hivellm
146 verified skills1,607 total stars
analysis
Create structured analyses with numbered findings, execution plans, and task materialization
research12
rulebook-skill-list
List all available Rulebook skills, optionally filtered by category or enabled status. Use to discover what skills are available for the project.
development11
review
Deep code review of recent changes or specified files
development11
Django
Language: Python
development11
Go
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
VS Code
IDE: VS Code with Copilot, Cody, Continue, or other AI extensions
tools11
rulebook-skill-show
Show detailed information about a specific skill including metadata, content preview, and enabled status. Use to inspect a skill before enabling it.
development11
rulebook-task-archive
Archive a completed Rulebook task to the archive directory with date prefix. Use after a task is fully implemented and validated.
testing11
rulebook-task-list
List all Rulebook tasks with optional status filtering and archive inclusion. Use to check project tasks, progress, or find tasks by status.
testing11
rulebook-task-management
Spec-driven task management for features and breaking changes using OpenSpec format. Use when creating new features, planning breaking changes, organizing development work, or managing project tasks with proposals and specifications.
development11
rulebook-task-update
Update a Rulebook task status. Use to mark tasks as in-progress, completed, or blocked.
tools11
rulebook-task-validate
Validate a Rulebook task format and structure against OpenSpec requirements. Use before archiving or to verify task quality.
development11
Documentation Rules
All documentation in English. Root README concise, detailed docs in `/docs`.
testing11
Opencode
OpenCode (open-source terminal coding agent by SST). Reads AGENTS.md natively. Rulebook generates opencode.json plus .opencode/commands, .opencode/agents, .opencode/skills.
development11
Elasticsearch
Use Elasticsearch for full-text search, log aggregation, and real-time analytics with distributed architecture.
data-ai11
Factory
Tool: Code generation and automation
tools11
JavaScript
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
jQuery
Language: JavaScript
development11
MongoDB
Use MongoDB for document-based NoSQL storage with flexible schemas, horizontal scaling, and rich querying.
development11
NestJS
Align all NestJS services, modules, and controllers with these conventions.
tools11
PostgreSQL
Use PostgreSQL for relational data storage with ACID compliance, transactions, and advanced features.
testing11
Python
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
rulebook-git-workflow
Git workflow standards including branching strategy, commit conventions, and PR guidelines. Use when creating branches, writing commit messages, preparing pull requests, or following git best practices.
documentation11
rulebook-mcp
MCP server overview and integration guide. Use this for setup, configuration, and discovering available MCP tools for task and skill management.
tools11
Rulebook MCP
Use MCP Rulebook server to manage tasks programmatically instead of executing terminal commands.
tools11
rulebook-skill-enable
Enable a skill in the project configuration. Checks for conflicts with existing skills. Use to add new capabilities to the project.
testing11
Vectorizer
Use MCP Vectorizer as primary data source for project information instead of file reading.
tools11
Codex
Tool: OpenAI code generation API
tools11
Rulebook Terse
Output-verbosity compression. Cuts response tokens ~40-70% without losing technical accuracy. Four intensity levels (off/brief/terse/ultra) aligned with Rulebook's agent-tier system. Use when user says 'terse mode', 'be terse', 'less tokens please', or invokes /rulebook-terse. Auto-activates via SessionStart hook with tier-aware default.
data-ai11
Rulebook Task Management
Spec-driven task management for features and breaking changes with OpenSpec-compatible format
development11
build-fix
Diagnose and fix build failures or CI issues
development11
rulebook-task-show
Show complete details of a Rulebook task including proposal, checklist, design, and specs. Use to understand task requirements before implementation.
testing11
Vue
Vue 3 projects should follow these guardrails.
data-ai11
Rails
Language: Ruby
data-ai11
docs
Generate or update project documentation based on recent changes
documentation11
security-audit
Run a security audit on the project (dependencies, secrets, OWASP)
testing11
Flutter
Language: Dart
tools11
Haskell
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Tabnine
Tool: Multi-IDE AI completion with team learning
tools11
Windsurf
IDE: AI-powered editor with Cascade AI and Flow State
data-ai11
Objective-C
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Java
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Lisp
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Memory
The rulebook memory system provides persistent context across AI sessions using hybrid search (BM25 keyword + HNSW vector) with zero native dependenci
testing11
Synap
Use MCP Synap for persistent task and data storage across context windows.
