516 个 · 按相关度排序
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.
中文简介正在准备中。当前显示原文说明。
DOCA-shipped Zero-Touch RoCE RTT congestion control (ZTR RTTCC) reference algorithm on a BlueField-3 DPA: deploy, tune and evaluate doca_pcc_dev_ztr_rttcc_algo through the shipped DOCA PCC sample. Trigger on "my RoCE-v2 flows aren't being throttled", "PCC sample isn't dispatching to my algo", "set-params returns fail", "algorithm loaded but counters are flat", "how do I pick the multipath PCC variant", or "do I need a custom CC algorithm on BF3", even without naming ZTR RTTCC. Your own algorithm through the host library belongs to doca-pcc; the doca_spcx_cc command line to doca-spcx-cc. Covers picking a variant (vanilla / PM / RX-rate / multipath / window-probeless) at DPACC build time, tuning host-set parameters, and DOCA_PCC_DEV_STATUS_FAIL from the algorithm. Refuse and route elsewhere for writing a custom PCC algorithm from scratch, read-only PCC counter inspection, or firmware-only pre-Programmable PCC.
中文简介正在准备中。当前显示原文说明。
Cross-platform issue triage. Pulls from Sentry (MCP), Linear (MCP), GitHub Issues (gh). Cross-references against code to find already-fixed issues. Auto-resolves fixed ones. Dispatches agents for active issues.
中文简介正在准备中。当前显示原文说明。
Autonomous multi-project orchestration engine. Audits all registered projects, structures work into dependency-wired tasks, dispatches parallel agents (subagents or Agent Teams), audits completions, and ships PRs. Registry-driven — works for any user with a configured project registry.
中文简介正在准备中。当前显示原文说明。
Production incidents dashboard. Reads ECS health, Sentry errors, CI failures. Offers to dispatch fix agents for active fires.
中文简介正在准备中。当前显示原文说明。
Autonomous PR merge pipeline. Scans all repos for open PRs, dispatches subagents to fix CI, resolve conflicts, address review comments, then merges. Use --main to also sync dev↔main branches.
中文简介正在准备中。当前显示原文说明。
Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code. Say 'check with codex' or 'ask gemini for a second opinion' and Claude runs the other agent, keeps a topic-aware session, and critiques the result.
中文简介正在准备中。当前显示原文说明。
Solves CTF challenges by performing first-pass triage, identifying the dominant category, and routing execution to the right specialized ctf-* skill. Use when the user gives you a challenge bundle, a remote service, a suspicious file, or only a vague challenge description and you must determine where to start. Do not use it when the category is already clear and a specialized skill can be invoked directly; this is the dispatcher and recon entrypoint, not the deepest reference for category-specific techniques.
中文简介正在准备中。当前显示原文说明。
Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work session. Also triggers in post-task feedback discussions and when the user mentions skill observations, the observation log, or skill taxonomy. Also known as "One Skill to Rule Them All" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a session-start hook (references/environments.md). A subagent dispatched by a session already running it does not run it: it writes nothing and puts its findings in its report.
中文简介正在准备中。当前显示原文说明。
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
中文简介正在准备中。当前显示原文说明。
Comet — OpenSpec + Superpowers dual-star development workflow. Start with /comet for automatic phase detection and dispatch to subcommands. Five phases: open → design → build → verify → archive.
中文简介正在准备中。当前显示原文说明。
Creates, reviews, and dispatches atomic work packets. Every task with a side effect requires an APPROVED packet before execution. Scope is immutable after approval — expansion requires a new packet.
中文简介正在准备中。当前显示原文说明。
Use for anything related to EAS Observe - adding `expo-observe` to an Expo project (AppMetricsRoot/ObserveRoot HOC, markInteractive and ObserveInteractiveMarker, the useObserve hook, the Expo Router / React Navigation integrations for per-route metrics, user-defined events via `Observe.logEvent`, error reporting via ObserveErrorBoundary and `Observe.reportError`, native crash reporting, source map upload for symbolicated stack traces, and runtime config such as sampleRate and dispatchInDebug), querying via the EAS CLI (`eas observe:metrics-summary`, `observe:metrics`, `observe:routes`, `observe:events`, `observe:session`, `observe:versions`, `observe:errors`, `observe:event`), interpreting the resulting metrics (cold/warm launch, TTR, TTI, navigation cold/warm TTR, update download, and the TTI frameRate/device/network params for triaging slow startups), or shipping an Observe integration inside a third-party package.
中文简介正在准备中。当前显示原文说明。
Guides performance investigation, benchmarking, and optimization of the Grida Canvas web editor (TypeScript reducer, Immer, React hooks). Use when profiling reducer dispatch cost, diagnosing slow interactions (drag, resize, color change), writing or running editor benchmarks, instrumenting with PerfObserver, or optimizing the JS-side state management pipeline.
中文简介正在准备中。当前显示原文说明。
Custom VM and bytecode reverse engineering playbook. Use when CTF challenges or protected software implement custom virtual machines with proprietary bytecode, dispatcher loops, or maze-style challenges.
中文简介正在准备中。当前显示原文说明。
Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or variant) dials. Discovers installed CLIs, proposes a lane map for user approval, and writes global or project config only after explicit yes. Use when the user asks to set up, configure, or reconfigure delegation lanes, a fleet of lanes, or which implementer handles feature/tests/ui work — not for dispatching a coding task to an implementer.
中文简介正在准备中。当前显示原文说明。
Use for day-ahead or multi-period unit commitment problems, including thermal on/off schedules, dispatch, startup/shutdown logic, minimum up/down time, ramping, spinning reserve deliverability, renewable curtailment, operating-cost accounting, and independent feasibility checks for power-system operations schedules.
中文简介正在准备中。当前显示原文说明。
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.
中文简介正在准备中。当前显示原文说明。
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.
中文简介正在准备中。当前显示原文说明。
Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.
中文简介正在准备中。当前显示原文说明。
Master Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices. Expert in the Julia ecosystem including package management, scientific computing, and high-performance numerical code. Use PROACTIVELY for Julia development, optimization, or advanced Julia patterns.
中文简介正在准备中。当前显示原文说明。
Build Unreal Engine 5 gameplay with Blueprint visual scripting: Blueprint Classes, the Event Graph and Construction Script, variables/functions/macros, and Blueprint communication (Cast, Interfaces, Event Dispatchers). Use when working in Blueprints, wiring an event graph, deciding how Blueprints talk to each other, or when the user mentions Blueprint, BP, event graph, construction script, or a Blueprint .uasset.
中文简介正在准备中。当前显示原文说明。
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
中文简介正在准备中。当前显示原文说明。
Use when diagnosing a Wake that failed, stalled, or produced no visible reply — dispatch, setup handoff, or reply-path issues. Routes to the deterministic trace evidence path.
中文简介正在准备中。当前显示原文说明。