436 个 · 按相关度排序
Plan and implement gradual upgrades of legacy systems while preserving existing business behavior. Map dependencies and risks, create migration stages and routing code, and prepare tests, monitoring, and rollback procedures to validate each step.
中文简介正在准备中。当前显示英语简介。
Design cloud architectures and migration plans for AWS, Azure, and GCP. Produce service diagrams, selection rationale, security designs, cost estimates, and recovery strategies, with deployment and rollback plans that account for availability and operational monitoring.
中文简介正在准备中。当前显示英语简介。
Assess a fixed patch or pull request diff before merging. Trace affected behavior, evaluate regression risks, tests, and recovery options, then provide an evidence-based recommendation and advisory automatic-merge eligibility without modifying or merging the patch.
中文简介正在准备中。当前显示英语简介。
Write and maintain technical documents for different readers, including READMEs, API references, operational procedures, architecture explanations, and onboarding guides. Organize practical examples, setup steps, design decisions, and recovery instructions around what each audience needs.
中文简介正在准备中。当前显示英语简介。
Plan advertising budget allocation, bidding, and spending pace using goals, financial constraints, and evidence about additional spending returns. Compare options and produce a plan with amounts, timing, owners, success measures, and triggers for reversing changes.
中文简介正在准备中。当前显示英语简介。
Prepare Bifrost releases by turning Git history into release summaries and module changelogs. Coordinate version updates across dependent modules, document database migration risks, and include closed issues and outside contributor credits.
中文简介正在准备中。当前显示英语简介。
Plan commits around complete features, fixes, or documentation changes, keeping related tests and docs together. Split larger work into reviewable units with recorded verification results and clear boundaries for rolling back changes.
中文简介正在准备中。当前显示英语简介。
Improve CircleCI build and test pipelines by identifying slow or unreliable jobs, then adjusting caching, data sharing between jobs, triggers, and parallel execution. Receive incremental configuration changes with expected effects, validation criteria, and rollback guidance.
中文简介正在准备中。当前显示英语简介。
Assess a fixed code patch for behavior changes, regression risks, test coverage, and recovery options. Receive an evidence-based report and structured assessment indicating whether it is ready to merge and qualifies as an automatic merge candidate.
中文简介正在准备中。当前显示英语简介。
Design enterprise AI and automation product pages that explain permissions, approvals, audit records, and recovery from failures. Organize verified metrics and case studies, accessible workflow details, and demo or waitlist forms that clarify what happens next.
中文简介正在准备中。当前显示英语简介。
Plan and carry out agent deployments on Google Cloud using agents-cli. The guide covers deployment targets, permissions, secrets, automated build and deployment pipelines, verification, and recovery procedures for agents built with supported frameworks.
中文简介正在准备中。当前显示英语简介。
Draft or revise pull request descriptions that show the change, evidence of its behavior, and merge risks. Use concise diagrams, trees, or diffs alongside before-and-after results to help reviewers assess impact and how easily changes can be reversed.
中文简介正在准备中。当前显示英语简介。
Recover missed Observal session deliveries, upgrade or downgrade the command-line tool, and roll back version changes. After specified connection or configuration failures, it can also create local Agent files when explicitly requested.
中文简介正在准备中。当前显示英语简介。
Deploy code changes to a live hero training run by starting a new run from a permanent checkpoint, a saved training state. Compare matching training steps against agreed criteria and roll back if the trial fails.
中文简介正在准备中。当前显示英语简介。
Review plans, designs, or code by imagining how they could fail. Checks potential risks against surrounding context and existing safeguards, separates verified threats from false alarms, and helps decide whether to mitigate or accept them.
中文简介正在准备中。当前显示英语简介。
Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic` native or `worker` gRPC plugin, with deterministic validation and rollback-safe registration.
