vadimcomanescu

AutoGPT platform for building, deploying, and running continuous autonomous agents. Use for visual workflow agents, persistent automation, and multi-step AI systems.

LangChain framework for building LLM apps with agents, chains, and RAG across providers. Use for chatbots, tool-calling agents, and retrieval workflows in prototypes or production.

LlamaIndex framework for data-centric LLM apps and RAG. Use for document ingestion, indexing, querying, and building retrieval-driven chatbots or knowledge tools.

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

Toolkit for styling artifacts with consistent themes (slides, docs, reports, HTML landing pages). Includes 10 preset color/font themes and a workflow for applying or generating a custom theme.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modifying existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas.

Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity tracking. Use for story writing, sprint planning, stakeholder communication, and agile ceremonies.

Verify an implementer's diff with an INDEPENDENT, different-vendor sub-agent (diff plus contract only); turn blocking issues into fix-tasks and loop until clean.

Run independent subtasks in parallel — one git worktree and one implementation sub-agent per task, each opening its own PR — then cross-review every PR. maestro never merges; the human does.

Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a synthesis. Use when the user wants the two perspectives stress-tested against each other, not just shown side by side.

Load per slice — the COORDINATOR's 3-role dispatch sequence (specifier → coder → refactorer, SEPARATE sessions, a handback to the coordinator between each) that drives ONE vertical slice from a failing acceptance test to refactored green in a single worktree. Load for every slice the wavefront dispatches.

Load ONCE at planning (coordinator + specifier) to turn a PRD into right-sized vertical slices tagged produces/consumes/touches, derive the dependency DAG, and tag the spine. Load before any slice is dispatched.

Load ONCE as the coordinator's orchestration loop after the DAG is built. Land the spine, then drive dependency-ordered waves of parallel independent slices until the DAG drains, and finish with the architect verification.

Load ONCE at the end — the final whole-feature join by a fresh architect at the integration HEAD. Run gates, mutation, and cross-slice DRY over the assembled feature and SIGN-OFF or BOUNCE, attributing each failure to its owning slice.

Load after each wave completes — owned by the coordinator/integrator, not the architect. Dup-scan the wave's worktrees to DETECT cross-slice duplication (routed to the owning slice, never rewritten inline), merge each slice branch into the integration branch one at a time re-greening the gates, and bounce anything beyond a mechanical merge-marker conflict to the owning slice's own session.

Generate a DESIGN.md from a live website URL, following Google's open DESIGN.md spec. The agent captures a viewport screenshot, samples colors and typography directly from the pixels, emits YAML frontmatter (tokens) plus canonical markdown sections, and validates the output with the official `@google/design.md` linter. Triggers on "extract design system from <url>", "generate DESIGN.md from <site>", "site to design md", "design audit of <url>", or any request to derive a design-system document from a live web page.

Generates visual assets (icons, illustrations, logos, hero images, background patterns, section dividers, Lottie animations, short video clips) by routing each request to the best AI provider and running a provider-tuned prompt. Use when the user asks for any graphic, image, icon, SVG, logo, hero, background, illustration, pattern, avatar, animation, or video asset. Routes between agent-svg (the calling agent authors SVG directly, with Recraft --format svg as the deterministic fallback for non-LLM agents), Recraft (vector and Lottie), FLUX (artistic raster), OpenAI Images (photorealistic), Ideogram (typography-heavy), Nano Banana (general raster), and Veo (video). Includes interactive credential setup via scripts/setup.js when providers are unconfigured.