tools11
Codebuddy
Tool: Intelligent pair programming assistant
tools11
Continue
Tool: Open-source Copilot alternative (VS Code extension + CLI)
tools11
Copilot
Tool: GitHub's AI pair programmer (inline + chat)
tools11
Cursor
IDE: AI-first code editor with Agent mode and Composer
development11
Zed
Tool: High-performance collaborative editor (Rust-powered)
tools11
Dart
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Quality Enforcement
These rules are NON-NEGOTIABLE and MUST be followed without exception.
development11
rulebook-quality-gates
Automated quality checks and enforcement for code commits. Use when validating code quality, running pre-commit checks, ensuring test coverage, or enforcing coding standards before commits and pushes.
development11
rulebook-skill-disable
Disable a skill in the project configuration. Removes its rules from the next AGENTS.md generation. Use to remove unwanted capabilities.
data-ai11
rulebook-skill-validate
Validate the current skills configuration for conflicts, missing dependencies, and errors. Use to ensure skills are properly configured.
testing11
rulebook-task-delete
Permanently delete a Rulebook task. Cannot be undone. Prefer archiving completed tasks instead.
tools11
rulebook-task-create
Create a new Rulebook task with standardized directory structure. Use when starting a new feature, breaking change, or architectural work that needs spec-driven planning.
tools11
Rulebook Terse Review
Ultra-compressed code review comments. One line per finding: location, problem, fix. Use when user says 'review this PR', 'code review', 'review the diff', or invokes /rulebook-terse-review. Independent of the base rulebook-terse mode.
development11
architect
Architecture review, design decisions, and ADR writing
testing11
migrate
Plan and execute migrations (database, API, framework)
development11
Angular
Angular projects must meet these standards before delivery.
tools11
Nuxt
Nuxt 3 applications must keep these standards to ensure SSR quality.
testing11
Next.js
Language: TypeScript, JavaScript
development11
React Native
Language: JavaScript, TypeScript
development11
Elixir
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Kotlin
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Ruby
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
PHP
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Memcached
Use Memcached for simple, high-performance distributed caching with minimal overhead.
tools11
DynamoDB
Use DynamoDB for serverless NoSQL database with automatic scaling, high performance, and pay-per-use pricing.
testing11
Google Cloud Storage
Use Google Cloud Storage for object storage, file uploads, static assets, and backup storage in GCP.
development11
GitHub MCP
Monitor CI/CD workflows after every `git push` using GitHub MCP.
tools11
MariaDB
Use MariaDB for MySQL-compatible relational database with enhanced features, performance improvements, and open-source licensing.
data-ai11
Kafka
Use Kafka for high-throughput event streaming, real-time data pipelines, and distributed messaging with fault tolerance.
devops11
MySQL
Use MySQL for relational data storage with high performance, replication, and wide ecosystem support.
data-ai11
Oracle
Use Oracle Database for enterprise relational data storage with advanced features, high availability, and comprehensive tooling.
tools11
RabbitMQ
Use RabbitMQ for reliable message queuing, pub/sub messaging, and task distribution with multiple exchange types.
tools11
Supabase
Use MCP Supabase for database operations, authentication, and storage.
tools11
deploy
Prepare deployment artifacts and verify CI/CD readiness
testing11
debug
Systematic debugging workflow for bugs and test failures
development11
React
React applications must comply with these quality bars.
development11
Karpathy Guidelines
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
development11
Electron
Language: TypeScript, JavaScript
development11
Auggie
Tool: TDD mode and intelligent refactoring
tools11
Azure Blob Storage
Use Azure Blob Storage for object storage, file uploads, static assets, and backup storage in Azure cloud.
devops11
handoff
Save session state to .rulebook/handoff/_pending.md for cross-session continuity
tools11
InfluxDB
Use InfluxDB for time-series data, metrics, IoT data, and real-time analytics with high write throughput.