中文简介正在准备中。当前显示原文说明。
WARNING: guides IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets); every mutating step is governed by doca-hardware-safety (window, rollback). BlueField-4 only: BlueField-3 bring-up is doca-bf3-deployment. Use this skill for BlueField-4 (BF4) day-1 platform bring-up from the BMC: installing the BlueField/DOCA bundle ISO onto the DPU (Grace, the Arm complex) over UEFI HTTP Boot, PXE, or Redfish Virtual Media; the PLDM firmware-update flow (BMC, NIC firmware, SBIOS, ERoT) via the Redfish UpdateService and pldmtool; and a Grace Ubuntu image with optional cloud-init. Trigger on BlueField-4/BF4 bring-up phrasings even without "BF4": {bring up my new BlueField-4}, {the BlueField ISO will not boot over HTTP from the BMC}, {attach BF4 virtual media via Redfish}, {BF4 firmware Task stuck at Running}, {prepare a BlueField-4 host: platform support, version alignment, safest first smoke test}. Application launch and library APIs belong to other skills.
中文简介正在准备中。当前显示原文说明。
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter write, NIC firmware burn, BFB reflash, NIC ↔ DPU mode flip, SR-IOV or device-emulation slot enable, kernel boot-parameter change (IOMMU, hugepages, VFIO), PCIe rebind / rescan / link-state flip, BlueField cold reboot, or remediation of a BlueField thermal shutdown. Wrap the change in pre-flight inventory, OOB reachability, a maintenance window, replica rehearsal, and rollback. Trigger on implicit phrasing: "flip BlueField mode over SSH", "enable SR-IOV and reboot", "burned firmware but mlxconfig shows old value", "BlueField thermal shutdown". Not for read-only inventory or version queries (doca-version, doca-caps). Refuse orientation (doca-public-knowledge-map), install or env debug (doca-setup), and program-side debug (doca-debug, doca-programming-guide).
中文简介正在准备中。当前显示原文说明。
[omh] Decided cross-module refactor to phase: refactor planning - turn a decided boundary-changing refactor into a phased plan - reconnaissance, contracts-first phase order, per-phase verification and rollback, a files table, and an explicit approval gate before any edit. Use when the user says: refactor-plan, refactor plan, plan this refactor, plan the refactor, refactor planning, refactor phases, phased refactor, refactor in phases.
中文简介正在准备中。当前显示原文说明。
[omh] Shipping a versioned release -- tag it, stage it behind a canary, or roll back the last deploy: decide what goes in, the version, the rollout stages, and a rollback with its trigger and exact command before it is needed. Use when the user says: release-cut, release cut, cut a release, cut the release, cut a new release, tag a release, tag the release, release candidate.
中文简介正在准备中。当前显示原文说明。
[omh] Database work on a relational store -- a slow query, an index to size, a migration on a big table, a lock taken during deploy, N+1 queries: plan it with the checks that prove it safe, and never call a migration ready without its lock behaviour and rollback. Use when the user says: relational-db, relational database, online migration, migration for a large table, lock-safe ddl, alter table, took a lock, table lock.
中文简介正在准备中。当前显示原文说明。
[omh] Infrastructure-as-code change -- Terraform, OpenTofu, Pulumi, a Kubernetes manifest, a Helm chart: read the drift, the blast radius and the cost delta from the saved plan, then stage the apply behind a health gate with a rollback per stage. Use when the user says: iac-change, iac change, infrastructure as code, infrastructure-as-code, terraform plan, terraform apply, terraform state, terraform drift.
中文简介正在准备中。当前显示原文说明。
[omh] Imminent production launch or release: evaluate release, deploy, security, observability, rollback, docs, and support readiness without claiming production access. Use when the user says: production-audit, production audit, production readiness, prod audit, prod readiness, ready for production, ready to ship, ship readiness.
中文简介正在准备中。当前显示原文说明。
Use when the user asks to "monitor my launch", "track our Product Hunt / Hacker News ranking", or "watch the launch window"; runs the T-0 to T+30 window watch — pre-launch instrumentation verification (UTM/event checks, the upstream of RAMP P1), HN rank/points/comments polling with a comments-over-points flamewar early-warning (Estimated heuristic), PH votes/featured status, store charts and reviews, news echo, D0/W1/M1 KPI snapshots vs targets, spike-vs-sustain and owned-capture reads, and alert thresholds against the launch-tier KPI targets. Not for launch-day go/rollback calls — use launch-day-conductor; not for metric deep-dives — use performance-analyzer; not for SEO rank tracking — use rank-tracker. 发布监控/排名轮询/火焰战比/spike-sustain
中文简介正在准备中。当前显示原文说明。