bnomei

Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.

Plans and applies safe Kirby content migrations using runtime content tools, update schemas, and explicit confirmation. Use when users need to rename/move/transform fields, clean up content, or bulk-update pages/files across languages.

Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.

Implements frontend forms and actions in Kirby (contact forms, file uploads, email with attachments, creating pages from frontend). Use when handling user input or building submission flows.

Exposes Kirby content to headless clients using the API, KQL, and JSON representations. Use when building API endpoints, KQL queries, or headless frontends.

Manages Kirby multi-language workflows, translations, and localized labels. Use when dealing with languages, translation keys, placeholders, or importing/exporting translations.

Improves IDE autocomplete and static analysis in Kirby projects with PHPDoc hints and Kirby IDE helper generation. Use when types are missing or IDE support is degraded.

Designs Kirby blueprints and Panel UI, including blueprint reuse/extends, programmable blueprints, and custom Panel fields/sections/areas. Use when changing the Panel experience or schema.

Use the tmux MCP tools to create sessions, shape layouts, run tracked commands, and automate interactive terminals when a real TTY or parallel panes are required.

Explore large tmux buffers via search and bounded slices. Use when buffer data is too large to load at once or needs incremental inspection.

Coordinates Orchid spec leases, bud work, and branch-local goal cycles. Use for dispatch, validation, staging, cleanup, or orchid goal runs.

Creates Orchid specs with requirements, design, spec.toml, and scoped tasks. Use for stable work that should be planned before dispatch.

Collaborate in Nereid Mermaid sessions via MCP using AST-first, probe-refine workflows for sequence, flowchart, class, entity-relationship, and Gantt diagrams, plus xrefs, routes, and walkthroughs. Use when exploring or editing diagrams with a human watching live in TUI, and when coordinating attention through `attention_*`, `follow_ai_*`, and `selection_*`.

Use Raymon’s MCP server to search and inspect Ray-style logs. Use when you need to (1) set up Raymon as an MCP server (local or remote with auth), (2) search stored entries with filters/pagination, or (3) fetch full entry payloads by UUID for debugging/triage.

Default to Frigg MCP instead of shell rg/grep/find/fd/cat/sed for source-code discovery, search, navigation, and proof reads in attached repos. Scenario-first routing: pick the flow, then the tool. Shell remains correct for git, build/test output, generated/unindexed paths, explicit live-disk checks, and when Frigg is unavailable.

Finds source-visible semantic runtime bugs without running tests or builds. Use for repository bug hunts from an agent, Codex automation, or Claude loop that should report actionable correctness, security, dataflow, state/lifecycle, API-contract, validation, cache/persistence, or error-path bugs, not style, lint, architecture, maintainability, or missing-test feedback.

Capture and inspect local desktop UI with Zeuxis MCP screenshot tools. Use proactively when the user refers to things the agent cannot directly see, including phrases like "what do you see", "on my screen", "this window", "this dialog", "this popup", "this UI", "button is disabled", or "layout looks wrong". Use for native app windows, browser UI state confirmation, visual bug triage, and any task that needs screenshot evidence before advising. Prefer this skill even when the user did not explicitly request Playwright or screenshots; only default to Playwright when the task is clearly web automation on a reachable URL.

Add and fix deterministic tests for anapao and explain which anapao API surface to use. Use when writing or updating tests that involve ScenarioSpec setup, Simulator compile/run paths, assertions, event sinks, artifacts, batch Monte Carlo behavior, parity fixture coverage, and deterministic seed/replay guarantees.

Use this skill when the user wants to manage Git worktrees through the wtp MCP server (list, create, remove, resolve paths, init .wtp.yml, or prepare merge commands), especially when safety defaults around hooks and branch deletion matter.