Agent Wiggum Cli Federiconeri
Autonomous coding agent that scans codebases, generates feature specs via AI interviews, and runs Ralph loops via Claude Code, Codex CLI, or any CLI-based agent. Reads GitHub backlog, runs loops, and auto-merges PRs. Use when automating feature development end-to-end, running autonomous coding loops, managing GitHub backlogs with AI, or implementing the Ralph loop methodology.
Agent Ralph Wiggum Snarktank
Autonomous AI coding loop that runs AI coding tools (Amp or Claude Code) repeatedly until all PRD items are complete. Each iteration is a fresh instance with clean context. Memory persists via git history, progress.txt, and prd.json. Use when building features hands-free through iterative AI loops, shipping code while away, or implementing spec-driven development with the Ralph Wiggum technique.
Webfetch
Fetches web pages as markdown or HTML for LLM consumption. Use when the user wants to fetch, scrape, download, retrieve, grab, pull, or access any URL or webpage content. Supports uvx, pipx, curl, wget, and python3 fallbacks. Always impersonates Safari to avoid blocks. Use this whenever the user asks to read a website, get page content, or fetch a URL.
Agent Ralph Wiggum Ghuntley
Geoffrey Huntley's Ralph Wiggum technique — a monolithic iterative loop pattern for autonomous AI-driven software development. Use when building greenfield projects through repeated LLM invocations in a bash-style loop, tuning prompts through observation, and treating the loop itself as the programmable unit rather than individual tool calls or multi-agent orchestration.
Matplotlib 3 11 0
>
Basedpyright 1 39 8
>
Scipy 1 17 1
SciPy (scientific Python) library reference for mathematics, science, and engineering. Covers optimization, integration, linear algebra, statistics, signal processing, FFT, interpolation, sparse matrices, spatial algorithms, special functions, image processing, clustering, I/O, and physical constants. Use when the user needs scientific computing in Python, numerical methods, data analysis with sc…
Acp 0 12 2
Protocol standardizing communication between code editors and AI coding agents using JSON-RPC 2.0 over stdio. Decouples agents from editors for cross-compatibility. Use when building AI coding agents needing editor interoperability, implementing persistent sessions with tool calls, connecting agents via MCP delegation, or working with the official SDKs.
Agent Ralph Wiggum Loop Beuke
Principles and conceptual framework of the Ralph Wiggum Loop pattern for goal-oriented autonomous AI agent loops. Covers agentic loop structure, failure modes, safety implications, control theory comparisons, and best practices. Use when designing or reasoning about iterative AI agent systems that act, check feedback, and repeat until a completion criterion is met.
Ruff 0 15 18
>
Cbc 2 10 13
>
Rqlite 10 2 4
>
Agent Nirzabari 0 1 0
Comprehensive guide to understanding and building coding agent harnesses, covering 7-layer architecture, context engineering, tool orchestration, safety systems, and real-world implementations from Codex, OpenCode, Cursor, and Claude Code. Use when designing agentic systems, analyzing agent architectures, or studying production-grade coding agent implementations.
Agent Ralph Loop Claude
Implements the Ralph Wiggum technique as a Claude Code plugin for iterative, self-referential AI development loops. Use when building projects that require hands-free AI implementation through continuous bash-style loops inside a single Claude Code session, where the same prompt is repeatedly fed back until completion criteria are met.
Requests 2 34 2
>
Scikit Learn 1 9 0
>
A2a 1 0 0
Open standard for communication between independent AI agent systems. Agents discover capabilities via Agent Cards and collaborate on tasks with streaming without exposing internal state. Supports JSON-RPC 2.0, gRPC, and HTTP+JSON bindings with enterprise security. Use when building multi-agent systems requiring agent discovery, task collaboration, or secure inter-agent communication.
Pandoc 3 10
Convert documents between formats using Pandoc 3.10. Use when the user mentions pandoc, document conversion, format transformation, or needs to convert between Markdown, HTML, LaTeX, PDF, Word (docx), OpenDocument (odt), PowerPoint (pptx), Excel (xlsx), CSV, TSV, EPUB, reStructuredText, Org mode, AsciiDoc, RTF, Textile, CommonMark, GFM, or any markup/format conversion task. Also use when user ask…
Pandas 3 0 3
>
Skman
Scaffold, validate, and inspect agent skills (SKILL.md files). Use when creating new skills, checking skill format compliance, or reviewing skill structure.
Agent Coding Wyattdave 0 1 0
A toolkit for creating custom AI coding agents using prompt engineering, instruction files, and skill modules. Use when building bespoke coding assistants for niche domains where general LLM training data is insufficient or misleading, particularly for specialized frameworks like Power Platform Code Apps with vanilla JavaScript.
Aiohttp 3 13 5
Async HTTP client/server for Python asyncio. Use when building async web applications, REST APIs, or making concurrent HTTP requests in Python.
Pytest Asyncio 1 4 0
>
Pulp 3 3 2
>
Uv 0 11 23
>
Plan
Phase/task based workflow system with PLAN.md as single source of truth. Use when tackling projects that require structured iteration through Planning, Analysis, Design, Implementation, Testing, Deployment, Maintenance, etc phases with clear dependency graphs.
Sympy 1 14 0
>
Pyomo 6 10 1
>
Mermaid 11 15 0
>
Agentmemory 0 9 4
Persistent memory engine for AI coding agents with cross-session context capture, hybrid search (BM25 + vector + knowledge graph), and multi-agent coordination via MCP server. Works with Claude Code, Cursor, Gemini CLI, and any MCP client without external databases. Use when building AI coding agent workflows requiring persistent memory or semantic recall.
