效率与工作流
1,947 个结果
- Awf Release IntegratorGitHub官方Upgrade gh-aw to latest gh-aw-firewall release and identify follow-up spec tasks.
- Copilot ReviewGitHub官方Teach Copilot how to plan, address, and respond to pull request review feedback.
- Cross Squad CommunicationGitHub官方Protocol for sending queries, delegating tasks, and sharing context between independent Squad instances across different repositories
- Developer ReleaseGitHub官方Release management, changeset workflow, firewall log parsing, breaking CLI change rules, and Go module summaries for gh-aw.
- External CommsGitHub官方PAO workflow for scanning, drafting, and presenting community responses with human review gate
- Git WorkflowGitHub官方Squad branching model: dev-first workflow with insiders preview channel
- Github Workflows QueryGitHub官方List GitHub Actions workflows with per_page pagination support.
- Project ConventionsGitHub官方Core conventions and patterns for this codebase
- ReportingGitHub官方Report formatting guidelines for gh-aw workflows (header levels, collapsible details, run-ID links)
- Resolve Merge ConflictsGitHub官方Merge a base ref and safely regenerate compiled workflow lock-file conflicts.
- Restricted Tool TriageGitHub官方Operate safely and efficiently inside a gh-aw workflow with a restricted tools/bash allowlist, and correctly triage tool-denial events before they exhaust the session's denial budget.
- Reviewer ProtocolGitHub官方Reviewer rejection workflow and strict lockout semantics
- Temporary Id Safe OutputGitHub官方Plan for adding temporary ID support to safe output jobs
- Eli5Cloudflare官方Transform technical jargon into clear explanations using before/after comparisons, metaphors, and practical context
- Cupynumeric Migration ReadinessNVIDIA官方Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning.
- Dali Dynamic ModeNVIDIA官方DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.
- Doca CompressNVIDIA官方Hardware compression offload with DOCA Compress on a BlueField DPU, ConnectX NIC, or host: DEFLATE compress and decompress, plus LZ4 decompress (stream and block; LZ4 encode is NOT supported), instead of CPU zlib / zstd.
- Doca VerbsNVIDIA官方Raw verbs inside DOCA Core (doca-verbs): direct control of QP, CQ, PD, SRQ and address-handle objects through doca_verbs_context, doca_verbs_qp_create / doca_verbs_qp_modify and doca_verbs_cq_create, porting libibverbs code into DOCA Core, or a QP attribute, opcode or WR flag the doca-rdma task API does not expose.
- Earth2studio Create DatasourceNVIDIA官方Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
- I4h Workflow CreateNVIDIA官方Create a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode. Use for fast new Workflow scaffolding.
- I4h Workflow FinetuneNVIDIA官方Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or checkpoint rollout.
- I4h Workflow Scene EditNVIDIA官方Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create a new workflow.
- I4h Workflow Train RlNVIDIA官方Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff.
- Jetson Headless ModeNVIDIA官方Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.