labs

Review a changeset for the Common Fabric repo — the local branch diff vs main, or a GitHub PR. Flags correctness and regression bugs loudly, checks that runtime-semantics changes stay coherent across docs/comments/examples, catches duplicated core machinery (hashing, serialization, cloning, identity) and code fighting the transformer/reactive model, and scrutinizes whether the tests guard the right principles. Report-first; offers to post a self-signed PR review. Use when asked to review code, review a PR, review the current branch or diff, or self-review before pushing. Invoke as /cf-review or /cf-review <PR#>.

Agent-specific interaction patterns for working with FUSE-mounted spaces. Use when deploying patterns via FUSE, working with Activity Logs, Annotations, or coordinating agent workflows that read/write pieces through the filesystem. Triggers include "deploy a pattern", "log an event", "create annotation", "agent workflow", or managing piece lifecycle via FUSE.

Critic agent that reviews pattern code for violations of documented rules, gotchas, and anti-patterns. Produces categorized checklist output with [PASS]/[FAIL]/[WARN] for each rule.

Guide for developing Common Fabric patterns (TypeScript modules that define reactive data transformations with UI). Use this skill when creating patterns, modifying existing patterns, or working with the pattern framework. Triggers include requests like "build a pattern", "fix this pattern error", "deploy this piece", or questions about handlers and reactive patterns.

Build Common Fabric patterns and sub-patterns

Guide for using the cf (Common Fabric) CLI to interact with pieces, patterns, and the Common Fabric. Use this skill when deploying patterns, managing pieces, linking data between pieces, or debugging pattern execution. Triggers include requests to "deploy this pattern", "call a handler", "link these pieces", "get data from piece", or "test this pattern locally".

Convert Common Fabric pattern unit tests (`*.test.tsx` driven by actions and computed assertions) into browser integration tests (`packages/patterns/integration/*.test.ts`) that exercise the rendered UI and can be recorded with `deno task demo`. Use when asked to promote, mirror, spot-check, browser-test, or make a video demo from an existing pattern test, including multi-user pattern tests.

Guide for hybrid workflows using CF FUSE filesystem mounting alongside the browser and CLI. Use when mounting spaces, editing cells via the filesystem, developing patterns for filesystem interaction, or combining browser + filesystem + CLI workflows. Triggers include "mount a space", "edit cells from filesystem", "use FUSE", "hybrid workflow", "filesystem sync", or working with pieces across both browser and CLI. For agent-specific patterns (deploying, activity logs, annotations), see the fuse-agent skill.

Map and verify the CTS/schema documentation corpus against its normative contracts, implementation, tests, fixtures, and runtime consumers. Use for claim-level audits or updates in docs/specs/ts-transformer, docs/specs/schema-generator, package guidance, and author-facing CTS docs, especially after transformer/schema changes or before releases.

Guide for developing Lit web components in the Common UI v2 system (@commonfabric/ui). Use when creating or modifying cf- prefixed components, implementing theme integration, working with Cell abstractions, or building reactive UI components that integrate with the Common Fabric runtime.

Shared foundation for Oracle & Corrector agents. Establishes the source hierarchy for resolving conflicts between documentation, code, and specs. Load this skill first when investigating how the system works.

Guide for managing tasks within a session using bd (beads) for subtasks and local todo lists. Use this skill when breaking down plans into issues, tracking progress, managing dependencies, or coordinating work across sessions and agents. Triggers include requests to "manage tasks", "track progress", "break down this work", or questions about bd workflow.

Debug Common Fabric runtime/multiplayer state from the durable store, offline, with `cf inspect`. Use when investigating "what is actually stored", a cell that looks different for two users, a lost/overwritten write, divergence across spaces, how state reached its current value, who/what touched a space, or any memory-v2 question you'd otherwise guess at from a live runtime. Reads space SQLite DBs read-only — no live server, no capture step.

Deploy patterns and test with CLI

Write and run pattern tests

Guide for writing side-effect-free tests that spawn child processes, especially Deno commands. Use when adding or reviewing tests that call Deno.Command, run deno check/test/run/task/install, generate temporary deno.json files, update goldens, write build artifacts, or otherwise risk changing deno.lock or files in the repository workspace.

Debug pattern errors systematically

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Design and polish pattern UIs with cf- components - theme-first styling via cf-theme, layout with cf-screen/cf-vstack, two-way binding ($value/$checked), and PerSession/PerUser/PerSpace UI-state scoping. Use when styling pattern JSX or writing a UI design doc.

Design schemas.tsx with Input/Output types for patterns

Analyze memory in a running Deno process via the V8 inspector CDP protocol. Use when the user asks about memory usage, memory leaks, heap analysis, heap snapshots, allocation profiling, or object retention in a Deno process running with --inspect.

Translate a Figma design selection into cf-* Lit component code. Use when implementing a design from Figma, reviewing component alignment, or checking how Figma properties map to code. Triggers include "implement this design", "translate from Figma", "what cf- component matches this", or having a Figma node selected to implement.