moeru-ai

Write grouped, user-friendly release notes from git history, changelogithub output, GitHub releases, PR lists, or raw commit logs. Use when Codex needs to turn technical changelogs into English-only release notes for AIRI or similar products, including…

Enforce AIRI's rules for time in render loops. Use when you write or review motion, reaction, animation, spring, or effect code that a Pixi (Live2D), TresJS (VRM), or Three (MMD) frame loop samples, or when an event outside the loop starts an effect that a…

Read and analyze AIRI IO traces that Tamagotchi saved to local files. Use when the user asks why a chat, speech, or audio turn was slow, failed, or behaved wrongly, and recording is enabled in Settings > System > Developer.

Use when Codex needs to inspect, debug, or automate an Electron app through `agent-browser` and Chrome DevTools Protocol, especially when the app has multiple `BrowserWindow` instances, lazy-created windows, duplicate URLs, or misleading `agent-browser tab…

Run AIRI-owned Vishot scenarios for stage-web or stage-tamagotchi, including skipping first-run onboarding and importing a local Live2D, VRM, or MMD display model before capture. Use when AIRI visual evidence must exercise a contributor-supplied avatar file…

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector,…

Prepare and create an AIRI pull request with verifiable change context, architecture evidence, and required visual evidence. Use when Codex must open, create, publish, or prepare a PR from the current branch.

Review pending AIRI translations on Crowdin in a batch, then sync them into the repository. Use when Crowdin has translations that wait for approval, when translations have not reached the repository for days, or when the user pastes output of…

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

kwaa's TypeScript best practices. Use when reading or editing .ts or .tsx files.

Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".

Generate or stream speech and transcribe recordings with xsAI's audio package.

Ask typed questions about an input with xsAI, such as classification, routing, policy checks, or rating. Answers are probabilities, choices, or scores.

Create text embeddings with xsAI for one string or a batch.

Generate images from text prompts with xsAI's image package.

Automate desktop applications with AUV. Use for screenshots, OCR, mouse and keyboard input, reusable GUI workflows, or operations on a paired AUV Device.

Use when explaining, creating, or changing a Pixi workspace, including manifests, dependencies, platforms, targets, features, environments, tasks, lockfiles, editable Python packages, CI commands, or IDE interpreter setup.

Prepare or update AUV pull requests with source-backed CLI, Protobuf/Runner, and public API change disclosures, before-and-after usage, and migration notes. Also use for retrospective API audits of specified PRs or revisions.

Prepare, diagnose, and validate Linux GPU and Wayland environments for AUV rendering and capture through XDG Desktop Portal and PipeWire. Use when installing AUV desktop runtime dependencies, connecting from another machine over SSH, using an existing…

Use this skill to generate well-branded interfaces and assets for AUV (the Moeru AI command-replay / inspect runtime), either for production or throwaway prototypes/mocks. Contains essential design guidelines, colors, type, fonts, assets, and UI kit…

Design, change, and review Protobuf schemas used as gRPC contracts, streaming protocols, typed data models, grpc-gateway REST APIs, OpenAPI specifications, or generated SDK inputs. Use for .proto files, RPC request/response design, oneof stream events,…

Select, pin, configure, install, build, and troubleshoot Buf code-generation plugins across remote BSR and local execution. Use for buf.gen.yaml plugin entries, protoc-gen-* tools, generated Go/Python/TypeScript/OpenAPI outputs, offline generation, BSR…

Configure, inspect, update, validate, and troubleshoot Buf workspaces and modules. Use when working with buf.yaml, buf.lock, buf.gen.yaml or domain-specific Buf generation templates; managing BSR dependencies; formatting, linting, generating, detecting…

Capture deterministic screenshots with the installed Vishot CLI and return a reproducible artifact manifest. Use for UI inspection, visual evidence, documentation images, or screenshot comparison across browser, Electron, and Capacitor applications.

Capture deterministic Capacitor application surfaces with Vishot while distinguishing browser-rendered WebView evidence from native-shell evidence. Use for mobile routes, responsive states, or Capacitor UI verification.

Capture deterministic Electron windows with Vishot. Use when an Electron application must be launched, a semantic window selected, or a product-owned Playwright scenario run before capture.

Prepare and capture a deterministic UI state that depends on selecting a local file. Use with Vishot when an Electron scenario, fixture route, or scene app must represent an import, upload, or open-file workflow.

Capture deterministic browser routes or Vite capture roots with Vishot. Use when a locally runnable web surface can reach the requested state at load time or through product-owned fixture routes and scene apps.

Use when explaining, creating, or changing a Pixi workspace, including manifests, dependencies, platforms, targets, features, environments, tasks, lockfiles, editable Python packages, CI commands, or IDE interpreter setup.

Use when a Pixi-managed project needs PyTorch but the host backend is not yet selected, including NVIDIA driver or GPU inspection, Apple Silicon MPS detection, CPU fallback, or post-install device verification.

Run and inspect the LoCoMo event segmentation debugger in `crates/event_segmentation/examples/locomo_segmenter.rs`. Use when debugging `EventSegmenter`, checking segment boundaries on LoCoMo samples, inspecting the emitted event-segment JSON array, slicing or…

Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, handle mentions, direct messages, subscribed threads, reactions, slash…

Guide for using injeca — a pure functional dependency injection library with application lifecycle management, inspired by go.uber.org/dig and go.uber.org/fig. Use this skill whenever the user imports from 'injeca', mentions injeca, needs dependency injection…

Prepare and publish coordinated Kirie releases across kirie-templates and godot-kirie. Use when a user requests a Kirie version release.

Upload a local image or file to GitHub's user-attachments storage and return a URL suitable for issue, pull request, discussion, or comment Markdown. Use when Codex must embed local screenshots, videos, logs, or other evidence in GitHub content without…