spences10

Private remote coding-agent hosts over Tailscale. Use when configuring unattended Linux workers, persistent remote agents, or private access to development services.

Coordinate parallel agent work. Use when decomposing complex tasks, running review/implementation in parallel, managing task lists, or choosing shared vs isolated workspaces.

Svelte deployment guidance. Use for adapters, Vite config, pnpm setup, library authoring, PWA, or production builds.

SvelteKit data flow guidance. Use when working with load functions, form actions, server/client boundaries, serialization, or invalidation.

Implement SvelteKit remote functions. Use for query(), query.live(), form(), command(), and prerender() patterns in .remote.ts files.

SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.

Svelte 5 core best practices. Use when creating, editing, or reviewing .svelte, .svelte.ts, or .svelte.js files. Routes to deeper Svelte skills.

Build Svelte LayerChart components. Use for tooltip snippets, Chart context access, gradients, highlights, axes, and Svelte 5 snippet patterns.

Setup guide for essential MCP servers. Use when configuring MCP servers or when user asks about search, SQLite, or MCP management.

Query Claude Code session analytics from ccrecall database. Use when user asks about token usage, session history, or wants to analyze their Claude Code usage patterns.

High-leverage prompts that challenge Claude's defaults. Use for "grill me", "prove it works", "scrap this", "what would 10x engineer do", "find ways this fails".

Maintain CLAUDE.md files effectively. Use when adding lessons learned, updating conventions, or restructuring project instructions.

Multi-agent orchestration patterns for Claude Code team mode. Use when coordinating teammates, decomposing complex tasks, or managing shared task lists.

Enhanced Research-Plan-Implement workflow with structured phase gates. Use when tackling complex tasks that benefit from a phased approach with user checkpoints.

Terminal setup for Claude Code. Use for Ghostty config, statusline customization, voice dictation, tmux worktrees.

Git worktree patterns for parallel Claude sessions. Run multiple Claude instances on same repo without conflicts.

Use when assessing ambiguous or high-risk coding work before creating an approved task harness. Establishes evidence, existing primitives, rejected options, a smallest vertical slice, and an optional execution contract.

Use when running an existing /tmp Pi task harness. Executes inside the active contract, records status, respects enforcement, and loops through validation.

Use when preparing or validating Pi monorepo releases, including Changesets, pnpm lockfile updates, package previews, release-age policy, and installability checks.

Use when evaluating proposed Pi customisation work against built-in Pi primitives before implementation, especially extensions, packages, slash commands, and workflow ideas.

Use when coordinating review-gated delivery of discrete GitHub issues between one implementation peer and a review-only lead, with user-owned Changesets and approval-gated commits.

Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.

Use when developing or reviewing packages/pi-observability dashboard/server changes locally, especially rebuilding dist, restarting the 43190 server, validating UI behavior, or keeping the local dashboard in sync with source edits.

Use when creating or modifying Pi extensions, built-in extension wiring, prompt shims, package scaffolds, package READMEs, or packages/pi-* implementation in this monorepo.

SvelteKit remote functions guidance. Use for query(), form(), command(), and prerender() patterns in .remote.ts files.

Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.

Svelte deployment guidance. Use for adapters, Vite config, pnpm setup, library authoring, PWA, or production builds.

Svelte runes guidance. Use for reactive state, props, effects, or migration. Covers $state, $derived, $effect, $props, $bindable. Prevents reactivity mistakes.

Svelte CSS styling patterns. Use for scoped styles, CSS custom properties, style: directive, :global, or styling child components.

SvelteKit data flow guidance. Use for load functions, form actions, server/client data, and invalidation. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error(), invalidateAll().

SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.

Guide to spences10's Claude Code ecosystem tools. Use when user asks which tool to use, how tools relate, or needs help choosing between MCP servers, skills, or CLIs.

Database migration patterns for SQLite. Use when creating migrations, modifying schema, or running database changes.

Remote functions reactive UI patterns. Use for smooth in-place updates, preventing page jumps, and managing loading states with .current property.

SvelteKit patterns for devhub-crm. Use for remote functions (query, form, command), routing, and server-side logic.

Better-auth integration for authentication. Use when implementing login, registration, protected routes, or email verification.

Vitest browser mode component testing. Use for testing Svelte 5 components with real browsers, locators, accessibility patterns, and reactive state.

SQLite operations using better-sqlite3 with prepared statements. Use when implementing CRUD operations, timestamps, and user-scoped queries with row-level security.

Svelte 5 error handling. Use for error boundaries, async await expressions, loading states, and form errors.

DaisyUI v5 form patterns. Use for inputs, selects, textareas, validation, and form structure with fieldset/legend.

Use when working with Daytona SDK - uploadFile(Buffer, path), pnpm setup, CodeLanguage options

Daytona sandbox security. Use for token handling, credential boundaries, and full paths in SSH.

Prepare reusable Daytona sandbox sessions for isolated evals, debugging, or manual command execution.

Manage Daytona sandboxes for isolated evals, smoke tests, and command execution.

Generate sandbox-scoped task prompts for any LLM or tool runner working inside Daytona sandboxes.

Troubleshoot Daytona sandbox runs, SSH access, snapshots, credentials, and command execution failures.

Use for reusable Daytona sandbox workflows, SSH access, git setup, and isolated command execution.

Ralph-town snapshot commands. Use for preflight checks and snapshot creation before reliable sandbox runs.

SvelteKit remote functions guidance. Use for command(), query(), form() patterns in .remote.ts files.

Research topics by verifying actual source content. Use when asked to research or study links and documentation.

Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.

Svelte deployment guidance. Use for adapters, Vite config, pnpm setup, library authoring, PWA, or production builds.

Svelte runes guidance. Use for reactive state, props, effects, attachments, or migration. Covers $state, $derived, $effect, @attach. Prevents reactivity mistakes.

SvelteKit data flow guidance. Use for load functions, form actions, and server/client data. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error().

SvelteKit structure guidance. Use for routing, layouts, error handling, SSR, or svelte:boundary. Covers file naming, nested layouts, error boundaries, pending UI, and hydration.

Maintain a wiki0 LLM wiki. Use when creating a new wiki, syncing sources, updating linked Markdown pages, answering from wiki context, or reviewing wiki health.

Use wiki0 itself before direct Markdown edits. Trigger when editing wiki docs, adding frontmatter, reading project memory, or updating dogfooding documentation.

Build and validate wiki0 package changes. Trigger when editing packages/core, packages/cli, packages/mcp, or exposing behavior through CLI and MCP.

Drafts or improves scottspence.com monthly newsletters in Scott's voice. Use when creating newsletter/YYYY-MM-DD.md, summarising recent posts, GitHub activity, talks, tools, or preparing monthly email copy.

Writes or improves scottspence.com blog posts in Scott's voice. Use when drafting posts, editing articles, choosing SEO titles/slugs, or turning repo/session history into a published post.

Fix and create Svelte 5 tests with vitest-browser-svelte and Playwright. Use when fixing broken tests, debugging failures, writing unit/SSR/e2e tests, or working with vitest/Playwright.

Rebuild cv-agent.db from CV copy files, sources.md, and ccrecall databases. Use when database is lost, corrupted, or needs full reconstruction.

Research topics by verifying actual source content. Use when asked to research or study links and documentation.