codex-implementation-loop
Delegate implementation work to Codex (via the codex-companion runtime), then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex to write code, mentions handing off / delegating implementation to Codex, asks to work through a plan or spec unit-by-unit with Codex doing the coding, or wants a review-and-merge loop wrapped around Codex output â and also when resuming such a loop ("keep going", "next unit", "继ç»ä¸ä¸ä¸ª"). It encodes constraints that are expensive to rediscover: Codex runs in the real environment with effectively read-only git, must not be pointed at a full test suite by default, accepts only specific --effort values, and its self-report is a claim rather than evidence.
product-architect
Complete product development system with 31 specialized agents and 23 frameworks. Use when user asks to build a product, write a PRD, create a roadmap, plan an MVP, design an app, do a security audit, create a financial model, plan hiring, launch a product, set up operations, prepare for IPO, or write a compliance policy. Also triggers on help me plan, product strategy, go-to-market, fundraising, pitch deck, unit economics, competitive analysis, user personas, sprint planning, SOP, checklist for, or how do I start a company. Do NOT use for general knowledge questions, coding tutorials, or creative writing unrelated to product development.
fullstack
Senior Full Stack Engineer that builds production code with unit tests from architecture docs and UX specs. Trigger on build, implement, code, debug, refactor, full stack, frontend, backend, or auth implementation.
Book â interactive course
Turns a source book into a folder that works as a self-contained web course. The learner opens it in a browser, reads explanations written for a complete beginner, plays with small animations, answers quizzes, writes code that is checked by unit tests, and their progress is stored in a file next to
Decompose
Decompose text into classified semantic units. Authority, risk, attention. No LLM.
Mcp Units
An MCP server that provides some common units conversions for cooking
testing-conventions
Apply Envilder testing conventions for Vitest unit tests and LocalStack e2e tests. Use when adding or updating tests for command handlers, domain entities, adapters, CLI, or GitHub Action flows.
robot-bringup
Patterns and best practices for bringing up a complete ROS2-based robotics system on a robot's onboard computer, including systemd services, launch file composition, ordered startup, and production monitoring. Use this skill when configuring a robot to start ROS2 nodes on boot, writing systemd unit files for ROS2 launch, composing layered launch files for full robot stacks, setting up watchdog monitoring, configuring udev rules for deterministic device naming, or debugging boot-time race conditions. Trigger whenever the user mentions robot bringup, robot startup, systemd for ROS2, ROS2 on boot, launch file composition, robot boot sequence, udev rules for cameras or serial ports, watchdog for robot systems, automatic restart for ROS2 nodes, network configuration for multi-machine ROS2, log rotation for robots, graceful shutdown of robot stacks, or SSH-based remote debugging of robots. Also trigger for environment setup in systemd (sourcing workspaces), ordered startup with health checks, deterministic device naming, or any discussion of running ROS2 systems as long-running production services. Covers systemd on Ubuntu 22.04/24.04 with ROS2 Humble, Iron, and Jazzy.
api-endpoint-generator
Scaffold complete REST API endpoints with input validation, error handling, typed request/response, JSDoc or docstrings, and a unit test stub. Use when asked to create a new API route, endpoint, controller, handler, or REST resource in Express.js (TypeScript) or FastAPI (Python). Produces production-ready code following immutable patterns, Zod/Pydantic validation, and RFC 7807 error responses.
agent-integration
Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent support", or wants to run the full agent integration pipeline end-to-end.
Ad Account Auditor · ä»è´¹å¹¿åè´¦æ·å®¡è®¡
Use when auditing a paid ad account for ROAS quality, wasted spend, or measurement integrity before scaling; runs RQS scoring with veto checks and a SHIP/FIX/BLOCK gate on your own exported account data. Not for building campaign structure â use campaign-architect; not for creative units â use ad-creative-builder. ä»è´¹å¹¿åè´¦æ·å®¡è®¡/ROASè¯å
RTOpacks
Australian VET National Register — qualifications, units, skill sets, AQF ladders.
agent-estimation
Accurately estimate AI agent work effort using the agent's own operational units (tool-call rounds) instead of human time. Use when asked to estimate, scope, plan, or evaluate how long a coding task will take. Prevents the common failure mode where agents anchor to human developer timelines and massively overestimate. Outputs a structured breakdown with round counts, risk factors, and a final wallclock conversion.
test-gen
Generate unit tests for existing code
Newton API Design Conventions
Detailed patterns that supplement AGENTS.md. Read AGENTS.md first for the basics (prefix-first naming, PEP 604, Google-style docstrings, SI units, Sphinx cross-refs).
