Use when something is broken and you need to find out why: test failures, runtime errors, crashes, regressions, or unexpected behavior. Trigger for 'it's not working', 'something broke', 'this used to work', 'I'm getting an error', 'CI is failing', 'the output is wrong', or 'why is X happening'. Systematic 4-phase diagnosis — never patches symptoms without finding the root cause.

Run tests, fix lint errors, break down large files, and clean up debug artifacts

Author or refine an inspequte rule spec from a rule idea, optional plan.md, and target rule-id. Use when writing src/rules/<rule-id>/spec.md from a fixed template while avoiding implementation details.

Use when the user asks about Omni platform documentation outside the narrow embed flow, including modeling, REST API, AI and MCP features, administration, permissions, connections, and platform setup; browse official `docs.omni.co` pages, prefer `$omni-embed-docs` for embed-specific questions, and answer with source links.

Perform isolated, file-based verification of an inspequte rule change using verify-input/. Use when producing a go/no-go verification report from spec.md, patch/diff, and report files without reading plan.md or chat logs.

Use when you have a spec and need to create tasks for it. Reads the spec, assesses separable work streams, proposes a task split, and creates task files.

SIMD vectorization for Rust — detects ISA features, identifies vectorizable patterns, generates platform-specific intrinsics (ARM NEON/SVE, x86 SSE/AVX/AVX-512), validates correctness and performance. Uses tiered research with baked-in references and /deep-research fallback.

Use this skill when the task is to reproduce or analyze a concrete AutoLabOS TUI/web symptom, especially when stale state, fresh-vs-existing divergence, resume mismatch, or persisted-artifact-vs-UI disagreement may be involved.

Morning briefing for team activity and repo health.

Edit LCP protocol docs under docs/protocol/ in BOLT-style (TLVs, message formats, state flow).

Migrated from the legacy agent profile. Use this as an on-demand specialist workflow.

[OMX] Guide on using oh-my-codex plugin

Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.

Bridge solid-js UI with @lumino/widgets and inversify in the Raykit browser runtime. Use when creating or refactoring browser-side widgets, renderer hosts, widget factories, application contributions, or service-driven communication between Solid views and external container state in Raykit packages and desktop browser code.

Check whether a normal implementation task is actually ready to be marked complete. Require real code changes, appropriate validation, and only minimal documentation updates tied to the implementation diff.

Expert guidance for WeChat monitoring and automation using wxauto (Windows) and Accessibility API (macOS).

[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.

Design optimal Facebook/Meta campaign structure for testing including ABO vs CBO, ad set organization, targeting, and budget allocation. Use when setting up new campaigns, planning test structure, or optimizing account architecture.

Initialize and manage AC Framework spec-driven workflows using acfm CLI. Use when setting up spec workflows, checking project status, creating changes, or understanding the .acfm/ vs openspec/ directory structures. Essential first step before using any OpenSpec skills.

>-

Master Java 21+ with modern features like virtual threads, pattern matching, and Spring Boot 3.x. Expert in the latest Java ecosystem including GraalVM, Project Loom, and cloud-native patterns. Use PROACTIVELY for Java development, microservices architecture, or performance optimization.

Especialista em design gráfico e comunicação visual — cria imagens, infográficos, slides e animações para Instagram, LinkedIn, TikTok e apresentações, obrigatoriamente baseadas em conteúdo fornecido pelo usuário.

Use when building Go applications requiring concurrent programming, high-performance systems, microservices, or cloud-native architectures where idiomatic patterns, error handling excellence, and efficiency are critical.

Update GSD to latest version with changelog display

Add and configure Neovim plugins in this dotfiles repo using lazy.nvim. Use when asked to install a plugin, create its config module, update lazy.nvim imports, read plugin README/docs, and add keymaps without conflicting with existing mappings under config/nvim.

Onboard Codex to the PeopleFlow HRMS Laravel application and guide safe changes across its multi-tenant, role-gated modules. Use when working in this repo on routes, controllers, middleware, models, Blade views, policy management, tenant onboarding, self-service, analytics, documents, payroll, shifts, or any change that needs app-specific context about tenant scoping, RBAC, route registration, or validation and service patterns.

Add Auth0 identity setup guidance and boundary-specific scaffolding for repositories that directly integrate with Auth0.

