MCP App StoreMCP App StoreSKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
claude-code-plugins-plus-skills
Refactor features toward the intended architecture: remove legacy cruft and simplify code to reduce long-term operational cost.
zylos-core
Channel skill that connects a CLI REPL to a Claude-like backend via a Unix socket, routing user input to the agent and delivering responses back to the REPL.
skills
Guidelines and examples for calling Python from Mojo and building Python extension modules in Mojo, with patterns for conversion, error handling, and module exp
vyper
Developer-focused guidance for working on the Vyper smart contract compiler: compilation pipeline, Venom IR, semantic analysis, codegen, testing, and contributi
better-icons
CLI and MCP skill to search 200+ icon libraries (Iconify) and retrieve SVGs for projects or AI agents.
repo-task-proof-loop
A repo-local workflow skill that creates auditable task folders and runs a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.
agent-lsp
Simulate code edits in-memory using an LSP-backed session to verify diagnostics and prevent breaking changes before writing to disk.
inkbox
Index of Inkbox skills: a directory and guide to Inkbox SDKs, CLI tools, and example skill prompts for agent identity, email, telephony, and vault integrations.
sage
Create, iterate on, and evaluate Agent Skills: write SKILL.md, design test cases, run benchmarks, and improve triggering and performance.
evjs
A React full-stack framework with type-safe routing, server functions (RPC), and TanStack integration for data fetching and routing.
codex-toolkit-for-claude
Canonical reference for Claude Code plugin schemas, frontmatter, hook events, and naming conventions — used when auditing or authoring Claude Code plugins.
claude-plugins
Quick reference for writing Python tests with pytest: fixtures, parametrization, coverage, mocking, and async testing.
auto-empirical-research-skills
Control and automate an Obsidian vault from the command line: read, create, search, update notes, manage tasks, and support plugin/theme development.
langium-ai
CLI to generate language descriptors, synthesize system prompts, and run evaluations to iteratively refine AI tooling for Langium projects.
claude-build-workflow
Convert product requirement documents (PRDs) or Markdown specs into Ralph's prd.json format, producing small verifiable user stories for autonomous execution.
code-abyss
Generates README.md and DESIGN.md scaffolds from a module's code and structure to accelerate project documentation.
tldraw
Create or update a pull request for the current branch, following repository PR standards and best practices.
claude-skill-registry
Structured debugging playbook for Python: triage, diagnostics, async/concurrency fixes, performance and memory profiling, and reproducible testing workflows.
skills
Run CLI commands, tests, and debugging reliably inside the project's Linux devcontainer to avoid host-architecture mismatches and preserve isolated test state.
manten
Compact Node.js testing patterns with standalone imports, AsyncLocalStorage-based context, concurrency controls, hooks, snapshot testing, and simple timeouts/re
specialist-agent
Run fresh verification commands (tests, build, lint, types) and require full output evidence before claiming work is complete or merging changes.
nevaberry-plugins
Add knowledge about Drizzle ORM changes (v1.0.0-beta.x) — validator import consolidation, Effect Schema support, node-sqlite driver, and .comment() query taggin
solana-clawd
Guides integration with MagicBlock ephemeral rollups on Solana: delegation flows, VRF, cranks, magic actions, lamports top-ups, and private payments for high-pe
ask-codex
Routes heavy repo exploration, implementation, and verification work from Claude Code to the Codex CLI with clear review loops and verification requirements.
feishu-cli
Export Feishu docs, wikis, and spreadsheets to local files (Markdown, PDF, DOCX, XLSX); supports image downloads, embedded sheet expansion, and async exports fo
tilth
A CLI for AST-aware code reading, search, callers, and structural diffs across many languages — faster, cheaper code intelligence for humans and agents.
agenvoy
Generate concise bilingual commit messages (English subject + Traditional Chinese body) from staged git diffs, with multi-topic detection and tag prioritization
skillpack
Convert a finished task or workflow into a reusable SkillPack with local skills, prompts, scripts, and an optional zip package.
specialist-agent
Generate an implementation plan matched to task complexity — from quick mini-plans to full design documents — before writing code or making large changes.
swiftbutler
CLI to analyze, syntax-check, reindent, and split large Swift source files for easier inspection and tooling.