agent`/`review-agent`: use when a service split affects ownership, deployment, scaling, isolation, contracts, or data; skip without a split decision.

`analysis-agent`/`task-agent`/`review-agent`: use when added code, dependency, abstraction, configuration, or shortcut may exceed current need; skip when minimality is proven.