Browse the directory

Compile JSON Schema (draft-07, 2019-09, 2020-12) into fast validators with Ajv, report every failure by its instancePath, and use Ajv options to coerce types, apply defaults, and remove unknown properties so incoming JSON is both validated and normalized.

Validates JSON files against their schemas when modified to ensure data integrity.

Configure MCP servers in the Claude Desktop app by editing claude_desktop_config.json. Grounded walkthrough covering config file locations, the mcpServers JSON structure, the filesystem server, and how to verify and troubleshoot the connection.

Turn CSV, JSON, or Excel data into publication-ready charts with Python: load it with pandas and render bar, line, scatter, and statistical plots in matplotlib (with seaborn styling), then export high-DPI PNG or SVG.

Pull text out of images, scans, and PDFs with the Tesseract OCR engine and OpenCV preprocessing. Run OCR in 100+ languages, read per-word confidence and page orientation (OSD), binarize and deskew for accuracy, and reconstruct tables into CSV or JSON.

Open-source toolkit from the Docling project for parsing PDF, DOCX, PPTX, XLSX, HTML, images, and more into a unified DoclingDocument, with advanced PDF understanding, OCR, and exports to Markdown and JSON for gen AI and RAG workflows.

Open-source Python library from dottxt for structured LLM generation, guaranteeing outputs that match a JSON schema, Pydantic model, regex, grammar, or multiple-choice set during generation across many model backends.

Official Flutter team Agent Skills for AI coding agents building Flutter apps, fixing layout issues, adding widget and integration tests, creating widget previews, applying layered architecture, routing, localization, JSON serialization, and HTTP workflows.

Apache-2.0 `gws` command-line tool for Google Workspace APIs with structured JSON output, dynamic Discovery API commands, npm and release installers, Gemini CLI extension metadata, and 100+ bundled Agent Skills.

Agent Skills for Obsidian by Steph Ango, teaching Claude Code, Codex, OpenCode, and skills-compatible agents to work with Obsidian Flavored Markdown, Bases, JSON Canvas, Obsidian CLI, vaults, plugins, themes, and Defuddle-powered web-to-markdown extraction.

Official Go SDK for Model Context Protocol servers and clients, maintained by the MCP project in collaboration with Google, with packages for MCP, JSON-RPC, OAuth primitives, OAuth protected-resource metadata, clients, servers, transports, examples, and conformance work.

Official Ruby SDK for Model Context Protocol clients and servers, published as the `mcp` gem with JSON-RPC handling, tool, prompt, and resource registration, stdio and Streamable HTTP transports, Rack/Rails integration, roots, sampling, elicitation, logging, cancellation, pagination, and RubyGems metadata.

Community reusable agent prompt for pre-publish review of MCP Registry server.json metadata using official quickstart and authentication documentation: namespace checks, package pointers, field validation, and duplicate listing detection.

Expert capability pack for reviewing Claude Code subagent transcript files, documented retention settings, compaction events, and summary handoff so verbose delegated work stays out of the main conversation.

Slash command that validates a HeyClaude Raycast extension feed JSON file against registry schema expectations: required entry fields, forbidden payload keys, HTTPS detail URLs, MCP install targets, and copy preview limits.

Source-backed workflow for publishing public MCP server metadata to the official MCP Registry with mcp-publisher, server.json, package verification, namespace authentication, and post-publish checks.

MCP server for Odoo ERP systems, with tools for reading records, discovering models and fields, aggregating data, diagnosing access, scanning addons, planning migrations, and running gated safe-write workflows.

PostToolUse hook that compares a just-edited OpenAPI or JSON Schema document against the version committed in git and warns about backward-incompatible drift — removed OpenAPI paths and removed required properties — so breaking API changes are surfaced before they ship. Advisory only; it never blocks the edit.

Read-only Claude Code PostToolUse hook that runs Biome's formatter, linter, and import-sorting checks on edited JavaScript, TypeScript, JSON, CSS, and GraphQL files without auto-writing changes.

Claude Code statusline that reads OSV-Scanner JSON results and prints a compact dependency vulnerability count for review sessions.

PostToolUse hook that keeps a project's README in sync with the code. When the README or package.json is edited it checks for the standard-readme core sections (Install and Usage) and verifies that the CLI commands exposed via package.json bin are documented. Advisory only; it never edits files.

Source-backed rules for reviewing AI-generated code that deserializes data before merge for insecure deserialization risk, covering native serialization formats (pickle, PyYAML, Java Serializable) that can execute arbitrary code on untrusted input, safe data-interchange alternatives, and class allowlisting/integrity checks when native formats can't be avoided.

A practical walkthrough of building and distributing a Claude Code plugin marketplace.

A practical walkthrough of running Claude Code non-interactively with claude -p: bare mode, output formats (text, json, stream-json), JSON schema output, piping stdin, auto-approving tools, and authentication for scripts and CI.

A practical walkthrough of structured outputs in the Claude Agent SDK: defining a JSON Schema via the outputFormat option, reading validated structured_output, type-safe schemas with Zod or Pydantic, and handling validation failures.

A source-backed collection for reviewing API contracts before release: OpenAPI drift detection, JSON Schema validation, GraphQL schema checks, Spectral lint review, Pact consumer contract verification, and generated clients or stubs from approved specs.

Use the built-in /hooks menu to inspect Claude Code hooks and configure them in settings.json so shell commands run deterministically at lifecycle events like PreToolUse, PostToolUse, and Stop.

Add Model Context Protocol servers to Claude Code with the claude mcp add CLI and the /mcp slash command, covering transports, scopes, and OAuth for remote servers.

A Claude Code statusline command (bash) that detects concurrent Claude Code sessions.

Scans for security vulnerabilities when package.json or requirements.txt files are modified.