OpenWaggle

This skill should be used when designing, implementing, reviewing, or operating OpenWaggle releases, version bumps, release-intent files, changelog/GitHub release notes, updater channels, or Alpha/Beta/RC/Stable update-track behavior.

Review pull requests and local diffs for correctness, regressions, security, missing tests, architecture drift, and maintainability. Use for PR reviews, branch audits, regression checks, and code quality assessments.

Run React Doctor diagnostics to catch React anti-patterns, performance issues, and compiler incompatibilities after completing any task that touches renderer code (src/renderer/). This skill should be used as a final verification step before presenting work for review.

This skill should be used when an agent is writing or reviewing TypeScript code that uses ts-match (published as @diegogbrisa/ts-match) for pattern matching, exhaustive discriminated-union handling, promise-aware branching, runtime validation, grouped cases, pattern helpers, or boundary assertions.

OpenWaggle-specific Pi runtime integration guidance for adapters, provider/model/auth metadata, sessions, tools, resources, MCP, compaction, attachments, and projection. Use when touching src/main/adapters/pi, agent run orchestration, session projection, provider catalog/auth, Pi resources, MCP adapter behavior, or Pi-native tool events.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Use @total-typescript/shoehorn for test-only partial mocks or intentionally invalid inputs. Use when writing tests, refactoring tests, or removing raw `as` casts from test fixtures.

QA testing skill for OpenWaggle's Electron app using the configured Chrome DevTools MCP server. Use after renderer, preload, IPC, or interactive main-process changes to verify behavior in the real Electron app via CDP on port 9222.

OpenWaggle Electron runtime guidance for child-process environment safety, native addon rebuilds, packaged app differences, CDP startup, and Electron-specific debugging. Use when Electron startup, packaging, native modules, child processes, environment variables, or Playwright Electron behavior are involved.

Codebase intelligence for JavaScript and TypeScript. Free static layer finds unused code (files, exports, types, dependencies), code duplication, circular dependencies, complexity hotspots, architecture boundary violations, and feature flag patterns. Optional paid runtime layer (Fallow Runtime) merges production execution data into the same health report for hot-path review, cold-path deletion confidence, and stale-flag evidence. 90 framework plugins, zero configuration, sub-second static analysis. Use when asked to analyze code health, find unused code, detect duplicates, check circular dependencies, audit complexity, check architecture boundaries, detect feature flags, clean up the codebase, auto-fix issues, merge runtime coverage, or run fallow.

Define and adapt git safety guardrails for agentic coding tools. Use when setting up command filters, hooks, or policies that prevent agents from pushing, hard-resetting, cleaning, deleting branches, or overwriting unknown work without explicit approval.

Set up the repo context expected by Matt Pocock engineering skills using AGENTS.md, .agents/, and docs/agents/. Run before first use of to-issues, to-prd, triage, diagnose, tdd, improve-codebase-architecture, or zoom-out when issue tracker, triage labels, or domain docs are not configured.

Create or update agent skills with progressive disclosure, strong metadata, and optional bundled scripts/references/assets. Use when the user wants to create, write, update, migrate, or package a skill.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

This skill is for interface design — dashboards, admin panels, apps, tools, and interactive products. NOT for marketing design (landing pages, marketing sites, campaigns).