Focused SKILL.md templates with safe boundaries.

Separate cloud-spend changes into usage volume, workload mix, and effective unit rates, with a reconciled example and read-only evidence checks.

A read-only-first workflow for turning operator evidence into bounded next steps.

Checks a change against build, test, migration, rollback, and browser evidence.

Reviews schema changes for locking, compatibility, backfill, and rollback risk.

Guides evidence collection for pods, rollouts, services, and cluster events.

Updates technical documentation while preserving verified commands and source boundaries.

Performs keyboard, semantics, contrast, motion, and responsive checks.

Traces trust boundaries, authorization, secrets, injection, and unsafe operations.

Plans additive changes, client overlap, deprecation, telemetry, and rollback.

Builds a reproducible baseline and attributes latency or resource cost before optimization.

Translates an approved design brief into consistent tokens, components, and visual QA.

An evidence-first workflow to plan a behavior-preserving refactor across explicit module boundaries.

An evidence-first workflow to review a change without confusing preference with a defect.

An evidence-first workflow to detect architecture boundary violations and accidental coupling.

An evidence-first workflow to prove that code is unreachable or unused before deleting it.

An evidence-first workflow to find missing behavioral coverage around a proposed change.

An evidence-first workflow to separate nondeterminism, shared state, timing, and environment failures.

An evidence-first workflow to design consumer-visible compatibility tests for an API boundary.

An evidence-first workflow to verify hierarchy and interaction behavior across supported viewport ranges.

An evidence-first workflow to attribute loading and interaction latency before proposing optimization.

An evidence-first workflow to review resource semantics, status codes, caching, pagination, and idempotency.

An evidence-first workflow to design bounded background work with retries, idempotency, cancellation, and observability.

An evidence-first workflow to verify signature handling, replay protection, retries, ordering, and idempotent processing.

An evidence-first workflow to locate the first actionable pipeline failure without rerunning blindly.

An evidence-first workflow to evaluate build, migration, configuration, rollback, and observability gates.

An evidence-first workflow to trace untrusted inputs, token permissions, artifact provenance, and protected deployment paths.

An evidence-first workflow to compare declared and observed deployment state without mutating either.

An evidence-first workflow to review infrastructure changes for replacement, privilege, exposure, cost, and rollback risk.

An evidence-first workflow to identify unintended permissions and privilege-escalation paths in cloud access policy.

An evidence-first workflow to review an image for provenance, contents, privileges, secrets, and reproducibility.

An evidence-first workflow to review rendered Kubernetes resources and upgrade behavior before a release.

An evidence-first workflow to map assets, trust boundaries, attacker capabilities, and abuse paths for a concrete change.

An evidence-first workflow to trace personal data collection, purpose, sharing, retention, deletion, and user controls.

An evidence-first workflow to explain a slow query from its plan, estimates, indexes, and runtime evidence.

An evidence-first workflow to verify freshness, completeness, uniqueness, lineage, and recovery behavior.

An evidence-first workflow to evaluate retrieval quality separately from answer quality and citation fidelity.

An evidence-first workflow to turn prompt behavior into a repeatable dataset and scored release gate.

An evidence-first workflow to review tool schemas, permissions, confirmation boundaries, and untrusted tool output.

An evidence-first workflow to verify that integration documentation matches the published API contract and real failure behavior.

An evidence-first workflow to write an incident procedure with entry conditions, safe checks, decisions, and stop conditions.

An evidence-first workflow to resolve conflicting intent while preserving both branches' tested invariants.

An evidence-first workflow to stage a backwards-compatible application and data migration with safe overlap.

An evidence-first workflow to reconstruct one request or failure across services without retaining sensitive payloads.

An evidence-first workflow to interpret error-budget burn across short and long windows before escalating.

An evidence-first workflow to turn an ambiguous request into testable outcomes, constraints, and explicit non-goals.

An evidence-first workflow to deduplicate and prioritize work using impact, evidence, dependency, and risk.

An evidence-first workflow to review an experiment for hypothesis quality, metrics, guardrails, exposure, and decision rules.

An evidence-first workflow to audit a workbook for formula errors, inconsistent ranges, hidden assumptions, and reproducibility.

An evidence-first workflow to review a PDF for tags, reading order, language, text alternatives, forms, and contrast.

An evidence-first workflow to review a presentation for narrative, evidence, readability, accessibility, and speaker flow.