Use when a problem under exploration needs its quality attributes (non-functional requirements) identified and prioritized before architecture and design begin. This should trigger when an issue's Quality Attribute Discovery point of view needs evaluation, or when a maintainer directly asks to discover and prioritize candidate quality attributes for a problem, before any ADR or design work starts. Part of Plinth Toolkit

Use when a framed and root-caused problem needs its assumptions made explicit before design or planning begins — explicit Assumptions, Unknowns, and a Validation plan. This should trigger when an issue's Assumption Analysis point of view needs evaluation, or when a maintainer directly asks to surface hidden assumptions and unknowns before committing to an approach. Part of Plinth Toolkit

Use when a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing point of view needs evaluation, or when a maintainer directly asks to frame a problem before root-cause analysis, design, or planning begins. Part of Plinth Toolkit

Use when a problem under exploration needs its surrounding system context identified before design begins — Existing systems, Integrations, Ownership, and External dependencies. This should trigger when an issue's Context Mapping point of view needs evaluation, or when a maintainer directly asks to map the systems, integrations, owners, and external dependencies relevant to a problem. Part of Plinth Toolkit

Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the root cause of a problem before proposing a fix. Part of Plinth Toolkit

Troubleshoots Google Cloud Gemini Enterprise Agent Platform issues (Agent Gateway, Registry, Identity, Policies, Model Armor, Identity-Aware Proxy (IAP)). Use when agent requests fail with 403 (especially unauthorized egress), Agent Runtime queries return 500, or gateway/IAP logs show permission errors. Don't use for general Google Cloud Identity and Access Management (IAM) debugging or networking issues unrelated to the Agent Platform stack.

Configure single-project Google Cloud Logging: regional log buckets, log sinks, log views, restricting or hiding sensitive logs in the default view (_Default) filter, IAM permissions for views (Logs View Accessor, IAM conditions), logs-based metrics, log exclusions, and sampling. Don't use for cross-project logging or multi-project setups.

Create or update a project roadmap with major milestones. Generates the configured roadmap artifact (default .ai-factory/ROADMAP.md) — a strategic checklist of high-level goals. Use when user says "roadmap", "project plan", "milestones", or "what to build next".

Run a strict multi-iteration Reflex Loop with phases (PLAN, PRODUCE||PREPARE, EVALUATE, CRITIQUE, REFINE) to improve an artifact until quality gates pass or iteration limits are reached. Use when user asks for iterative refinement, quality-gated generation, or "generate -> critique -> refine" loops.

Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.

Analyze project and generate Docker configuration: Dockerfile (multi-stage dev/prod), compose.yml, compose.override.yml (dev), compose.production.yml (hardened), and .dockerignore. Includes production security audit. Use when user says "dockerize", "add docker", "docker compose", "containerize", or "setup docker".

Archive completed plans and roadmap milestones. Moves finished plans to the archive directory and optionally trims closed milestones from ROADMAP.md. Use when user says "archive plans", "clean up plans", "archive completed", or "trim roadmap".

Custom commit workflow that replaces the built-in aif-commit. Demonstrates the skill replacement feature of the extension system.

A hello world skill provided by the aif-ext-hello extension. Demonstrates extension-provided skills.

Definição da responsabilidade principal do IM do cc-viewer: ajudar o usuário a gerenciar os projetos ccv deste servidor. Seja quando o usuário pergunta «o que você consegue fazer / em que pode me ajudar», seja «liste / quais projetos existem», «quais ccv já foram iniciados», «quais projetos estão rodando», «inicie / abra / suba o projeto X», «me dê um endereço que abra no celular / na rede local», ou até apenas um simples «oi / olá / e aí / hi / hello» sem nenhum pedido concreto, você deve usar esta habilidade (diante de um simples cumprimento, apresente-se por conta própria e diga ao usuário o que você sabe fazer). Assim que uma mensagem envolver consultar, iniciar ou o endereço de acesso de um projeto ccv, ou for apenas uma cordialidade de cumprimento, passe por aqui com prioridade — é o trabalho próprio do IM, não o contorne para improvisar por conta própria.

