etienne

Deterministic communication metrics for the mirrored Teams channels. Computes reply-latency distributions, after-hours share, burst/fragmentation index, unanswered blockers, and interruption-cascade depth from data/teams/*/messages.jsonl, and refreshes the hyperscreen dashboard data. Use before making ANY quantitative claim about team communication.

Generate an interactive "application simulator" — a tiny, agent-built React mock of an external app (SAP MD04, a CRM, an ERP form) that the trainee can click through. The trainee's clicks stream back to you via viewerState so you can coach in real time. Each simulator is a single self-contained HTML file under `out/simulators/<app>.simulator.html`. Use this skill when the expert asks for a simulator (often in the context of curriculum topic 4 "Werkzeuge") or when a guest asks "can I practice this somewhere?".

Co-author a new roleplay scenario with an expert. Interview the expert about the persona, topic, hints with point values, and evaluation criteria, draft the JSON, and on confirmation write it to roleplay/<slug>.roleplay.json. Use when the expert invokes "Author a roleplay scenario" from the menu, asks "let me add a customer call to practice", "I want to script a difficult buyer", or equivalent. The scenarios authored here are consumed at runtime by the roleplay-engine skill.

Maintains a project knowledge wiki at wiki/ as the agent's long-term memory, dynamically structured around the mission in wiki/_meta/mission.md. Use whenever the user shares a fact, decision, preference, requirement, or finding worth remembering; whenever the user says "remember this", "add to wiki", "we decided", "save", "note that", or "for the record"; whenever the user asks "what do we know about X", "have we considered Y", "what did we decide", "summarize what we have"; whenever a file in the project codebase contains information relevant to the mission and should be ingested; at the end of a session to consolidate findings; and at session start to load relevant context. Reads index first, deduplicates before writing, tracks provenance, appends history rather than overwriting, and creates stubs for mentioned-but-unresearched topics. Pure markdown, no embeddings, no external network.

Engineering Design Support System. Use this skill whenever the user is doing long-horizon product/engineering design and wants to capture intent, decisions, risks, assumptions, evidence, open questions, or hypotheses; whenever they say 'add a decision', 'propose a hypothesis', 'what did we rule out', 'what changed', 'generate a status report', 'show whitespots', 'sharpen this', 'mission', 'realign', or ask what the project knows; at session start to load mission + state; and as the curator/researcher/synthesizer/critic loops. The mission is the versioned north star; the RDF knowledge graph is the system of record for a typed dependency graph (Concept/Decision/Risk/Assumption/Evidence/OpenQuestion/Gap/Whitespot/Hypothesis/Test); the scrapbook is a projected view; the wiki is synthesized prose; hypotheses run as stateful workflows. Pull-only: never push to the engineer except a critic mission-contradiction.

Use this skill whenever the user wants to take structured notes, collect ideas, organize project requirements, or manage a project notebook — trigger on phrases like 'scrapbook', 'add a note', 'what have we captured', 'notebook', 'show my notes', 'what should I focus on', 'jot this down', or any request to review, prioritize, or organize project items. Reads and writes to the project scrapbook via MCP tools, presenting content as a structured hierarchy with priorities and focus levels.

Create and manage XState-based stateful workflows with human-in-the-loop support via MCP tools

Assemble a Word .docx by copying sections from one or more source PDF/Word documents in source/ into a target template in target/, applying per-section transformation instructions (translate, summarize, include/exclude images). Driven by source-target.sectionmappings.json. Trigger on "create the document", "build the target docx", "generate the document from the mappings", or when the user finishes the section-mapping dashboard.

Describes the agent's personality, current capabilities and its relation to the user. Answers questions like 'Who are you?', 'What can you do for me?".

Index and search documents using semantic search (RAG). Automatically indexes files in the project's documents/ folder and enables natural language document retrieval.

Offline reflection on the project's recent chat sessions. Use when the user asks "what did I learn last week?", "summarize my recent sessions", "what strategies emerged?", or wants to see/manage the strategy memory under .agent/wiki/. Provides background on the dreaming pipeline (HARVEST/SEGMENT/REFLECT/DISTILL/GROUND/CONSOLIDATE/PROMOTE/INDEX) that runs nightly to maintain strategy SKILL.md cards under .claude/skills/strategies/<domain>/<id>/, and a feedback artifact at dreaming/dream-<date>.dreams.json. Reads .agent/wiki/ for prior strategies, never invents one without trajectory support, and asks the user before acting on a contested strategy.

Parse and extract text from Office documents, PDFs (including scanned/image-based PDFs), and images. Trigger on phrases like 'parse this PDF', 'extract text from Word file', 'read this spreadsheet', 'convert document to text', 'parse this .docx', 'extract content from PowerPoint', 'OCR this', 'read scanned PDF'. Uses LiteParse for local, spatial text extraction with built-in OCR. THIS IS THE ONLY TOOL FOR DOCUMENT PARSING — never use Python, pdf2image, pytesseract, PyPDF2, pdfplumber, or any other approach.

Guides the agent to create professional public websites with React/MUI served from the project's /web subdirectory with hot-reloadable API endpoints

Allows the agent to create cron job to execute actions later or regularly

Validate parameters against both WHO and EU standards even when targeting one jurisdiction. Use when: evaluating compliance for a water treatment design. Provides: check every critical parameter against both WHO and EU limits separately, even if deployment is outside the EU.

