pawrrtal-ai

Use when changing, extending, testing, or reviewing the Bun-backed Paw CLI package and its generated agent skills.

Use when writing or reviewing Pawrrtal Effect TypeScript code in backend-ts: API contracts, HttpApi handlers, services, repos, layers, tagged errors, Effect tests, streams, SQL, auth middleware, or vendor-source API checks.

Use when running the Bun-backed Paw CLI: local health, active context, shell completions, output modes, profiles, and verification of the supported command surface.

Turn a bad or long Pawrrtal work session into durable project learning. Use when the user says $retro, asks to learn from a session, says too much went wrong, or asks to create/update skills or rules from recent failures.

Use when touching Pawrrtal channels, providers, tools, plugins, subagents, context providers, turn orchestration, or code that decides where an integration should live. Enforces the split between generic kernel code, manifest plugins, trusted runtime adapters, provider adapters, channel adapters, and agent runtime primitives.

Operate Pawrrtal as a live service: prove the running commit, local origins, Cloudflared public URL, database schema, Telegram channel, and shutdown state. Use when checking whether Pawrrtal is live, deployed, reachable, healthy, broken in Telegram, safe to restart, or safe to take down.

Apply Pawrrtal-specific taste rules for clean modern UX, CLI output, Telegram rendering, and agent/tool presentation. Use when changing UI copy, visual polish, CLI labels, Telegram flow output, tool names, folder/file listings, thinking/tool rendering, or when generalizing user feedback into repo conventions.

Use when planning creative, ambiguous, or multi-step work: new features, components, behavior changes, refactors, or any task whose requirements need clarifying before implementation.

Use when creating, editing, restructuring, or reviewing AGENTS.md files or the CLAUDE.md symlink. Covers Pawrrtal's two-tier layout, what belongs in AGENTS.md vs memory vs skills, and line budgets.

Use when writing or reviewing Pawrrtal code: naming booleans and callbacks, shaping function signatures, adding TSDoc/JSDoc, splitting files, choosing readonly params, or deciding how to verify a change. Covers frontend (Next.js/TS), Python backend, and backend-ts Effect strangler. Stack-specific skills refine these rules.

Use when creating or modifying GitHub Actions workflows for Pawrrtal. Covers mandatory OctavianTocan actor gate, self-hosted runner defaults, pull_request_target exception, and where CI jobs must live. For VPS runner launch/cleanup, use runner-ops.

Use when creating, editing, pruning, or curating path-scoped rule files under .agent/rules/. Covers YAML paths frontmatter, category layout, CURATED.md, and harness symlinks (.claude/rules, .agents/rules).

Use for Pawrrtal repo workflow: beans issue tracker, git and PR policy, multi-agent safety, sentrux architecture gates, extension-boundary summaries, commit conventions, and the no-pre-existing-excuse rule. Load before beans tasks, parallel-agent work, structural refactors, or CI workflow authoring.

Use when Pawrrtal local dev, auth, deployment routing, or domain vocabulary questions come up during a task. Read memory/semantic/DOMAIN_KNOWLEDGE.md first; this skill adds task-triggered pointers to domain-effect and live-ops.

Create new AI chat interface components for the ai-elements library following established composable patterns, shadcn/ui integration, and Vercel AI SDK conventions. Use when creating new components in packages/elements/src or when the user asks to add a new component to ai-elements.

This skill should be used when the user asks to "configure Biome", "extend biome config", "set up BiomeJS", "add biome overrides", "biome lint-staged", "fix biome errors", or mentions biome.jsonc, Biome linting, or Biome formatting configuration.

Guide AI agents through Electron app development with React including security patterns, type-safe IPC, React integration, packaging with code signing, and testing. Keywords: electron, electron-vite, electron-forge, contextBridge, IPC, security, react, packaging, code signing, notarization, playwright, desktop app.

Build cross-platform desktop applications with Electron, covering main/renderer process architecture, IPC communication, BrowserWindow management, menus, tray icons, packaging, and security best practices. Use when the user asks about Electron, needs to create desktop applications, implement Electron features, or build cross-platform desktop apps.

Retrieve and search meeting summaries, transcripts, and action items from Fireflies.ai. Use when asked to check recent meetings, search for specific topics discussed in meetings, or get transcripts/details of a meeting.

Audit whether Pawrrtal work is actually in the intended PR and matches the user's full requested scope. Use when continuing long goals, answering "is everything in this PR?", before saying a PR is ready, after operational VPS work, or whenever implementation, CI, reviews, live deploy, and runtime checks are mixed together.

Guardrail for dry-python/returns in pawrrtal. Use when an agent proposes Maybe, Result, IOResult, FutureResult, railway-oriented error handling, or adding the returns dependency.

Operate Pawrrtal self-hosted GitHub Actions runners safely. Use when starting, stopping, installing, debugging, replacing, scaling, cleaning, or checking CI runners for Pawrrtal, especially on the VPS mounted volume.

Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.

Use when adding, modifying, generating, checking, or debugging repo-local skill fragments embedded in source code with //<skill-gen> markers.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Teach the user a new skill or concept, within this workspace.

Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation frameworks; analyzing coverage gaps; performance testing with k6 or Artillery; security testing with OWASP methods; debugging flaky tests; or working on QA, regression, test automation, quality gates, shift-left testing, or test maintenance.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Write and review user-facing text across Pawrrtal's surfaces (Telegram, Google Chat, Web). Use when adding or editing any string a user sees — tool or action display names, command labels, buttons, status lines, error messages, cards, notices — or when reviewing copy. Enforces Title Case "Tool Name" for tool/action names (never tool_name or "Tool name"), American spelling, and consistent labels across channels.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

General coding patterns and conventions.

Testing patterns and best practices.

Manage and schedule recurring workspace heartbeats and database-bound reminders.

First-run setup for a new Pawrrtal workspace.

Maintain the Paw's name, voice, style, emoji, and working preferences.

Ports Telegram-style tileable SVG preset masks plus a procedural SVG tile generator into a Next.js App Router app as an ambient CSS-mask texture on panels (chat/main shell), with a small customization UI and idempotent install steps. Bundles 33 preset SVGs under bundled-patterns/ for direct copy to public/. Use when adding subtle panel textures, “Telegram-style” chat backgrounds, mask-based overlays, or onboarding a host repo to match the Pawrrtal whimsy feature without backend persistence.