Definisjonen av cc-viewer IM sitt kjerneansvar: å hjelpe brukeren med å administrere ccv-prosjektene på denne serveren. Enten brukeren spør «hva kan du / hva kan du hjelpe meg med», eller «list opp/hvilke prosjekter finnes» «hvilke ccv er startet» «hvilke prosjekter kjører» «start prosjekt X for meg / åpne det / få det i gang» «gi meg en adresse jeg kan åpne på mobil/lokalnett», eller bare «hi / hello / hei / hallo» som en ren hilsen uten et konkret ønske — i alle disse tilfellene bør du bruke denne ferdigheten (ved en hilsen tar du selv initiativ til å presentere deg og fortelle brukeren hva du kan). Så lenge meldingen handler om å vise ccv-prosjekter, starte dem eller om en tilgangsadresse, eller bare er en hilsen og litt småprat, så gå denne veien først — dette er IM sitt egentlige arbeid, ikke gå utenom det for å improvisere på egen hånd.

Definizione della responsabilità principale dell'IM di cc-viewer: aiutare l'utente a gestire i progetti ccv di questo server. Che l'utente chieda «cosa sai fare / in cosa puoi aiutarmi», oppure «elencami / quali progetti ci sono», «quali ccv sono stati avviati», «quali progetti sono in esecuzione», «avvia / apri / fai partire il progetto X», «dammi un indirizzo apribile da mobile / dalla rete locale», o anche solo un semplice «ciao / salve / ehilà / hi / hello» senza alcuna richiesta precisa, devi usare questa skill (a un semplice saluto, presentati di tua iniziativa e di' all'utente cosa sai fare). Non appena un messaggio riguarda la consultazione, l'avvio o l'indirizzo di accesso di un progetto ccv, o è solo un convenevole di saluto, passa in via prioritaria da qui: è il vero compito dell'IM, non aggirarlo per improvvisare per conto tuo.

Définition de la mission principale de l'IM cc-viewer : aider l'utilisateur à gérer les projets ccv de ce serveur. Que l'utilisateur demande « que peux-tu faire / en quoi peux-tu m'aider », ou « liste-moi / quels sont les projets », « quels ccv ont été lancés », « quels projets tournent », « lance / ouvre / démarre le projet X pour moi », « donne-moi une adresse ouvrable depuis le mobile/le réseau local », ou même un simple « salut / bonjour / coucou / hi / hello » sans demande précise, il faut utiliser cette compétence (pour un simple bonjour, présente-toi spontanément et dis à l'utilisateur ce que tu sais faire). Dès qu'un message touche à la consultation, au lancement ou à l'adresse d'accès d'un projet ccv, ou n'est qu'une formule de politesse, passe en priorité par ici — c'est le vrai travail de l'IM, n'en fais pas l'impasse pour improviser de ton côté.

Definición de la responsabilidad principal del IM de cc-viewer: ayudar al usuario a gestionar los proyectos ccv de este servidor. Tanto si el usuario pregunta «¿qué puedes hacer / en qué puedes ayudarme?», como «lístame / qué proyectos hay», «qué ccv se han iniciado», «qué proyectos están en marcha», «inicia / abre / arranca el proyecto X», «dame una dirección que pueda abrir desde el móvil / la red local», o incluso un simple «hola / buenas / qué tal / hi / hello» sin ninguna petición concreta, debes usar esta habilidad (ante un simple saludo, preséntate por iniciativa propia y dile al usuario qué sabes hacer). En cuanto un mensaje tenga que ver con consultar, iniciar o la dirección de acceso de un proyecto ccv, o sea solo una cortesía de saludo, pasa por aquí con prioridad: es el trabajo propio del IM, no lo esquives para improvisar por tu cuenta.

The core responsibility of the cc-viewer IM: helping users manage the ccv projects on this server. Whether the user asks "what can you do / how can you help me", or "list / what projects are there", "which ccv have been started", "which projects are running", "start / open / spin up project X for me", "give me an address I can open on my phone / LAN", or even just says "hi / hello" as a plain greeting without any concrete request, you should use this skill (on a greeting, proactively introduce yourself and tell the user what you can do). As long as a message touches on viewing, starting, or getting access addresses for ccv projects, or is just small talk, route it here first—this is the IM's actual job; don't sidestep it and improvise on your own.