Skill directory

Agent skills

Focused instruction packs that teach a coding agent one job well. Browse the catalog and use any of them inside a RiverX project.

18,175Skills

1,902Publishers

249Official

67 skills

Sort by

Actualizeneolabhq/context-engineering-kitReconcile the project's FPF state with recent repository changes01 Add Taskneolabhq/context-engineering-kitcreates draft task file in .specs/tasks/draft/ with original user intent01 Agent Evaluationneolabhq/context-engineering-kitEvaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.01 Analyseneolabhq/context-engineering-kitAuto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target01 Analyse Problemneolabhq/context-engineering-kitComprehensive A3 one-page problem analysis with root cause and action plan01 Analyze Issueneolabhq/context-engineering-kitAnalyze a GitHub issue and create a detailed technical specification01 Apply Anthropic Skill Best Practicesneolabhq/context-engineering-kitComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure01 Attach Review To PRneolabhq/context-engineering-kitAdd line-specific review comments to pull requests using GitHub CLI API01 Brainstormneolabhq/context-engineering-kitUse when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes01 Build MCPneolabhq/context-engineering-kitGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).01 Cause And Effectneolabhq/context-engineering-kitSystematic Fishbone analysis exploring problem causes across six categories01 Commitneolabhq/context-engineering-kitCreate well-formatted commits with conventional commit messages and emoji01 Context Engineeringneolabhq/context-engineering-kitUnderstand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.01 Create Agentneolabhq/context-engineering-kitComprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns01 Create Commandneolabhq/context-engineering-kitInteractive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration01 Create Hookneolabhq/context-engineering-kitCreate and configure git hooks with intelligent project analysis, suggestions, and automated testing01 Create Ideasneolabhq/context-engineering-kitGenerate ideas in one shot using creative sampling01 Create PRneolabhq/context-engineering-kitCreate pull requests using GitHub CLI with proper templates and formatting01 Create Ruleneolabhq/context-engineering-kitUse when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.01 Create Skillneolabhq/context-engineering-kitGuide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization01 Create Workflow Commandneolabhq/context-engineering-kitCreate a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts01 Critiqueneolabhq/context-engineering-kitComprehensive multi-perspective review using specialized judges with debate and consensus building01 Decayneolabhq/context-engineering-kitManage evidence freshness by identifying stale decisions and providing governance actions01 Design Testing Strategyneolabhq/context-engineering-kitUse before writing any type of tests. Distills 14 industry sources into deterministic decision gates, schemas, and worked test examples.01 Do And Judgeneolabhq/context-engineering-kitExecute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop01 Do Competitivelyneolabhq/context-engineering-kitExecute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis01 Do In Parallelneolabhq/context-engineering-kitRun independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.01 Do In Stepsneolabhq/context-engineering-kitExecute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the results of earlier ones.01 Fix Testsneolabhq/context-engineering-kitSystematically fix all failing tests after business logic changes or refactoring01 Git Notesneolabhq/context-engineering-kitUse when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.01 Git Worktreesneolabhq/context-engineering-kitUse when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories.01 Implement Taskneolabhq/context-engineering-kitImplement a task step by step with automated LLM-as-Judge verification at the end of each phase01 Judgeneolabhq/context-engineering-kitLaunch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation01 Judge With Debateneolabhq/context-engineering-kitEvaluate solutions through multi-round debate between independent judges until consensus01 Kaizenneolabhq/context-engineering-kitUse when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements.01 Launch Sub Agentneolabhq/context-engineering-kitLaunch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification01 Load Issuesneolabhq/context-engineering-kitLoad all open issues from GitHub and save them as markdown files01 Load PR Commentsneolabhq/context-engineering-kitUse to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.01 Memorizeneolabhq/context-engineering-kitCurates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering01 Multi Agent Patternsneolabhq/context-engineering-kitDesign multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.01 Plan Do Check Actneolabhq/context-engineering-kitIterative PDCA cycle for systematic experimentation and continuous improvement01 Plan Taskneolabhq/context-engineering-kitRefine a draft task specification into a fully planned, implementation-ready task with acceptance criteria, architecture, per-step sub-task files and verifiable phases01 Prompt Engineeringneolabhq/context-engineering-kitUse this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.01 Propose Hypothesesneolabhq/context-engineering-kitExecute complete FPF cycle from hypothesis generation to decision01 Queryneolabhq/context-engineering-kitSearch the FPF knowledge base and display hypothesis details with assurance information01 Reflectneolabhq/context-engineering-kitReflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification01 Resetneolabhq/context-engineering-kitReset the FPF reasoning cycle to start fresh01 Resolve Fixed PR Commentsneolabhq/context-engineering-kitVerify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.01

Skills, installed in one click

Put a skill to work

Open any project, search the Skills panel in the chat, and the agent picks it up from there.

Start building free