Discover Development skills, compare source repositories and read the instructions for each workflow.
Evidence-before-claims discipline for implementation completion. Use before claiming any work is complete, fixed, or passing. Run verification commands and confirm output before making success claims.
Verification-first approach to code review feedback. Use when receiving review comments during the implement phase. Evaluate suggestions rigorously before implementing - no performative agreement.
Concurrent agent dispatch for independent problems. Use when facing multiple independent tasks that can be worked on simultaneously. Reduces total time by parallelizing work that has no shared state.
Rigorous TDD methodology enforcing RED-GREEN-REFACTOR discipline. Use when implementing features or fixing bugs during the implement phase. Tests must be written before production code - no exceptions.
Root cause investigation methodology for bugs and failures. Use when encountering test failures, unexpected behavior, or errors during research or implement phases. Find the cause before attempting fixes.
Code review methodology for evaluating implementation changes. Use when reviewing code changes for quality, design, correctness, and maintainability. Focuses on changes made during implementation using Conventi...
Collaborative design methodology for creative work. Use before research or planning when requirements are unclear, multiple approaches exist, or the idea needs exploration. Refines ideas through progressive que...
Transform user feedback into structured Linear issues with AI-enhanced parsing for labels, priority, acceptance criteria, and estimates
Guidance on when and how to apply design patterns. Use when: (1) asking which pattern to use, (2) refactoring code, (3) discussing code smells, (4) need to decouple components, (5) building extensible systems.
Enforce a precise, minimal design system inspired by Linear, Notion, and Stripe. Use this skill when building dashboards, admin interfaces, or any UI that needs Jony Ive-level precision - clean, modern, minimal...
Deploy agents and skills with full verification. Single command deployment with rollout monitoring, health checks, and automatic rollback.
Create a new AI agent from template using kubani-dev CLI. Use when adding a new agent to the cluster, starting a new monitoring or automation project.
Testing patterns, fixtures, and best practices for Kubani. Use this skill when writing or running tests.
Use and develop MCP servers for agent capabilities. Includes Temporal, Qdrant, Memory, Discord, and Registry MCP servers.
Standard code patterns and conventions used in Kubani. Reference this skill when writing new code or reviewing existing code.
Add a new node to the Kubernetes cluster. Use when connecting new hardware, expanding cluster capacity, or setting up worker nodes.
Rollback AI agent to a previous version. Use when reverting a deployment, undoing changes, or recovering from failed deploys.
Voyager-inspired continuous learning system with Critic Agent, Reflection Agent, and Discord-based approval workflow for skill proposals.
Build MCP (Model Context Protocol) servers for Claude Code integration. Use when creating tools, resources, or prompts that extend Claude's capabilities. Supports Python FastMCP and TypeScript implementations.
Run comprehensive agent evaluations using YAML-defined test suites with multiple evaluator types including automated, LLM-as-judge, and human review.
Kubani architecture principles, patterns, and design decisions. Use this skill when making architectural decisions or understanding the system design.
Bootstrap a new node for Kubernetes without joining it to the cluster. Use when preparing nodes in advance, testing setup, or staging hardware.
Increment agent version in pyproject.toml. Use when releasing new versions, updating semantic version, or preparing for deployment.
Complete guide for local agent development using kubani-dev CLI, unified configuration, MCP integration, and seamless iteration.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.