AI Agent Workflow Collection

Use when an API, schema, payload, event, or contract change must be checked for backward compatibility, client impact, versioning risk, and migration safety.

Use when the core problem is structural change: boundaries, coupling, module seams, interface extraction, or safe refactor sequencing. This skill helps decide how to reshape code without turning implementation into guesswork.

Use when the main question is what a proposed or partial change will affect across code, interfaces, configs, tests, docs, consumers, and rollout surfaces. This skill maps blast radius before implementation, merge, or release.

Use when a change may increase infrastructure or runtime cost (compute, storage, network egress, third-party API calls, observability volume) and the team needs a focused cost-impact review before merge or rollout.

Use when a schema change, backfill, data migration, or persistence-layer transition must be reviewed for rollout order, reversibility, backfill safety, and operational risk.

Use when the main question is whether a third-party dependency is acceptable to adopt, upgrade, keep, or ship. This skill focuses on package risk, license or policy fit, supply-chain awareness, and recommended next actions.

Use when the main risk is environment parity, config drift, secrets wiring, flags, defaults, or deployment-time assumptions rather than code logic itself.

Use when a problem is driven by alerts, logs, metrics, traces, dashboards, or visible production impact. This skill focuses on blast radius, mitigation direction, and telemetry-first investigation before jumping into implementation.

Use when the main problem is latency, throughput, memory, resource usage, render slowness, or another performance bottleneck that needs investigation and prioritization.

Use when an incident has already been mitigated and the team needs a structured post-incident retrospective with timeline, impact, root cause, contributing factors, and follow-up actions.

Use when a change is shippable in principle but still needs a safer rollout shape, rollback plan, monitoring checkpoints, or staged release execution strategy.

Use when review comments, requested changes, or PR feedback must be processed systematically. This skill groups comments, decides what to accept, and turns feedback into verified edits instead of ad hoc reactions.

Use when work is nearly complete and needs a final readiness check for merge, release, or deployment. This skill focuses on remaining blockers, verification state, risks, rollback awareness, and documentation gaps.

Use when the main question is whether current verification is sufficient for a change, which test layers are missing, and where the smallest high-value regression protection should be added.