Start with the job, then find an open-source answer

searching-apple-notes lets Claude query and update an Apple Notes archive through natural language in Chinese or English. BGE-M3 embeddings and ChromaDB run locally on the Mac, with citations in answers and formatted notes written back; no API key, MCP setup, or third-party server is required, aside from downloading the model once.

Browser Tools gives coding agents a Chrome DevTools Protocol interface for launching isolated browser sessions and validating real pages. Agents can navigate, inspect and interact with the DOM, capture screenshots, and diagnose console or network activity. Chrome for Testing support helps make browser setups more repeatable.

claude-skills-collection is a curated set of drop-in Claude Code skills for automation, data extraction, code generation, and productivity work. It is aimed at people who want to extend Claude with reusable capabilities instead of assembling each workflow from scratch.

This Claude Code skill starts a Metalsmith project from the micro starter, asks discovery questions, selects reusable components, and builds pages with the expected YAML frontmatter. You can refine the site through live-preview feedback and then receive help pushing to GitHub for Netlify deployment. Node.js 18, Git, GitHub, and a connected Netlify account are prerequisites.

GPSE Skill adds Google Programmable Search Engine queries to Claude Code, with filters for dates, sites, exact phrases, and excluded terms. It supports paginated results and formats titles, links, and snippets as Markdown, using plain JavaScript without external packages. Setup requires a Google Cloud project with the Custom Search API enabled, an API key, and a Programmable Search Engine ID.

PinMeTo Location Reports Skill converts multi-location analytics into polished PDF and PowerPoint reports for board meetings, executive presentations, quarterly reviews, or marketing summaries. It can be used with Claude Desktop, Claude.ai, or Claude Code. A PinMeTo MCP server connected to the user's account is required, and desktop or web use also needs code execution and file creation enabled.

Buildkite Skills offers eight installable workflows for checking build status, retrieving logs, diagnosing failures, troubleshooting stuck agents, unblocking approvals, triggering builds, analyzing skipped steps, and editing pipeline YAML. Users can ask for these actions in natural language rather than navigating each Buildkite screen manually. The skills rely on Buildkite's remote MCP server with OAuth, so a Buildkite account and an AI client that supports skills and MCP are required.

DocuGen turns a recorded or described web workflow into step-by-step documentation with annotated screenshots and contextual explanations. It can highlight click targets, blur sensitive values such as passwords and API keys, and adapt the guide for different audiences. The tool requires Python 3.8 or newer and Claude Code or Claude.ai with Playwright MCP.

The Metric Mandate guides an AI project through five concrete decisions: the number that should change, its current baseline, the minimum worthwhile improvement, when it will be measured, and what outcome should stop the project. It rejects vague answers and stress-tests whether a metric can be improved without solving the real problem. The result is a concise table of success criteria and metric gameability before implementation begins.

Moodle Herd Installer Skill gives Claude Code, OpenCode, and similar assistants a focused procedure for installing Moodle 5.x on Laravel Herd. It addresses the new public directory layout, broken CSS or JavaScript responses, gzip decoding errors, Nginx slash arguments, and database driver selection. The repository includes a configuration template and an Nginx snippet, and is intended specifically for this local Moodle and Herd setup rather than general deployment.

BIAN Skill helps banking architecture teams describe capabilities through standardized business areas, service domains, and service operations, then use those definitions to shape APIs and system boundaries. It covers domains such as customer and party data, payments, products, channels, risk, and compliance, with guidance for current-state mapping, gap analysis, and phased modernization.

Decision Memory watches product conversations for moments such as accepting, rejecting, deferring, merging, or shipping an idea. It asks for the reasoning and any revisit or notification details, then formats the result as a searchable decision record and closure-message draft. The skill works on its own with Markdown output, while an optional IdeaLift MCP connection can persist records and link them to ideas.

Use this skill when creating Gutenberg blocks, dynamic rendering, or Full Site Editing features in Claude Code. It covers block.json, InnerBlocks, variations, transforms, WordPress scripts, and server-side rendering, and can activate automatically or be invoked with /wp-gutenberg.

Use this skill to review or implement accessibility in WordPress themes with Claude Code. Its guidance covers WCAG 2.1 AA concerns such as skip links, landmarks, color contrast, forms, screen-reader support, keyboard navigation, and focus management, with automatic or direct invocation after installation.

Use this Claude Code skill when moving a WordPress plugin or theme to PHP 8.x. It covers language features such as named arguments, union types, match expressions, enums, readonly properties, and constructor promotion while keeping backward-compatibility strategies in view.

Council sends the same review prompt to several configured AI coding agents in parallel, then asks the host agent to synthesize a deduplicated report for staged Git changes. It can mix Claude Code, Codex, OpenCode, and Cursor backends, but requires at least one supported and authenticated CLI.

Zero-Context Validation checks whether documentation is truly sufficient by giving a fresh sub-agent only the docs and a concrete implementation task. Any missing interface, file location, or contract must be reported instead of guessed, so the main agent can revise the material and repeat the test. It is designed for Claude Code or compatible agents and uses their built-in task mechanism.

UED Copilot reviews screenshots or design-system materials for visual hierarchy, interaction flow, usability, accessibility, and platform conventions across web, iOS, and Android. It can use a team's own standards or fall back to Apple HIG, Material Design, Nielsen heuristics, and WCAG guidance. The Claude Code skill presents issues interactively and can include concrete code changes and implementation steps.