This skill provides comprehensive support for developing ERC-4337 compliant Account Abstraction wallets with privacy-preserving features, specifically designed for vehicle identity and other sensitive

Build CEFR-split word tree markdown files from the dated daily vocab note in the current language folder. Use this when the user wants to read `vocab/daily/daily-notes-YYYY-MM-DD.md`, organize every vocab item by part of speech, expand each item with usable grammar details, verify CEFR level through web search, rewrite the daily vocab note into the normalized word-tree schema, write dated `vocab-CEFR-YYYY-MM-DD.md` files inside per-level `daily/` folders, and update the cumulative CEFR vocab files.

Definir hooks ligeros para automatizar validaciones repetitivas y proteger calidad en este repositorio. Usar cuando se quiera ejecutar checks automáticos antes o después de editar archivos, correr tests o preparar commits.

Use when collecting external app or pattern references for product decisions and you need a disciplined output that separates facts, patterns, risks, and open questions.

Diagnose order synchronization failures between Trello and Google Sheets, including pending operations, rollback errors, and missing card linkage.

Risk-based test strategy for software delivery. Use when defining coverage, setting CI gates, managing flaky tests, or establishing release criteria.

Run Prisma and Postgres operational workflows for Node services, including generate, migrate, seed, and test reset. Use when working with Prisma-backed projects such as projects/node-backend-starter-v2.

Finish a Taskdeck change with the right checks and doc updates. Use at the end of implementation to choose verification scope, decide whether canonical docs changed, and prepare the required handoff summary.

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

Resolve on-screen 5chan DOM elements to React source files, line numbers, component names, and ownership stacks using the app's dev-only element-source helpers and playwright-cli. Use when Codex needs to inspect a page element, map a snapshot ref to source code, confirm which component rendered a node, or follow up after $profile-browsing finds a rerender hotspot and needs file-level attribution.

Start a research project with intelligent agent orchestration

Short, explicit alias for vc-router. Use only when the user explicitly invokes `use vcg:` and wants the shortest reliable router command.

Architecture Decision Records with trade-off analysis. Guides through decision context, quality-attribute scoring, and ADR generation via a domain-adapted hint ladder. Defers to AGENTS.md.

Generate a structured deep research prompt. USE WHEN the user needs to research a complex topic, market, or bug deeply. Capabilities include objective clarification, tech stack validation, and prompt generation.

iOS Simulator automation and interaction using the AXe CLI tool. Use when working with iOS simulators for UI automation, testing, accessibility verification, or screen recording. Specific use cases include simulating touches and gestures (tap, swipe), entering text, pressing hardware buttons (home, lock, Siri), recording or streaming simulator video, extracting UI accessibility information, or automating iOS simulator interactions. Assumes axe CLI is already installed.

Capture atomic learning insights into .workflow/learning/lessons.jsonl. Lightweight CRUD over the shared learning store — supports capture, list, search, and show modes. No LLM or CLI calls; all operations are pure file reads and writes.

Skill to update and improve README.md. This skill is usefull for adjusting README to latest source code contents.

Deploy Tempo Zones, start zone nodes, validate router swap-and-deposit flows, and debug zone sync, portal ingestion, withdrawal, sequencer key, and generated zone artifact issues in this repository. Use when working with just deploy-zone, zone-up, deploy-router, demo-swap-and-deposit, or generated/<name>/zone.json.

Implement or adjust the core color pipeline (parse, normalize, scale, resolve) guided by src/planning/spec-v0.3.md and src/planning/roadmap-v0.3.md.

Migrated from the legacy agent profile. Use this as an on-demand specialist workflow.

Write, critique, and iterate prompts for OpenAI GPT-5 series models. Use for tasks like: (1) turning vague requirements into high-signal instructions, (2) selecting between quick vs deep reasoning behaviors, (3) creating robust structured-output prompts (JSON schemas, tool calls), (4) designing evaluation prompts and rubrics, and (5) debugging prompt failures (hallucinations, format drift, tool misuse). Trigger when the user mentions GPT-5, prompt engineering, system/developer messages, structured outputs, agent prompts, or wants best-practice templates.

Structured workflow for discovering, reproducing, and fixing bugs in Searchlite by inspecting real code paths (CLI/HTTP/core), validating durability invariants, and producing regression tests; use when investigating incorrect results, crashes, data loss risks, or “it sometimes fails” reports.