Expert guidance on Nix, NixOS, home-manager, flakes, and Nix packaging. Use when writing or debugging Nix expressions, configuring NixOS or home-manager, authoring derivations, managing flake inputs, encrypting secrets with agenix or sops-nix, or hardening a NixOS host. Triggers on Nix, NixOS, nixpkgs, home-manager, flake.nix, nixos-rebuild, nix build, nix develop, devShell, derivation, overlay, agenix, and on Nix errors such as hash mismatches, infinite recursion, or evaluation failures. Advisory rather than generative: it explains, reviews, and debugs. If the repository provides its own skill for authoring host configurations, prefer that for writing config.

Defines model-callable tools and renders their calls in assistant-ui. The authoring model: a "use generative" file whose default export is defineToolkit({...}), compiled by withAui from @assistant-ui/next, aui() from @assistant-ui/vite, or withAui from @assistant-ui/metro, mounted with AuiConfig({ tools: Tools({ toolkit }) }), and exposed to the model with new AISDKToolkit({ toolkit }).tools({ frontend }). Covers the tool kinds (backend, "use client" frontend, humanTool(), providerTool(), externalTool(), stubTool(), defineMcpToolkit()), render and display, ToolCallMessagePartProps, approval gates, MCP servers, MCP Apps, WebMCP, and sub-agent messages. Reach for it when a tool is never called, a tool UI does not render, a frontend result never reaches the model, humanTool() throws at runtime, or an approval gate cannot be answered. For model-composed UI use generative-ui, for MCP servers users add in the browser use react-mcp, and for the styled ToolFallback and ToolGroup use elements.

This skill should be used when the user asks to "merge a PR", "review and merge pull requests", "integrate external contributions", "handle PR conflicts", "cherry-pick from a PR", or needs to merge GitHub PRs while maximizing contributor attribution.

How to use the `@gate` / `@force-gate` test directives instead of `it.skip` or fake-green skip patterns. Use when a test is known-failing under some test-matrix dimension (dev mode, a bundler, an experimental flag like cacheComponents), when converting `if (isNextDev) return` guards or env-var `describe.skip` branches, when adding a condition to test/lib/gate/conditions.ts, or when keying a fixture's experimental flag on a __NEXT_TEST_AXIS letter. Covers directive choice, condition tiers, the test-axis fixture pattern, pitfalls, and verification commands.

Show the app connection picker or setup widget when users ask to connect apps, reopen setup, or need an app that isn't connected yet. Use QM’s authenticated backend for app discovery, consent, and execution without exposing project keys.

Domain knowledge for triaging and fixing .NET failures on Apple mobile (iOS, tvOS, MacCatalyst) and Android. Use when runtime-extra-platforms or mobile CI is failing, when investigating iOS, tvOS, MacCatalyst, iossimulator, tvossimulator, or Android build/test failures, or when a change touches mobile pipeline YAML, AppleAppBuilder/AndroidAppBuilder, code signing, provisioning, simulator/emulator startup, platform conditionals, or NativeAOT-on-mobile behavior. Covers failure triage (infrastructure vs code), CI pipeline structure, platform-specific code paths, and NativeAOT compilation on mobile.

Guidance for writing and modifying Microsoft.Extensions.* and System.IO.Compression code in dotnet/runtime. Covers DI lifetime management, configuration binding, options validation, logging provider patterns, caching semantics, compression format compliance, and host lifecycle. For full code review, delegates to the @extensions-reviewer agent. Trigger words: Microsoft.Extensions, IServiceCollection, IConfiguration, ILogger, IHost, IMemoryCache, IOptions, ZipArchive, HttpClientFactory, IFileProvider, IChangeToken.

Link workspace packages in monorepos (npm, yarn, pnpm, bun). USE WHEN: (1) you just created or generated new packages and need to wire up their dependencies, (2) user imports from a sibling package and needs to add it as a dependency, (3) you get resolution errors for workspace packages (@org/*) like "cannot find module", "failed to resolve import", "TS2307", or "cannot resolve". DO NOT patch around with tsconfig paths or manual package.json edits - use the package manager's workspace commands to fix actual linking.

Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.

Show whether Mem0 memory is working in this repository, covering configuration, capture state, pending flushes, and whether the Mem0 API key is valid. Use when the user asks whether memory is on, why a memory is missing, or anything looks broken.

Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.

Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.

Acknowledge a "remember this" request and make sure it is captured well. Use when the user explicitly asks to remember, note, or save something for future sessions.

Convert a docker-compose.yml (e.g. from Umbrel, CasaOS, linuxserver.io, or an upstream repo) into a self-contained, strictly confined snap suitable for publishing in the Snap Store. Use when asked to "snap" a compose-based app, translate compose services into snapcraft parts/daemons, or package a multi-container web app (app server + postgres + redis + workers) as a single snap.

Scaffold a new in-house Folia/Paper plugin for the FoliaNexa cluster (folia-server repo), either from a feature description or by pointing at an existing mod/plugin on Modrinth and producing an original, Folia-native plugin that replicates its player-facing behavior. Use when a developer asks to create/write/build/port a plugin for this cluster, or says something like "make a plugin like <modrinth URL>" / "port this mod to Folia". Covers requirement gathering, the Modrinth lookup + feature-triage procedure (and its legal/ethical boundaries — never copy source, always disclose inspiration), the Gradle/Java 21/paper-api project skeleton, Folia-safe RegionScheduler/GlobalRegionScheduler/AsyncScheduler usage, and wiring the finished plugin toward mgmt/src/folia_mgmt/catalog.yaml per docs/plugin-dev/03-submitting-for-review.md.

Use when a local AI agent needs to reach into a remote Linux server over SSH — to explore data, run commands, inspect logs, diagnose something on the server, or pull data down to the local machine — or to set up that SSH access for the first time. Triggers include "luffy-arm", "connect to my server", "ssh into the remote box", "explore/poke around the server", "run this on the server", "download/fetch data from the server", "set up remote access", "reverse remote-ssh", 远程服务器, 远程开发. Not for purely local work, and not for moving the agent or its config onto the server.

Use sem for entity-level (function/class/method) code questions in any Git repo. Four questions, four verbs - where is it (sem find, sem grep), what does my change touch (sem impact), is it correct (sem check), what should a human review (sem certify). Trigger whenever the user asks where something is defined or called, what a change breaks or which tests to run, whether a change is correct, what changed in a commit or PR, or what to review; also use it proactively before refactors and in code review, where line-level git output is noisy.

Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for `$ccb_diagnose agentname`, `$ccb-diagnose agentname`, or reports that a CCB agent is stuck, disconnected, not continuing, not replying, or showing provider errors.

Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for `$ccb_diagnose agentname`, `$ccb-diagnose agentname`, or reports that a CCB agent is stuck, disconnected, not continuing, not replying, or showing provider errors.

Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for `$ccb_diagnose agentname`, `$ccb-diagnose agentname`, or reports that a CCB agent is stuck, disconnected, not continuing, not replying, or showing provider errors.