Data

Take a client's externally-hosted project (Lovable export, a repo on another GitHub/GitLab, a dev project) and re-home it onto your own GitHub + Vercel, then…

Migration and housekeeping utilities for BMad artifacts and l3io-pm state.

Use this skill when creating a new OpenSpec spec whose name follows `wi-<azure-devops-work-item-id>-<change-name>` so the spec can be enriched from Azure…

Produces a self-contained plan folder for **one scoped change** — `context.md`, a design doc explaining the approach, key decisions, and data flow with…

Agree on the UI structure with a low-fidelity wireframe before writing any production frontend code, then lock it.

Fully automatic repository health audit with mandatory silent remediation loop.

Detect, choose, build, evaluate, migrate and document software architecture.

Mutation testing for a data pipeline's quality checks: generates deliberately corrupted copies of a dataset (duplicated samples, dropped rows, shuffled…

Compares a frozen analysis plan (primary metric and direction, estimand, sampling and group units, split digest, multiplicity allocation, practical margin…

Audits the provenance chain of a result: every source, intermediate and output artifact as a versioned id, each transformation's required inputs and stages…

Audit paired model, assay or pipeline losses when many observations belong to a few independent donors, plates, sites or training runs.

Compares two independent implementations of the same analysis (R vs Python, student vs postdoc, old vs refactored pipeline, paper table vs re-run) quantity by…

Audits a tabular dataset before training or evaluation for exact duplicate rows across train/test, the same subject, patient, cell line or sensor appearing in…

Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page…

Reference for the /start pipeline - workspace layout, state keys, phase machine, ruling and finding formats, and the shared scripts.

Rewrite or review human-facing prose to remove generic AI mannerisms while preserving meaning, facts, uncertainty, citations, intended voice, and project…

Conduct version-matched deep research with MCP tools and citation tracking.

Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude.

Resolve the unanswered questions in a Ready Agent 1 readiness report by interviewing the developer, then record the answers as engine inputs and re-score.

UI/UX design intelligence.

Turn markdown drafts, outlines, rough notes, or mixed document materials into polished DOCX/PDF deliverables with a repeatable pipeline that normalizes…

ego-browser (ego-lite) is a Chromium-based browser designed from the ground up to be friendly to both human users and AI Agents.

Update and verify the private Madabot usage dashboard.

Dataset annotation management — COCO labels, sequences, export, and Kaggle upload