1889 个 · 按相关度排序
Design specialized assistants that work with their own separate context. Define responsibilities, delegation conditions, working steps, and report formats for reusable subagents handling verification, debugging, security audits, or code reviews.
中文简介正在准备中。当前显示英语简介。
Investigate bugs by tracing symptoms through code and recent changes, reproducing failures, and testing a specific cause before fixing it. Produce a focused correction, a regression test to catch recurrence, and an evidence-based debugging report.
中文简介正在准备中。当前显示英语简介。
Guide AI agent development from requirements and project setup through implementation, behavior evaluation, deployment, and monitoring. Provides coding rules, debugging steps, and links to specialized skills so each phase follows a defined process.
中文简介正在准备中。当前显示英语简介。
Investigate bugs and failing tests through four stages: finding the root cause, comparing working patterns, testing a hypothesis, and implementing a fix. Uses reproduction steps, diagnostic evidence, and regression tests to check the result.
中文简介正在准备中。当前显示英语简介。
Guide Nexent backend design, implementation, debugging, and review across database schemas, FastAPI endpoints, services, and configuration. Check existing interfaces, consult references for each affected layer, and verify successful and failed behavior while preserving public contracts.
中文简介正在准备中。当前显示英语简介。
Apply a short quality checklist to everyday code changes. Read existing code first, keep edits focused, check types and common security risks, verify execution, remove debugging leftovers, and summarize what changed and its impact.
中文简介正在准备中。当前显示英语简介。
Route GitHub Agentic Workflows requests to the appropriate task guide. It selects prompts for design, creation, updates, debugging, or upgrades, with additional guidance for specialized tasks and repository-specific instructions when available.
中文简介正在准备中。当前显示英语简介。
Set up gh-aw, a GitHub CLI extension that turns Markdown workflows into GitHub Actions. The skill provides installation options and points agents to further instructions for creating, updating, debugging, and optimizing those workflows.
中文简介正在准备中。当前显示英语简介。
Set up one mirrord-up.yaml file to debug several related services locally at the same time. Define each application’s command, Kubernetes target, environment settings, and traffic mode, then manage the sessions together with mirrord up.
中文简介正在准备中。当前显示英语简介。
Operate a physical Android phone connected to OpenMausBot through authorized USB debugging. Open apps, read screens, tap controls, enter text, and swipe, checking the resulting screen after each action to support app testing and phone tasks.
中文简介正在准备中。当前显示英语简介。
Inspect Kiln’s interface in a real browser, capture screenshots, and run or debug end-to-end tests that check complete user flows. A sandbox with sample project data provides populated screens for checking UI changes.
中文简介正在准备中。当前显示英语简介。
Apply a compact checklist to everyday code changes. Read existing files first, keep edits focused, check types and security, verify execution, remove debugging leftovers, and summarize what changed and its impact.
中文简介正在准备中。当前显示英语简介。
Build research workflows that regenerate results from raw data with a single command. Organize project files, configure workflow tools, manage software environments and data versions, and prepare replication packages for journal submission.
中文简介正在准备中。当前显示英语简介。
Guide implementation, upgrades, and debugging by checking official documentation and local specifications first. Identify the relevant version, confirm supported behavior, and use those findings to produce an implementation or answer with appropriate validation.
中文简介正在准备中。当前显示英语简介。
Work with AI as a coding partner, choosing who writes code and who guides the work. Supports role switching, test generation, ongoing code review, debugging, and step-by-step explanations for learning.
中文简介正在准备中。当前显示英语简介。
Investigate bugs, failing tests, and unexpected behavior before proposing changes. Follow four stages to gather evidence, compare working examples, test a specific cause, and verify a focused fix with a test that reproduces the problem.
中文简介正在准备中。当前显示英语简介。
Establish a routine for checking and invoking relevant skills before answering or taking action. It prioritizes skills that define the workflow, then guides the agent toward task-specific skills and any checklists they contain.
中文简介正在准备中。当前显示英语简介。
Drive repeated debugging cycles with the required diagnose skill: establish evidence for a cause, choose one focused fix, and rerun the original validation. Reassess after each change until no credible fix remains or further progress requires user input.
中文简介正在准备中。当前显示英语简介。
Deterministic debugging with rr record-replay. Use when debugging crashes, ASAN faults, or when reverse execution is needed. Provides reverse-next, reverse-step, reverse-continue commands and crash trace extraction.
中文简介正在准备中。当前显示原文说明。
Runs a hypothesis-driven debugging loop across any language or binary, escalating to orthogonal oracle angles and locking the fix with a failing test. Use for crashes, silent failures, hangs, wrong responses, memory leaks, async misbehavior, or reverse engineering.
中文简介正在准备中。当前显示原文说明。
Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent __syncthreads/__syncwarp, or cuda::barrier / wgmma issues. Do NOT use for host/CPU-side bugs (use valgrind or AddressSanitizer) or global-memory data races (out of scope). Trigger keywords - compute-sanitizer, memcheck, racecheck, initcheck, synccheck, CUDA memory error, OOB, race condition, uninitialized memory, __syncthreads, barrier, deadlock.
中文简介正在准备中。当前显示原文说明。
Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.
中文简介正在准备中。当前显示原文说明。
Use this skill when the user is dealing with the DOCA environment around their workload — verifying an install is healthy, preparing the build env (pkg-config, headers, LD_LIBRARY_PATH, hugepages, devlink, representors), debugging env-class failures, deciding container-vs-bare-metal deployment shape, or reaching a DOCA install from a host that doesn't have one yet via the NGC DOCA container Stage-1 fallback. Trigger even when the user does not explicitly mention "DOCA setup" — typical implicit phrasings include "just got a BlueField, what now", "code is built, how to run it", "pkg-config can't find doca-flow", "no free 2048 kB hugepages", "representor X not found", "on a Mac and want to learn DOCA". Refuse and route elsewhere for library API specifics (Flow pipes, RDMA queues), the modify-a-sample first-app workflow or DOCA_ERROR_* program-side debugging, and "where is X documented" knowledge-map questions — those belong to other skills.
中文简介正在准备中。当前显示原文说明。
[omh] Agent is stuck, looping, or drifting: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recovery action. Use when the user says: agent-debug, agent debug, agent debugging, agent introspection, agent self-debug, self-debug, self debugging, looping agent.
中文简介正在准备中。当前显示原文说明。