The stack behind smarter agents.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

A git safety tool that sets up hooks to block dangerous git commands before they execute, preventing destructive operations in code repositories.

Writing, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Compact the current conversation into a handoff document for another agent to pick up.

Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

wait-what is an AI agent tool designed to request clarification and rephrase messages to ensure clear communication and understanding.

An AI tool that organizes and shapes raw textual material into a structured article, paragraph by paragraph, facilitating content creation and presentation.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

Hand the current conversation off to a fresh background agent that picks up the work immediately.

An interactive, stateful workspace designed to teach users new skills or concepts through structured lessons, resources, and learning records.

A developer tool for migrating TypeScript test files to use type-safe partial data assertions with @total-typescript/shoehorn instead of unsafe 'as' type assertions.

An AI tool that rigorously questions and evaluates plans or decisions by constructing and exploring a branching design tree of user decisions to achieve thorough understanding and stress-test thinking.

Ask which skill or flow fits your situation. A router over the skills in this repo.

An AI tool designed to conduct rigorous interview-style sessions to refine plans or designs.

An AI tool that automates the creation of targeted questionnaires to gather information from others in order to aid decision-making.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

A tool that automates setting up Husky pre-commit hooks with lint-staged, Prettier formatting, type checking, and tests in a code repository.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

Implement a piece of work based on a spec or set of tickets.

Use when you need to resolve an in-progress git merge/rebase conflict.

Grill me about specs for the workflows I want to build, within this workspace.

A tool designed to facilitate the structured writing and editing of agent-related documents and skills for AI agents, focusing on clarity, modularity, and efficient context handling.

Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

An AI tool that assists users in exploring and collecting unstructured writing fragments to aid creative writing and idea development.

n8n is a workflow automation platform with native AI capabilities, offering visual building and custom coding with over 400 integrations.

JS API for Yahoo Finance

Agent-native CLI for AI app automation across iOS, Android, tvOS, Android TV, macOS, Linux, and web.

An open-source AI agent that brings the power of Gemini directly into your terminal.

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

GitLab MCP server for projects, merge requests, issues, pipelines, wiki, releases, and more

ato-mcp is an AI agent specializing in Australian tax, providing cited answers and tools for income tax, GST, deductions, depreciation, BAS, and audit risk management.

Live global intelligence: real-time markets, conflicts, country risk, chokepoints, energy. 39 tools.

The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches

🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!

🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

TrendRadar is an AI-driven tool that monitors public opinion and trends across multiple platforms with intelligent filtering, translation, and smart alerts for real-time analytics.

Context7 provides up-to-date code documentation tailored for LLMs and AI code editors to aid developers.

Chrome DevTools for coding agents

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this,"...