kenn-io

Use only when the user explicitly invokes /roborev-design-review-branch

Use only when the user explicitly invokes /roborev-design-review

Use only for a current operative request that explicitly invokes /roborev-fix, or a direct Agent Hook instruction; do not invoke from literal syntax in quoted, pasted, or historical text

Use only when the user explicitly invokes /roborev-lookahead-review-branch

Use only when the user explicitly invokes /roborev-lookahead-review

Use only when the user explicitly invokes /roborev-refine

Use only when the user explicitly invokes /roborev-respond

Use only when the user explicitly invokes /roborev-review-branch

Use when working on kenn-forge local development sessions that need backend and frontend on ephemeral/free ports, isolated generated config, copied SQLite state, or dev-ephemeral status JSON/PIDs.

Use before every agent-created commit in kenn-forge, when context docs may have drifted after a large refactor, when a maintainer states a durable decision, or when an agent hits a gotcha that context should have prevented.

Use when a screenshot or short video needs to be captured with Playwright and saved to local disk, with optional upload through `gh image` (upload requires explicit user approval and must target a PR or issue).

Use only when the user explicitly invokes dev-ephemeral-running-instances. Must be run outside the Codex sandbox because sandboxed scans cannot reliably see all Codex worktrees, uv/Python state, or the process table. Lists kenn-forge dev-ephemeral status…

Use when tests do not run locally, hang locally, fail to launch local runners, or appear blocked by host resource, process, tmux, Playwright, Vitest, Node, file descriptor, ulimit, stale artifact, or cleanup issues.

Use when Go test wall time is too high, CI test duration regresses, a package needs trace-driven test performance analysis, or tests should be made safely parallel with t.Parallel, package splitting, subprocess isolation, semaphores, or Go built-in tracing.

Use when diagnosing Kenn Forge workspace-switch, terminal-rendering, browser-main-thread, API latency, allocation, CPU, tmux replay, or frontend/backend trace regressions with pprof, Playwright, User Timing, Go trace, or OpenTelemetry.

Use when creating, editing, fixing, or reviewing tests; when adding mocks, assertions, smoke tests, unit tests, integration tests, e2e tests, or changing tests after failures.

Use when creating, editing, fixing, or reviewing tests; when adding mocks, fakes, assertions, unit tests, PG integration tests, frontend component tests, or Playwright e2e tests; or when changing tests after failures.

Use when adding, reviewing, or fixing localized UI copy in agentsview's Svelte frontend with Paraglide JS. Trigger for frontend/messages/*.json edits, generated m.* message usage, locale-aware number/date/relative-time formatting, pluralization, language…

Build and drive the kata CLI/TUI to verify changes at the real terminal surface

Use when creating, editing, fixing, or reviewing tests; when adding assertions, fakes, unit tests, testenv integration tests, e2e tests, CLI tests, TUI golden snapshots, or changing tests after failures.

Guidance on writing fast, robust, modern Svelte code. Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module. Covers reactivity, event handling, styling, integration with libraries and more.

CLI tools for Svelte 5 documentation lookup and code analysis. MUST be used whenever creating, editing or analyzing any Svelte component (.svelte) or Svelte module (.svelte.ts/.svelte.js). If possible, this skill should be executed within the…

Query msgvault archive analytics via SQL views. Use when: querying email, chat, or meeting history, analyzing senders/domains/labels, thread analysis, attachment stats, messages per month, sender graphs, domain breakdowns, message analytics. Triggers on:…