Vega Lite 6 4 3
>
Agent Ralph Wiggum Fstandhartinger 0 3 0
Autonomous AI coding with spec-driven development combining iterative bash loops and SpecKit-style specifications for fully autonomous AI-assisted software development. Use when building projects that require hands-free AI implementation, working from specification files, or running autonomous development loops with completion verification.
Sqlalchemy 2 0 51
>
Duckdb Python 1 5 4
DuckDB Python client 1.5.4 API reference and usage patterns. Use when working with the `duckdb` Python package — in-process analytical SQL database. Covers connection management, relational API (lazy evaluation), data I/O (CSV/Parquet/JSON), Python UDFs, type system, pandas/PyArrow/Polars integration, fsspec filesystems, ADBC driver, profiling, and extensions. Trigger on: duckdb, DuckDBPyConnecti…
Agentmemory 0 8 10
Persistent memory engine for AI coding agents with cross-session context capture, hybrid search (BM25 + vector + knowledge graph), and multi-agent coordination via MCP server. Works with Claude Code, Cursor, Gemini CLI, and any MCP client without external databases. Use when building AI coding agent workflows requiring persistent memory or semantic recall.
Tzip
Lightweight token-pruning communication mode that drops filler and hedging while keeping full sentences and professional tone. Follows guidelines for code quality. Default intensity is lite. Use when user requests tzip, prune tokens, be concise, or needs efficient communication without losing clarity.
Jq 1 8 2
jq 1.8.2 — lightweight command-line JSON processor. Use when the user needs to parse, query, transform, or manipulate JSON data from the command line, process API responses, extract fields from JSON, convert between formats (JSON-to-CSV, JSON-to-XML), validate JSON, or work with any structured data in JSON format. Covers filters, builtins, regex, modules, streaming, and all jq 1.8.2 features.
Agentmemory 0 8 9
Persistent memory engine for AI coding agents providing automatic cross-session context capture, hybrid search (BM25 + vector + knowledge graph), and multi-agent coordination via MCP server with 43 tools. Works with Claude Code, Cursor, Gemini CLI, OpenCode, Hermes, OpenClaw, and any MCP client without external database dependencies. Use when building AI coding agent workflows requiring persisten…
Agent Coding Mini Rasbt 0 1 0
Minimal standalone coding agent framework by Sebastian Raschka backed by Ollama, providing workspace context collection, tool execution with approval gates, session persistence, and subagent delegation. Use when building lightweight local coding agents for file manipulation, shell commands, code editing, or automated workflows without external API dependencies.
Agent Ralph Loop Vercel Labs
Continuous autonomy framework for the Vercel AI SDK implementing the Ralph Wiggum technique — an iterative outer loop that keeps feeding an AI agent a task until verifyCompletion confirms success. Use when building autonomous coding agents, long-running code migrations, refactoring tasks, or any workflow requiring iterative verification and feedback loops beyond single-shot LLM tool calls.
Formulas 1 3 4
Evaluate Excel formulas in Python without Excel. Use when the user needs to compute spreadsheet formulas, calculate xlsx files, convert formula-based spreadsheets to calculated values, export Excel to CSV/JSON, run batch scenarios, build JSON models from workbooks, or serve spreadsheets as a Flask API. Also triggers on mentions of formulas package, openpyxl calculation, or spreadsheet automation.
Duckdb 1 5 3
DuckDB 1.5.3 — high-performance analytical OLAP database with embedded SQL engine. Use this skill whenever the user queries about DuckDB, needs to run SQL analytics on local files (CSV, Parquet, Excel/XLSX), wants to install or use extensions (excel, json, icu, parquet, httpfs, delta, iceberg, postgres_scanner, sqlite_scanner, fts, spatial, and others), needs data import/export workflows, or is c…
Aiohttp 3 13 0
Async HTTP client/server for Python asyncio. Use when building async web applications, REST APIs, or making concurrent HTTP requests in Python.
Ty 0 0 51
Run ty (Astral's Python type checker, v0.0.51) for type checking, rule diagnostics, and language server integration. Use when the user mentions ty type checking, Python type errors, ty check, ty rules, ty suppression, migrating from mypy or pyright to ty, configuring ty.toml or pyproject.toml type checking, or setting up a Python language server. ty is 10x-100x faster than mypy/Pyright and suppor…
Networkx 3 6 1
>
Git
Git version control. Use when the user mentions git, commits, branches, pushing, pulling, merging, rebasing, stashing, worktrees, submodules, or any version control task. Covers straightforward workflows (add/commit/push) and advanced topics.
Numpy 2 4 6
NumPy 2.4.6: array creation, manipulation, broadcasting, ufuncs, linear algebra, statistics, random sampling, structured arrays, and I/O. Use whenever working with numerical arrays, matrices, scientific computing, data analysis, or any task involving NumPy operations. Covers ndarrays, dtype system, einsum, stride tricks, masked arrays, FFT, polynomials, and the full NumPy 2.x API.
Pytest 9 1 0
Write, run, and debug Python tests with pytest 9.1.0. Use when the user mentions pytest, writing tests, test fixtures, parametrization, test discovery, conftest.py, pytest plugins, test marks, skip/xfail, monkeypatch, tmp_path, capsys, caplog, assertion rewriting, or any Python testing task.
Yq 4 53 3
Query, transform, and convert YAML, JSON, XML, INI, TOML, HCL, CSV, TSV, Properties, Lua, Shell variables, and Base64 data using jq-like expressions. Use when the user mentions yq, YAML processing, JSON-to-YAML conversion, config file manipulation, Kubernetes YAML editing, or any structured data transformation task. Supports multi-document YAML, anchors/aliases, comments, and in-place updates.
Websearch
Searches the web via DuckDuckGo and returns results as markdown, CSV, or JSON. Use this skill whenever the user wants to search the web, look up information online, find URLs, do web search, research a topic, or needs current/web-based answers.