documentation11
Replit
Tool: Cloud IDE with Ghostwriter AI
tools11
research
Explore codebase and gather context about a topic or area
development11
Symfony
Language: PHP
tools11
TypeScript
TypeScript language rules with strict mode, testing, linting, and CI/CD best practices
development11
Cursor CLI
Tool: Cursor IDE automation and scripting
tools11
Agent Automation
Mandatory workflow that AI agents MUST execute after EVERY implementation.
tools11
Aider
Tool: AI pair programming in terminal (`pip install aider-chat`)
tools11
Amazon Q
Tool: AWS-focused AI assistant with security scanning
tools11
C
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Claude
Tool: Anthropic Claude API with 200K context window
tools11
Claude Code
Tool: Anthropic Claude Code CLI (`npm install -g @anthropic-ai/claude-code`)
tools11
Cline
Tool: VS Code extension with autonomous mode
tools11
Codeium
Tool: Free AI coding assistant
tools11
Context7
Use MCP Context7 to access up-to-date library documentation before adding dependencies.
tools11
C++
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
DAG Workflow
Maintain a clean dependency graph (DAG) to prevent circular dependencies and ensure maintainable architecture.
testing11
Figma
Use MCP Figma for design system integration, asset export, and design-to-code workflows.
tools11
Flask
Language: Python
development11
Gemini CLI
Tool: Google Gemini API with 2M token context
tools11
Grafana
Use MCP Grafana for metrics visualization, alerting, and observability dashboards.
tools11
Kilocode
Tool: Lightweight coding companion
tools11
perf
Performance analysis, profiling, and optimization
research11
Notion
Use MCP Notion for documentation, task tracking, and knowledge management.
tools11
R
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Ralph Autonomous Loop
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)
data-ai11
Redis
Use Redis for high-performance caching, session storage, pub/sub messaging, and real-time features.
data-ai11
refactor
Identify code smells and execute safe refactorings
development11
Rulebook Terse Commit
Terse Conventional Commits generator. Subject ≤50 chars (hard cap 72), body only when 'why' isn't obvious, no filler. Use when user says 'write a commit', 'generate commit', 'commit message', or invokes /rulebook-terse-commit. Independent of the base rulebook-terse mode.
documentation11
rulebook-typescript
TypeScript development with strict mode, Vitest testing, ESLint linting, and CI/CD best practices. Use when working on TypeScript projects, writing tests, configuring linting, or setting up build pipelines.
development11
S3
Use AWS S3 for object storage, file uploads, static assets, and backup storage with high availability.
devops11
Scala
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Serena
Use MCP Serena for AI-powered development assistance, code analysis, and intelligent automation.
tools11
Solidity
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Spring
Every Spring service must satisfy these quality gates before merge.
testing11
SQL
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
SQLite
Use SQLite for embedded databases, local storage, development, and small-scale applications with zero configuration.
development11
SQL Server
Use SQL Server for enterprise relational data storage with advanced features, high availability, and Windows integration.
data-ai11
Swift
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Zend
Language: PHP
tools11
Zig
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
rulebook-skill-search
Search for skills by name, description, or tags. Use to find skills matching specific requirements or technologies.
testing11
MinIO
Use MinIO for S3-compatible object storage, self-hosted file storage, and development/testing with S3 APIs.
development11
Lua
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Cassandra
Use Cassandra for distributed NoSQL database with high availability, linear scalability, and eventual consistency.
data-ai11
Rust
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Laravel
Laravel services must respect these conventions and quality checks.
testing11
accessibility
Accessibility audit for WCAG compliance and usability
testing11
Ada
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
C#
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Neo4j
Use Neo4j for graph data modeling, relationship traversal, and complex connected data queries.
data-ai11
SAS
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
JetBrains AI
IDEs: IntelliJ, PyCharm, WebStorm, GoLand, RustRover, Rider, CLion, PhpStorm
tools11
Julia
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Erlang
Execute these commands after EVERY implementation (see AGENT_AUTOMATION module for full workflow).
tools11
Atlassian
Use MCP Atlassian for Jira issues, Confluence documentation, and Bitbucket repositories.
tools11
db-design
Database schema design, migrations, and query optimization
data-ai11
Playwright
Use MCP Playwright for automated browser testing and web automation.
tools11
spec
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
research11
api-design
Design or review API endpoints (REST/GraphQL)
development11