Commit, Push & Create PR
Commit changes in meaningful units and create a PR in one go.
sdlc-align
The **window** check. Every other alignment gate in LoopSmith looks at one unit of work: `sdlc-plan-review` §4 holds a single plan to the north-star, and `sdlc-retro` asks what a single goal taught. Neither can see the shape of *twenty* goals, and that is where strategy actually drifts â no singl
charlie
Your AI CFO for bootstrapped startups, named after Charlie Munger who embodied the principle that capital discipline is a competitive advantage. Provides financial frameworks for cash management, runway calculations, unit economics (LTV:CAC), capital allocation, hiring ROI, burn rate analysis, working capital optimization, and forecasting. Use for questions like "should we make this hire?", "how much runway do we need?", "what metrics should I track?", "how do I forecast revenue?", or any strategic financial decision at a self-funded company.
batch
Research and plan a large-scale change, then execute it in parallel across 5-30 isolated worktree agents that each open a PR. Use when the user wants to make a sweeping, mechanical change across many files (migrations, refactors, bulk renames) that can be decomposed into independent parallel units.
interactive-testing
Smoke-test the running Lightcode Electron app end-to-end via Chrome DevTools Protocol. Use when the user asks to "smoke test", "test the app", "verify the refactor in the UI", "open the app and click through", or otherwise wants Claude to drive the real running app instead of relying on unit tests. Boots dev server + Electron with CDP enabled, uses raw CDP or agent-browser as appropriate, walks the surfaces most relevant to the current diff (provider selector, ThreadDraftView, ChatPane, ThreadRuntimeRequestPanel, Browser panel), and reports findings with screenshots.
bead-workflow
The mandatory process for every unit of work. Use this skill whenever starting work on a bead, bug, feature, or task. Enforces claim â hypothesize â implement â test â validate â close â pause. Every transition is gated by PreToolUse hooks that block (exit 1) on violations. Ulysses REFLECT escalation activates automatically on 2 consecutive surprises. If you're about to write code, check a bead, close an issue, or start new work â this skill applies.
analyzing-dtc-stores
Use when the user provides a DTC or ecommerce store URL and asks for a teardown, breakdown, brand analysis, competitor teardown, investor memo, store audit, deep dive, or 'what's going on with [brand]'. Produces an investor-grade markdown teardown report covering brand, market, unit economics, supply chain, channel mix, marketing, reviews, agentic-commerce readiness, risks, and a falsifiable verdict. Triggers: 'dtc teardown', 'brand teardown', 'store teardown', 'competitor teardown', 'analyze this store', 'investor memo on [brand]', 'break down [store url]'. Do NOT use for SEO-only audits, design-system extraction, lead-gen scraping, or general web scraping with no brand/investor focus.
Skolverket MCP
MCP server for Skolverket's open APIs - Curriculum, School Units, and Adult Education
Atomic Commit
Atomic Commit helps create clean, atomic commits by analyzing changes, detecting mixed concerns, and ensuring each commit is a complete unit of work. Key words to detect are atomic, atomic commits, clean commits.
Development Tools
Run unit tests, integration tests, and development tasks for multigres
agent-recorder-fixtures
Record real OpenAI/Anthropic HTTP back-and-forth (requests + responses, including streaming text/event-stream) and print paste-ready Swift fixtures for SwiftAgent unit tests (ReplayHTTPClient) using the AgentRecorder CLI or HTTPReplayRecorder. Use when adding/updating any provider adapter tests (text, streaming, structured outputs, tool calls), when payload formats change, or when debugging agent loop mismatches by inspecting recorded JSON/SSE payloads.
acceptance-test-generation
Use when acceptance criteria need unit, integration, or end-to-end tests generated from implementation context
testing-clickup-cli
Run and manage tests for clickup-cli. Covers unit tests, e2e tests against a real ClickUp workspace, and the test data setup. Use when running tests, adding test coverage, debugging test failures, or setting up test fixtures.
bcsc-core-native-testing
Create native unit tests for Swift (iOS) and Kotlin (Android) code in the bcsc-core package. USE WHEN: testing native code, adding unit tests for native modules, writing XCTest or JUnit tests for bcsc-core, mocking native protocols or interfaces. DO NOT USE FOR: TypeScript/React tests, UI integration tests, or E2E tests.
EXECUTE IMMEDIATELY
Fierce ralph is a main-loop **Workflow** whose loop condition is owned by the SCRIPT, not narrated by an agent: a worker does the next unit of work, a verifier independently checks progress + completion against the real repo, and it repeats until done â bounded by a hard iteration cap, a token bud
Running Unit Tests
How to correctly run unit tests in the Subscribe with Google (swg-js) repository
quartz-unit-test-lock-recovery
Recover from CS2012 DLL lock failures when running Quartz unit tests
Google Workspace Mcp
Google Workspace Admin via MCP. Manage users, groups, aliases, org units.
block-and-density
Design urban blocks and optimize density using typological analysis, FAR calculations, and building configuration strategies. Use when the user asks about block dimensions, block layout, density calculations, FAR optimization, building footprint coverage, height-density relationships, block typologies, perimeter block design, courtyard blocks, tower-podium configurations, or massing studies. Also use when the user needs to understand how many units fit on a site, calculate gross vs net density, or optimize a block plan for daylight and privacy.
test-writing
Write comprehensive tests for code including unit tests, integration tests, and end-to-end tests. Use this to ensure code quality, catch bugs, and validate functionality.
qwik
Workflow and pitfall checklist for Qwik core development (packages/qwik). Use when the user mentions Qwik, packages/qwik, Signal/AsyncSignalImpl, reactive-primitives, serialization/hydration (serialize/inflate), or cursor queue; it enforces running unit tests immediately after any implementation change, following signal/async-signal patterns, and running build/E2E/API validations before finishing.
Pull Request Review Pipeline
End-to-end PR review: runs code review checklist, generates missing unit tests, then suggests refactoring improvements.
Io.Github.Rog0x/Math
Calculator, units, statistics for AI agents