Skill UI

This skill helps identify explanatory attributes or hypotheses for variations in process metrics such as duration, waiting time, utilization, and rework. It involves checking metadata correlations, statistical evidence, and cohort comparisons to distinguish competing explanations. The method emphasizes evidence-based analysis, avoiding silent assumptions, and framing findings as testable hypotheses rather than definitive causal claims. It supports structured investigation of process efficiency and bottlenecks using specific analytical tools and frozen baseline scopes.

Read a paper and write study annotations into its PDF via zotero-cli: a context box, a four-part abstract summary, role-coded highlights, one box per figure panel with teaching comments, and a reading note.

Geolocates and chronolocates photos with tool-verified reasoning: metadata and OCR intake, reverse image search, candidate ranking, satellite and street-view matching, sun and shadow math. Outputs coordinates with error radius, evidence images and tiered confidence.

Access MCP (Model Context Protocol) servers and their tools, resources, and prompts through the mcpdo CLI. Offers commands for listing, connecting, inspecting, and scripting against MCP servers (stdio or HTTP), extending your capabilities with external MCP connections.

Find animation, short-video and motion-design references through the 1human human-agent shared library. Search public feeds and agent-recommended repos, review saves and preferences, and publish creations only with prior owner authorization.

Run assay on a web page you just wrote or changed: it serves the page locally, opens it in a real Chromium browser via Playwright, exercises every control, and reports where the page contradicts itself. No LLM API key required.

This skill explains compiler and runtime errors when users paste error messages. It reads the error and surrounding code, then provides explanations and fixes. Notably, explanations are always written in French regardless of the user's language. It also offers detailed examples if further clarification is requested.

A browser runtime skill that provides isolated WPE WebKit sessions, native input, screenshots, and ordered JSONL automation. Supports docker-based container lifecycle, deterministic testing, and GitHub Actions verification. Useful for reproducible browser checks and self-hosted runtime integration.

Looot is an MCP server providing access to over 2,500 data API endpoints. It allows users to search for work emails, company information, SERP results, and web pages from a single prepaid balance. Ideal for enriching person or company data, analyzing SEO metrics, scraping web content, and retrieving social media profiles. It supports various tools like Claude, Cursor, and Gemini via the Model Context Protocol.

Build or fix frontends to look designed, not AI-generated. Includes taste direction, craft floor checklists, and browser-based quality gate that renders pages at phone and desktop widths, catching overlap, low contrast, and AI-slop defaults. Proof before calling work done.

This skill fetches public webpages and converts them into clean Markdown format suitable for AI agents. It allows users to read, summarize, quote, or cite webpage content while preserving the original source URL. The workflow involves sending a GET request to a specific endpoint to retrieve the rendered content. It is designed for read-only access and does not support private pages or content modification.

This skill identifies hidden risks in code changes beyond the diff and verifies safety by executing real code. It helps determine the blast radius of modifications before merging or designing, ensuring multi-file edits and shared path updates do not break existing clients or systems.