Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.

Review changes that affect how the carnival looks (UI routes, shared styles, drawing code and art) against the visual design baseline. Use on pull requests that touch index.html, src/main.ts, src/style.css, any src/**/*.ts that draws to a canvas, or anything under docs/visual-baseline.

RDMA data movement on NVIDIA BlueField/ConnectX NICs (RoCE/InfiniBand) with DOCA RDMA, instead of hand-written libibverbs/rdma_cm. Use when the user moves data between processes or hosts over the NIC, or hits "one-sided read returns permission denied", "completions never arrive after submit", "connection callback never fires", atomic compare-and-swap over RoCE, or DOCA_ERROR_FULL on the send queue under burst, even without naming DOCA RDMA. Covers bringing up an RDMA context on a doca_dev, connection methods (RDMA CM, bridge/OOB, or gRPC exchange of doca_rdma_export()), the eleven task types (Send/Receive/Send-Imm, Read/Write/Write-Imm, Atomic CmpSwap/FetchAdd, Get/Set/Add Remote Sync Event), matching mmap + RDMA permissions, queue and connection sizing, doca_rdma_cap_* queries, and DOCA_ERROR_* from RDMA calls. Raw QP/verbs control belongs to doca-verbs. Refuse and route elsewhere for general RDMA / ibverbs theory (queue pairs, MRs, RoCE vs IB), installing DOCA itself, or non-RDMA DOCA libraries.

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).

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Selecting WHO handles work is the Routing table; selecting HOW they handle it (Direct, Lightweight, Standard, Full) is Response Mode. This skill contains the complete decision table, exemplar prompts for each mode, the Lightweight spawn template, and the upgrade rules. Squad coordinator loads this on demand once routing has identified the agent — to pick the right ceremony level for the task.

Use this when working on the VS Code integrated browser ("browserView") to understand its architecture and mental model. Covers the embedded Chromium browser, its editor tab, navigation, overlay/layout, sessions, and agent browser tools under `src/vs/platform/browserView` and `src/vs/workbench/contrib/browserView`.

Use when asked to write or create an ai_eval test under test/ai_evals/ for an evaluation use case in test/ai_evals/eval_data/evals/. Works across all DevTools domains (performance, network, elements, sources, console, accessibility, storage). To minimize latency, in your FIRST turn call view_file in parallel on SKILL.md, task.textproto + agent_prompt.md for <eval-id>, and test/ai_evals/BUILD.gn (plus test/ai_evals/<domain>/BUILD.gn if <domain> is known).

Publish a GitHub release for the C# MCP SDK after a prepare-release PR has been merged. Refreshes release notes to include any PRs merged since preparation, warns about version or breaking change impacts from late-arriving PRs, and creates a draft GitHub release. Use when asked to publish a release, finalize a release, create release notes, or complete a release after the prepare-release PR has been merged.

Workflow, guardrails, and output format for reviewing NIC pull requests. Use when reviewing a PR locally (Copilot Chat, Claude, or other agent), when running the pr-review prompt, or when acting as the GitHub Copilot Code Review bot. Delegates codebase-specific detail to the domain skills (nic-structure, nic-add-feature, nic-add-policy, nic-docker-images, nic-ci-pipelines, nic-testing) rather than duplicating them.

Plan, write, and review VS Code blog posts. ALWAYS use this skill when the user asks to "write a blog post", "draft a blog", "add a blog post for", "review this blog post", or provides a feature/issue/PR to announce on the VS Code blog. For new posts, it proposes an outline and asks clarifying questions first, and does not edit any files until you approve the plan.

Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as agent-browser.dev and portless.sh. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

Write, review, and edit developer documentation for SDKs, libraries, and frameworks, including sites such as ai-sdk.dev and chat-sdk.dev. Use for getting-started guides, tutorials, API references, conceptual explanations, integration guides, migration guides, troubleshooting, and code examples.

Launch an independent Fable code review and return it verbatim. Use only when the user explicitly invokes /fable-review.

Make a still portrait speak from supplied audio with Magic Hour Talking Photo, or lip-sync existing video to replacement audio. Use when Magic Hour is requested or configured and suitable. Both routes require audio; neither synthesizes speech from text. Preserve an explicitly requested alternative provider.

Make a Basic Memory project ready for OKF v0.2 export by finding and fixing what blocks it. Use when preparing a project for OKF export, publishing, or handoff, or checking an OKF bundle.

Concrete, per-area proof that a change actually works before reporting it fixed, done, or "should work now" — which dev server, test command, or invocation proves a template UI change, an action, a migration, a guard, or a core/package change. Use before every wrap-up, and before stopping mid-task to ask permission instead of continuing.

Framework-wide voice dictation in the agent sidebar composer. Use when changing composer microphone UX, the transcribe-voice route, or the Voice Transcription settings section. Covers transcription-source routing, cleanup routing, Google realtime gating, and the voice transcription application-state keys.

知易知识库 → 短视频 流水线。把 knowledge_cards（蓝/绿/红卡）批量生成书摘/知识类短视频（复用 MoneyPrinterTurbo），并提供本地 faster-whisper 转写桥，把任意视频转文字入库成为脚本源。触发：用户想"把书/知识库做成视频""批量产出书摘视频""把视频转写进知识库"。

Use when writing or adding Vitest tests for Positron src/vs/ or extensions/ code, checking a branch/PR for test-coverage gaps, or testing React components with RTL.