754 个 · 按相关度排序
Add personality to interfaces through small interaction responses, completion animations, illustrations, and product-specific messages. Shape enjoyable moments around the brand and user context while preserving task flow, accessibility, and performance.
中文简介正在准备中。当前显示英语简介。
Design and improve welcome flows, empty screens, and guided tours that help new users complete their first useful task. Includes contextual hints, optional guidance, completion tracking, and ways to assess whether users understand what to do next.
中文简介正在准备中。当前显示英语简介。
Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.
中文简介正在准备中。当前显示英语简介。
Guide agent replies in Matrix chat rooms, including when to mention a coordinator, report completion, raise blockers, or answer questions. The rules limit repetitive acknowledgments and stop exchanges that add no new task, question, or decision.
中文简介正在准备中。当前显示英语简介。
Turn ready project tasks into clear instructions for AI workers, with defined ownership, deliverables, acceptance criteria, and reporting rules. Handle assignment notifications and check submitted results before passing them to the project management workflow for acceptance.
中文简介正在准备中。当前显示英语简介。
Help an agent join a shared project by reading the project plan, identifying assigned tasks and dependencies, recording work, and reporting completion to the coordinator. It also covers Git author settings so each worker's contributions can be identified.
中文简介正在准备中。当前显示英语简介。
Manage terminal work across panes: open jobs, run commands, read output, and wait for completion. Report agent status, exchange messages, and request human decisions through tuios, a terminal window manager with a background service.
中文简介正在准备中。当前显示英语简介。
Write and revise documents that guide AI agents, including skills and AGENTS.md files. Organize steps, define checkable completion criteria, and clarify when to load references so agents can follow a consistent process across different tasks.
中文简介正在准备中。当前显示英语简介。
Build Claude Code plugin hooks: automated checks triggered by tool use or session events. Get guidance on prompt and command hooks for validating actions, checking task completion, loading context, and testing configurations.
中文简介正在准备中。当前显示英语简介。
Write or review skills for a consistent process across runs. Check activation conditions, ordered steps, completion criteria, and reference placement, then identify unclear instructions, overlapping triggers, and content that belongs in an existing skill.
中文简介正在准备中。当前显示英语简介。
Coordinate AI agents running in Herdr workspaces inside Ghostty. Inspect terminal output and agent status, send instructions, wait for completion, share missing context, and combine results into one summary while avoiding duplicate work.
中文简介正在准备中。当前显示英语简介。
Checks whether work is truly complete before reporting success, committing changes, or creating a pull request. It runs the relevant checks, reads their full output, and ties status reports to current evidence.
中文简介正在准备中。当前显示英语简介。
Review and fix concurrency issues in Swift 6.2+ code, including compiler errors and unsafe shared data. Apply actor isolation, which controls access to state, and separate UI updates from background work while preserving existing behavior.
中文简介正在准备中。当前显示英语简介。
Turn a bug report, improvement request, or experiment into a structured GitHub issue. Check for duplicates, write reproduction steps or testable completion criteria, apply suitable labels, and verify the published title and body.
中文简介正在准备中。当前显示英语简介。
Restructure an existing SKILL.md into v5 Hybrid format. Four agents use indexed reference books to identify workflow states, actions, decision rules, constraints, and completion conditions, then combine their findings into an upgraded skill and validation report.
中文简介正在准备中。当前显示英语简介。
Manage background agents without repeatedly checking whether they have finished. The skill directs the main agent to continue other work, rely on completion notifications, and inspect status files when results are needed or the user asks for an update.
中文简介正在准备中。当前显示英语简介。
Coordinate parallel agents running in the background while keeping lengthy results out of the main conversation. Track completion through shared status files, store detailed findings separately, and organize work into batches of up to 15 agents.
中文简介正在准备中。当前显示英语简介。
Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready. Requires fresh verification output before success claims. Do not use for root-cause debugging, TDD implementation, test-report packaging, or review-feedback triage.
中文简介正在准备中。当前显示原文说明。
Verify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a feature is ready for GO.
中文简介正在准备中。当前显示原文说明。
Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_dpa_completion`, running `doca_dpa_cap_*` discovery, choosing between the DPA comm component (inter-DPA messaging) and the DPA verbs component (in-kernel RDMA), or debugging `DOCA_ERROR_*` from `doca_dpa_*`. Trigger even without "DOCA DPA" or "Data-Path Accelerator": "run compute on the DPA from my host", "DPA kernel hangs, no completion", "DOCA_ERROR_DRIVER on launch", "DOCA/DPACC version skew", or "does this BlueField expose a DPA". Route elsewhere for DPA-side kernel programming itself, DPACC compiler internals, host↔DPU messaging (doca-comch), host-side RDMA (doca-rdma), and GPU-initiated networking (doca-gpunetio).
中文简介正在准备中。当前显示原文说明。
Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + file_size_limit_policy, thread priorities/cores), decoding against the matching DPA-side ELF, or diagnosing empty/noisy captures. Trigger even when the user does not explicitly mention "DOCA DPA tracer" or "high-level tracer" — typical implicit phrasings include "DPA kernel returns wrong result but host completions look clean", "kernel-entry to first-comm latency is huge", "RDMA WR to drain gap on the DPA", "trace file truncated mid-run", "TRACE doubled my DPA latency", or "tracer wrote a file but parser shows zero events". Refuse and route elsewhere for writing DPA kernels, DPA-Comms/DPA-Verbs programming, raw per-cycle DPA profiling, host-side doca-dpa debugging, or production DPA telemetry — those belong to other skills.
中文简介正在准备中。当前显示原文说明。
[omh] Completion claim tested by Jev: Jev done check: does the gathered evidence support the completion claim? It can only object. Use when the user says: jev-done-check, jev done check, ask jev if this is done, jev evidence check.
中文简介正在准备中。当前显示原文说明。
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants. Triggers: "Azure OpenAI", "AzureOpenAIClient", "ChatClient", "chat completions .NET", "GPT-4", "embeddings", "DALL-E", "Whisper", "OpenAI .NET".
中文简介正在准备中。当前显示原文说明。
Use when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion claims.
中文简介正在准备中。当前显示原文说明。