Ground TCO analysis in regional reference cases with published data. Use when: analyzing water treatment costs for a new geographic scenario. Provides: immediately cite a nearby successful deployment (e.g., Bequia for Caribbean) with published capex, opex, and payback metrics; use it as an anchor to identify region-specific cost drivers.

Include small genset in PV+battery hybrid rather than 100% battery for island RO systems. Use when: designing a renewable energy system for remote island desalination with solar resource available. Provides: size a 70/30 PV+genset hybrid (e.g. 70% renewable, 30% genset backup) instead of 100% PV+battery, using the genset to enable emergency CIP cycles and evening load coverage.

Validate against multiple regulatory standards even when only one applies locally. Use when: A technology selection involves water quality standards or regulatory limits that vary by jurisdiction, and the local jurisdiction is outside the primary standard-setting region (e.g., EU, WHO). Provides: Evaluate the design against both the locally applicable standard AND the stricter international standard (EU, WHO). Document the comparison and make a deliberate choice about which to design to, even if only one is legally required..

Enables tracking of higher-level user tasks across projects using MCP tools

Crawl and extract content from websites. Saves pages as Markdown, HTML, or text into the web-crawling/ folder, organized by site. Supports static pages, JavaScript-heavy sites, and sites with bot protection.

Daily quality insights for the 3-machine factory line. Combines quality reports (xlsx), machine status (json), production orders (json), and MQTT events to surface root causes for the past 7 days. Emits useful findings as quick-action chips.

AI-powered image generation and editing using GPT Images 2.0 with thinking mode. Use this skill when the user wants to generate images, create illustrations, design infographics, edit photos, create consistent image series, or any visual content creation task. Triggers on phrases like "generate an image", "create a picture", "edit this image", "make an infographic", "design a series of images", "create illustrations for", "visualize this", or any request involving image creation or modification.

Deep scientific research pipeline with subagent orchestration, parallel web search, and citation management. Use this skill whenever the user asks for a literature review, scientific research summary, evidence synthesis, systematic review, or any deep research task that requires searching multiple sources and producing a cited report. Also triggers on phrases like "research this topic", "find papers on", "what does the evidence say about", "literature review on", or "deep dive into".

Use this skill whenever the agent communicates with external agents via the A2A protocol. It establishes auditable 'diplomatic channels' — dedicated counterpart projects (a2a-<agent-name>) in the workspace that store all exchanged files in a controlled exchange/ folder and maintain a human-readable conversation log. Trigger on any A2A tool invocation, inter-agent delegation, or when the user asks to collaborate with an external agent.

Use this skill when the user wants to send or receive emails, check an inbox, email someone a report or file, or when discussing email-based communication. Provides guidance on using the email_send and email_check_inbox MCP tools, and explains how incoming emails arrive as events on the agent bus.

Background learning skill that automatically extracts business entities and relationships from every user message, building a domain-specific ontology. Creates a .knowledge file for visual browsing. On first use, onboards by discovering the business model. Then silently maintains the ontology. Always active — never needs explicit invocation.

Use this skill when the user asks to install, set up, or deploy an agent persona (e.g., 'install supplyagent', 'set up supply chain agent', 'deploy agent persona', 'install persona'). Reads persona artifacts from agent-personas/, translates to the user's preferred language, and provisions sub-agents, cron jobs, knowledge graph structure, and dashboard into the current project.

Use this skill to understand Etienne's system architecture, service dependencies, and data layout. Consult when reasoning about what services are available, what credentials are needed, where project data lives, how skills depend on backend modules and external services, or how the UI viewer system works. Trigger phrases: 'what services are running', 'system architecture', 'what depends on what', 'where is the data stored', 'what credentials do I need', 'how does the viewer work'.

Report application issues for automated diagnosis and patching. Use when the user wants to report a bug, error, or malfunction. Guides users through creating a structured issue report with title, description, reproduction steps, expected and actual behavior. Issues are submitted to an admin for review before any automated repair is triggered.

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.

Orchestrates ontology-grounded decision support for Node.js applications using quadstore (RDF), ZeroMQ event-based condition monitoring, and an LLM reasoning layer. Use when the user wants to derive actionable decisions from a chat context, define conditions and actions on ontology entities, build or refine decision graphs, or export rule sets for the ZMQ execution layer.

Orchestrates ontology-grounded decision support for Node.js applications using quadstore (RDF), ZeroMQ event-based condition monitoring, and an LLM reasoning layer. Use when the user wants to derive actionable decisions from a chat context, define conditions and actions on ontology entities, build or refine decision graphs, or export rule sets for the ZMQ execution layer.

Automates RFQ intake via web form and email, calculates pricing from product definitions, and drafts HTML quote emails for sales review

Use this skill whenever the user wants to brainstorm, collect ideas, or visually structure their thinking — trigger on phrases like 'brainstorm', 'let's collect ideas', 'map this out', or any request for a mindmap, flowchart, or sequence diagram, even if phrased casually. Creates and maintains versioned Mermaid diagram files in an ideation/ folder, with automatic backups before every change and a living ideas.md index.

A Claude Code skill for managing voice calls via the Vapi MCP server. Supports making outbound calls, querying recent inbound/outbound calls, and summarizing call transcriptions.

Indexes and searches documents in the my-documents folder using knowledge graph vector store