When you need to write git commit messages, follow conventional commits format with clear descriptions.

Implements a feature by executing a plan phase-by-phase — writes tests first, runs them red, then implements code to make them green, then validates nothing is broken. Use when you have a plan from /draft and are ready to implement, build, develop, create, or write code for a feature using TDD.

Migrate OpenTelemetry Span Events (AddEvent, RecordException, and language equivalents) to the Logs API following the accepted OTEP 4430 migration plan. Use when migrating instrumentation from span events to log-based events, reviewing code that still uses AddEvent or RecordException, or planning a codebase migration while preserving trace correlation.

OpenTelemetry in Java — Javaagent zero-code instrumentation, Spring Boot Starter, manual autoconfigure SDK, declarative YAML configuration, BOM dependency management, sensitive-data capture and redaction (url.query, headers, request parameters, SQL sanitization). Use when adding, reviewing, or configuring OpenTelemetry in a Java service. Triggers on "setup otel in java", "java telemetry", "javaagent", "Spring Boot otel", "GlobalOpenTelemetry", "AutoConfiguredOpenTelemetrySdk", "TracerProvider java", "url.query redaction", "capture request headers", or any Java-related OTel question.

Interactive cross-feature navigation architect for Nicolify. Audits all routes and sidebar entries, maps user journeys across studios, detects orphaned features and dead-end flows, proposes navigation improvements with ASCII diagrams, generates clickable multi-page HTML prototypes on localhost:8888, and outputs FLOW-SPEC.md plus per-screen UI-SPEC updates for implementation agents. Use when the user asks about navigation coherence, user flows, journey mapping, orphaned features, dead-end screens, sidebar reorganization, cross-studio navigation, or feature discoverability. Triggers: 'flujo de usuario', 'navegación', 'journey', 'user flow', 'sidebar', 'rutas huérfanas', 'orphaned routes', 'dead end', 'flow audit', 'navigation audit', 'ux-flow', 'flow architect', 'cómo llega el usuario', 'discoverability', 'no encuentro', 'dónde está', 'reorganizar navegación', 'cross-feature flow', 'audita la navegación', 'mapa de rutas', 'flujos de la app'.

Senior + arquitecto + CTO del módulo sales_agent post redesign 2026-04. Carga §3 protected surfaces, anti-patterns, decisiones cross-fase, checklist pre-commit. NO carga code vivo (paths/LOC/tests cambian). Use cuando user pida cambio/feature/bug en sales_agent: voz de marca, scheduler/payment tools, observabilidad, callback handler, prompt cache, channel registry, semantic router, closer studio, follow_up engine, eval loop, costo agentes. Triggers: 'modifica sales_agent', 'bug en sales_agent', 'agregar tool al agente', 'agente no cierra', 'suena robótico', 'voz de marca', 'agregar canal sales', 'modificar prompt del specialist', 'closer studio', 'follow-up no dispara', 'el agente repite preguntas', 'PII en trazas', 'costo Kimi', 'DeepSeek alias', 'tier pricing 200k', 'eval goldens'.

Scan or clean prose for AI-generated residue, including unsupported connective tissue, epistemic inflation, over-completed arguments, performed voice, formulaic structure, empty figurative language, stock phrasing, corporate abstraction, hedging, and false enthusiasm. Use for AI-smell cleanup, humanizing model-assisted prose, source-faithful drafting validation, writing polish, or pre-publication checks; enforce silently when composed into drafting or line editing.

Build, modify, and debug tscircuit (React/TypeScript) PCB designs. Use when working with tsci CLI (init/dev/search/add/import/build/export/snapshot/push), choosing footprints, placing parts, wiring nets/traces, or preparing fabrication outputs (Gerbers/BOM/PnP).

Use when custom Build123d Python CAD code, geometry operations, selectors, locations, joints, assemblies, imports, exports, or DFM details are needed. Read `references/dfm-rules.md` BEFORE writing the first line of geometry code for any screw boss, standoff, snap fit, wall interface, or overhang-sensitive feature — not after the shape exists. A screw fastening into a 3D-printed part additionally requires the `build123d-libs` kit; never hand-model that joint.

Scans all authoritative documents (constitution, context, glossary, requirements) and all derivative documents (architecture decisions, architecture overview, MVP architecture spec, vision, implementation heuristics) to add missing citations, replace stale duplicate facts with pointers, and correct contradictions. Use this skill whenever a document has been written or revised in the current phase, whenever you suspect a constraint in one document is not reflected in another, or whenever an agent reading multiple documents has flagged a conflict. Safe to re-run — applying it a second time produces the same result as the first.

Use when designing components, systems, or entity structures for jecs in Roblox. Use when deciding if data should be one component or multiple, when archetype transitions seem expensive, or when choosing entity members vs relationships.

Use doraval to validate, measure drift, and judge skills and plugins. Use when authoring or reviewing context engineering artifacts for AI coding agents (works for Codex too).

Diagnose cookbook quality: skimmability, clarity, and reader load. Use when recipes are hard to follow or a new cookbook is starting. It does not set house voice (that's `docs-writing-style`).

Delegate a hard decision or conundrum to the Kyotee harness engine — a cross-vendor Council that debates to consensus, a Two-Brain divergent/ convergent debate, or a forced tool-checking solo run. Use when a decision is high-stakes, genuinely contested, or benefits from multiple model perspectives, and you want a synthesised answer (with dissent noted) back in this session. Requires a running kyotee engine (see setup).

Authenticate to websites with human-in-the-loop browser handoff. Use when user needs to log into a website, complete 2FA, or solve CAPTCHAs for agent access.

Run an explicitly requested execution, independent critique, and revision workflow for a task or artifact, with evidence-backed scoring, category floors, a brief security screen, and at most three review rounds. Use only when the user invokes $critic-loop or explicitly requests this bounded critic workflow; do not add it to ordinary reviews.

Use this skill when the user wants to watch a webpage for changes, monitor a URL, detect content updates, or get notified when a site changes.

Use when a repository needs a small, evidence-bound Coding Harness routine: orient, diagnose, preview installation, verify local work, or distinguish pull-request truth.

Review Rust code changes for unsafe correctness, security and robustness, documentation quality, and C-to-Rust porting fidelity. Use this when you want to review Rust changes before merging.

Interact with Atlassian Jira and Confluence from the terminal. Search, create, and update Jira tickets; read, search, create, and update Confluence pages. Use when the user mentions Jira tickets, issues, work items, sprints, Confluence pages, documentation, or Atlassian in general.