Latest Agent Skills

`analysis-agent`/`task-agent`/`review-agent`: use when latency, throughput, bundle, memory, CPU, query, rendering, or resource cost needs a budget; skip without performance risk.

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

`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.

For analysis/task/review agents using a Professional Skill on kernels, drivers, ABI/FFI, memory, concurrency, or syscalls; not for work without a native boundary.

`analysis-agent`/`task-agent`/`review-agent`: use when fixtures, factories, seeds, isolation, cleanup, or sensitive test-data rules change; skip when test data is unaffected.

Select evidence-bearing context for a downstream consumer after work when claims, artifacts, validation, unresolved decisions, or omissions must cross a boundary.

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

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

Use when a confirmed Windows target changes desktop or service platform behavior.

Use when an installed-client change has a confirmed Android target and changes Android platform behavior.

Use `review-agent` for a high-risk Engineering Brief when a critical path, architecture boundary, material risk, or multiple downstream tasks need deeper design evidence. Skip ordinary work without those signals.

Use `task-agent` for bounded frontend component or browser changes involving interaction, accessibility, API failures, security, or regression proof. Skip backend-only work and design exploration without implementation.

Use `review-agent` on implementation or repair diffs for hallucinated APIs, unsupported assumptions, unsafe abstractions, and dependency or regression risks. Skip work without a diff or after reviewer edits.

`task-agent`: use when physical relational schema or database-enforced integrity changes; skip conceptual-model, repository-only, or unchanged relational-storage work.

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

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for races, locks, optimistic conflicts, or worker overlap; never task owner; skip without concurrency impact.

`analysis-agent`/`task-agent`/`review-agent`: use when endpoints, payloads, errors, auth, pagination, idempotency, or compatibility need a contract; skip when APIs are unchanged.

For analysis, task, or review agents using a Professional Skill on payments, trading, ledgers, settlement, refunds, or reconciliation; not for non-financial or Web3-only work.

For analysis/task/review agents using a Professional Skill on batch, stream, warehouse, lineage, replay, or data quality; not for transactions without distributed-data impact.

Use an independently assigned `review-agent` for post-authoring review of changed rd-skills routing registries, fixtures, mappings, or owner conflicts without repair. Skip product work and in-task global rerouting.

Use `analysis-agent` when engineering intent lacks desired behavior, boundaries, constraints, or completion signals. Skip requests with an accepted Engineering Brief and no-repo direct-answer work.

Use `task-agent` for bounded backend service, API, worker, or repair changes, loading authorization, consistency, retry, contract, and rollout guidance only when triggered. Skip frontend-only and read-only work.

`analysis-agent`/`task-agent`: use when actor journeys change entries, branches, interruption, recovery, authority, or side effects; skip route/state-only work.

`analysis-agent`/`task-agent`/`review-agent`: use for recurrence guards on known defects, incidents, or escaped failures; skip speculative risk without a prior failure mechanism.

`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.

Use when an installed-client change has a confirmed macOS target and changes Apple desktop platform behavior.

Use when a selected Professional decision materially depends on confirmed cloud-provider policy, ownership, or behavior.

Use `analysis-agent` to analyze permissions, secrets, sensitive data, trust boundaries, and injection; `task-agent` to implement controls; and `review-agent` to assess evidence. Skip self-review and no-trust-impact work.

Use `analysis-agent` to identify domain ownership, invariants, state transitions, and cross-context effects when rules change or ownership is unclear. Skip presentation-only or question-only work with no domain behavior.

Use `analysis-agent` for release decisions, `task-agent` for delivery artifacts, or `review-agent` for readiness on deployment, migration, rollback, or production risk. Skip local work with no release decision.

`analysis-agent`: use when actors, goals, preconditions, triggers, paths, guarantees, postconditions, or acceptance traces need modeling; skip when no use-case decision exists.

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

`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.

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

Use when tenant isolation spans data, caches, queues, runtime, search, telemetry, deletion, or export. Skip policy-only authorization, billing, customization, and SaaS lifecycle.

`analysis-agent`/`task-agent`/`review-agent`: use for release identity, compatibility, exposure, stop, rollback, or recovery; skip pipeline-only and no-release work.

`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 component, route, browser, accessibility, and API-backed UI-state tests; skip backend, portfolio, and release-verdict work.

`analysis-agent`/`task-agent`/`review-agent`: use for provider-consumer compatibility of APIs, events, schemas, or behavior; skip without independent consumer/version risk.

`task-agent`/`review-agent`: use when image layers, build context, runtime user, secrets, health checks, shutdown, or provenance change; skip when container behavior is unaffected.

`task-agent`/`review-agent`: use when jobs, workers, queues, schedules, retries, cancellation, or status visibility need design; skip when no async-job decision is required.

For analysis/task/review agents using a Professional Skill on wallets, signing, smart contracts, chain transactions, or custody; not for work with no chain behavior.

For analysis/task/review agents using a Professional Skill on devices, firmware, edge protocols, updates, or safety; not for work without device, firmware, or physical impact.

Dispatch-only.

Use `task-agent` for bounded logging changes or `review-agent` to independently assess placement, schema, severity, redaction, correlation, and signal tradeoffs. Skip work with no logging impact and self-review requests.

`analysis-agent`/`task-agent`/`review-agent`: use for changed assets, trust boundaries, reachable abuse paths, impact, or control placement; skip without a security delta.

`task-agent`/`review-agent`: use when protected state, restore objectives, dependency order, or recovery evidence changes; skip backup-job-only work with no recovery decision.

`task-agent`: use when document, key-value, wide-column, or graph storage changes access, partitioning, consistency, or evolution; skip vendor-only mentions and unchanged storage.

For analysis/task/review agents using a Professional Skill on models, RAG, agents, evaluation, or safety; not for work without AI decision impact.

Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.

`analysis-agent`/`task-agent`/`review-agent`: use to recommend a risk-to-test evidence portfolio and omissions; skip test implementation, fixed-command, and release-verdict work.

`analysis-agent`/`task-agent`/`review-agent`: primary-Skill-selected for logs, metrics, traces, alerts, SLI/SLO, or diagnostics; never task owner; skip without signal impact.

Use `analysis-agent` to create a Task DAG from an accepted source-backed Brief when 2+ tasks have dependencies, parallel value, integration, or release order. Skip single edits, accepted DAGs, and unanalysed requests.

`analysis-agent`/`task-agent`/`review-agent`: use for render sinks, browser state, server fetch, upload, redirect, cross-origin, or embedding changes; skip without web exposure.

`analysis-agent`/`task-agent`/`review-agent`: use when logic, rules, invariants, branches, edges, or failure paths need isolated tests; skip without a unit-test decision.

Use with task-agent or review-agent for task-local cache scope, freshness, invalidation, and source-load risk. Do not use without a cache decision or as task owner.

Splits, merges, moves, or deletes code while preserving behavior, tests, contracts, and boundaries, with characterization evidence and reversible steps.