GoCluster

Use after neutral discovery and before Scope Ledger drafting when consequential design uncertainty, ownership placement, lifecycle/state responsibility, compatibility, migration, algorithm choice, operability, or reversibility could admit a materially different safe approach. Begin with a lightweight design-space probe when the lead currently sees one obvious design but an alternative may plausibly exist. Run the full comparison when the probe identifies two or more viable approaches or when choosing incorrectly would be materially consequential. Do not trigger when settled constraints clearly force one safe design.

Explain, trace, or deeply review existing code using inspected repository evidence without implementing changes. Use for code-understanding requests unless the user explicitly asks only for a concise, brief, quick, high-level, or initial overview. This skill explicitly owns thorough reviews, comprehensive explanations, audits, diagnosis, correctness analysis, architecture assessment, risk analysis, execution tracing, concurrency analysis, lifecycle analysis, and full subsystem understanding.

Use when actual scientific or model inputs, outputs, semantics, units, boundaries, classifications, calibration, uncertainty, tolerances, or claims change or require authoritative resolution. Independently derive and evaluate the scientifically defensible contract, compare competing interpretations, create independent golden vectors, and make evidence-qualified recommendations while leaving product policy, scope, architecture, and implementation authority with the user and lead. Do not trigger for mechanical work that cannot affect model behavior or claims.

Use before approval when testability or oracle quality could materially affect scope, behavior, architecture, observability, or validation planning, and after approval before implementation when the detailed planned evidence may not falsify a broken design. Apply to unclear parser, protocol, config, lifecycle, retained-state, performance, scientific/model, security, workflow-checker, or other material oracles. Do not trigger when accepted checks directly prove a localized mechanical change.

Use when reviewing or changing Codex workflow authority, approval, validation routing, review rules, templates, repo-managed skills, or enforcing scripts. Select conformance mode when checking implementation against accepted workflow policy. Select effectiveness mode when the user explicitly asks whether the workflow, its rules, or its architecture should be retained, changed, consolidated, replaced, or removed. Do not trigger for ordinary product documentation or runtime work whose workflow contract is unchanged.

Use after current-state discovery when material product, operator, compatibility, failure, classification, default, threshold, ordering, precedence, persistence, or test-oracle semantics still admit more than one plausible interpretation. Compare interpretations and make conditional recommendations, but unresolved material semantics remain user-owned and block concrete design selection and an unconditional Scope Ledger until explicitly resolved by the user, controlling authority, or evidence that eliminates every competing interpretation. Do not trigger merely because requirements are detailed or work is Non-trivial.

Deliver a concise initial orientation to existing code without implementing changes. Use only when the user explicitly asks for a concise, brief, quick, high-level, or initial overview and no more specific repo-managed review, audit, diagnostic, domain, or engineering skill applies. Do not compose this skill with a specialist skill or use its output format to constrain specialist analysis.

Use for read-only review of newly written gocluster Go implementation when the work is High-risk or substantial: shared/exported interfaces, material algorithms or state machines, substantial rewrites, meaningful residual uncertainty, or multiple production packages with shared impact or cross-package uncertainty. Do not trigger for every Non-trivial Go edit.

Use for read-only adversarial review of a Proposed Scope Ledger when scope is High-risk, uncertain, disputed, difficult to reverse, or leaves material residual uncertainty. Do not trigger for every Non-trivial ledger.

Use when Go work involves or investigates goroutine, timer, ticker, channel, socket, file-handle, process, shutdown, lifecycle, queue, retained-heap, map/cache/index, pprof, trace, or long-running leak concerns. Distinguish static/local evidence from runtime confirmation.

Use when a Codex task may change a durable architecture, operations, scientific, or workflow decision; originates in troubleshooting; or edits ADR/TSR records and indexes. Do not trigger merely because work is Non-trivial or require a no-change ADR.

Use before planning, approving, reviewing, or implementing Go changes with uncertain blast radius, shared interfaces, semantic call/reference impact, package dependency impact, tests/docs/support routing impact, or cross-package behavior. Classify required and optional analysis tools separately.

Use when Codex needs to understand unfamiliar or cross-package Go behavior before planning or changing code. Walk current source using package docs, crawler-entry comments, semantic navigation, tests, ADR/TSR history, and support routing; report inspected evidence and unknowns before proposing changes.

Use before designing, reviewing, or modifying Go YAML config loading, schema validation, defaults, operator settings, reference tables, optional secret/tool config, or config-owned runtime behavior.

Use when Go work involves long-lived inbound or outbound network connections, reconnect/retry/backoff behavior, keepalives, deadlines, silent-stall or zero-data modes, EOF/read-loop recovery, connection shutdown, source liveness, or operator-visible connection diagnostics. Compose with go-leak-detection when goroutines, sockets, timers, channels, queues, cancellation, or resource cleanup are touched.

Use when designing, reviewing, or modifying Go server-lifetime retained state: maps, sync.Maps, heaps, indexes, caches, pools, interners, retained slices, cleanup/eviction paths, or memory optimizations that add side tables. Require explicit ownership, bounds, eviction coupling, churn tests, and cardinality observability.

Use when the user asks to review, compare, or interpret multiple local Go pprof bundles across optimization rounds. Classify bundles as cold, warm, or transition, extract exact deltas for target symbols, and produce a net-win or net-regression judgment with explicit confidence and caveats.

Use when Go work involves or investigates goroutine, timer, ticker, channel, socket, file-handle, process, shutdown, lifecycle, queue, retained-heap, map/cache/index, pprof, trace, or long-running leak concerns. Distinguish static/local evidence from runtime confirmation.

Optional. Use when the user asks to review, compare, or interpret multiple local Go pprof bundles across optimization rounds. Classify bundles as cold, warm, or transition, extract exact deltas for target symbols, and produce a net-win or net-regression judgment with explicit confidence and caveats.

Use before planning, approving, reviewing, or implementing Go changes with uncertain blast radius, shared interfaces, semantic call/reference impact, package dependency impact, tests/docs/support routing impact, or cross-package behavior. Classify required and optional analysis tools separately.

Use when Fable needs to understand unfamiliar or cross-package Go behavior before planning or changing code. Walk current source using package docs, crawler-entry comments, semantic navigation, tests, ADR/TSR history, and support routing; report inspected evidence and unknowns before proposing changes.

Use before designing, reviewing, or modifying Go YAML config loading, schema validation, defaults, operator settings, reference tables, optional secret/tool config, or config-owned runtime behavior.

Use when Go work involves long-lived inbound or outbound network connections, reconnect/retry/backoff behavior, keepalives, deadlines, silent-stall or zero-data modes, EOF/read-loop recovery, connection shutdown, source liveness, or operator-visible connection diagnostics. Compose with go-leak-detection when goroutines, sockets, timers, channels, queues, cancellation, or resource cleanup are touched.

Use when designing or reviewing Go runtime-performance patches on hot paths. Inspect the actual caller pattern and data shape first, choose the algorithm to match the runtime shape, define allocation targets up front, and require targeted benchmarks plus live-profile acceptance criteria.

Use when designing, reviewing, or modifying Go server-lifetime retained state: maps, sync.Maps, heaps, indexes, caches, pools, interners, retained slices, cleanup/eviction paths, or memory optimizations that add side tables. Require explicit ownership, bounds, eviction coupling, churn tests, and cardinality observability.

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

Use when designing or reviewing Go runtime-performance patches on hot paths. Inspect the actual caller pattern and data shape first, choose the algorithm to match the runtime shape, define allocation targets up front, and require targeted benchmarks plus live-profile acceptance criteria.