juxt/allium
Give your AI agents something more useful than a prompt. Velocity through clarity.
Give your AI agents something more useful than a prompt. Velocity through clarity.
npx skills add https://github.com/juxt/allium/tree/main/skills/alliumGive your AI agents something more useful than a prompt. Velocity through clarity.
This repo contains 5 individual skills — each has its own dedicated page.
Extract an Allium specification from an existing codebase. Use when the user has existing code and wants to distil behaviour into a spec, reverse engineer a specification from implementation, generate a spec from code, turn implementation into a behavioural specification, or document what a codebase does in Allium terms.
Run a structured discovery session to build an Allium specification through conversation. Use when the user wants to create a new spec from scratch, elicit or gather requirements, capture domain behaviour, specify a feature or system, define what a system should do, or is describing functionality and needs help shaping it into a specification.
Generate tests from Allium specifications. Use when the user wants to propagate tests, generate test files from a spec, write tests for a specification, create property-based tests, produce state machine tests, check test coverage against spec obligations, or understand what tests a specification requires.
Tend the Allium garden. Use when the user wants to write, edit, update, add to, improve, clarify, refine, restructure, fix or migrate Allium specs. Covers adding entities, rules, triggers, surfaces and contracts, fixing syntax or validation errors, renaming or refactoring within specs, migrating specs to a new language version, and translating requirements into well-formed specifications. Pushes back on vague requirements.
Weed the Allium garden. Find where Allium specifications and implementation code have diverged, and help resolve the divergences. Use when the user wants to check spec-code alignment, compare specs against implementation, audit for spec drift or violations, sync specs with code or code with specs, or verify whether the implementation matches what the spec says.
A Claude Code skill that maintains a per-project AIREADME/ — the project's AI-native source of truth (12-file model) for cross-project understanding and drift prevention. (Docs in Chinese.)
A reproducible operating model for running team-led OpenClaw agents with Work Units, evidence, and alert-only monitoring.
Host-agnostic agent skill for TickTick — Bun/TS CLI (`bin/ticktick`) + SKILL.md + Workflows/ for any AI agent ecosystem (PAI, Claude Code, custom MCP). Wraps ticktick-client (the unofficial v2 API library). Two-account support (--account live|test). Tasks, projects, tags, nested subtasks, time + geofence reminders, sections, bulk ops.
Agentic workflow template with Claude Code skills and GitHub Actions
🚀 Sync Claude's todos to Fizzy.do for real-time team visibility, turning tasks into persistent cards to boost collaboration and track progress effortlessly.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.