Skills & Agents
Structured commands that run where your team already works. No plugins, no extensions.
What It Is
A skill is a structured command. When you run one, Claude already knows the codebase, the blueprint, and what was agreed. No repeated instructions, no lost context, no starting from scratch. Agent-powered skills go further, spawning parallel research agents to explore the codebase before acting. Every skill runs exactly where your team already works, in Claude Code for developers, and in the Claude app for Product Owners and Designers.
The AI stays focused on what was agreed. Every decision still goes through you.
Product Owner
Commands to create, refine, and validate tickets using the contract template.
Create a new ticket using the contract template. Claude structures the goal, context, and requirements from the Product Owner's input.
Deep codebase research. Spawns 3 parallel research agents to map affected areas, find patterns, and detect gaps before writing.
Validate a ticket against quality gates before marking it ready. Checks for completeness, testable requirements, and clear acceptance criteria.
Designer
Commands to shape the interface using the ticket as the source of truth.
Fill the UI/UX section of a ticket with component references from the codebase. Maps existing patterns and components to the new requirements.
Validate design specs against existing components and patterns. Flags inconsistencies or missing references before handing off to the Developer.
Developer — Blueprint Lifecycle
Commands to generate, update, and validate the technical recipe.
Generate a blueprint from a ticket. Pulls the structured content and creates the technical recipe in .blackbox/blueprints/.
Update a blueprint after a send-back. Overwrites ticket-owned sections while preserving Developer-owned sections.
Deep codebase research. Spawns 3 parallel research agents to map affected areas, find patterns, and detect gaps. Drives a guided Q&A before writing.
Return a ticket to Product Owner or Designer when requirements are unclear or incomplete.
Developer — Development Flow
Commands to execute and track the actual implementation.
Review the blueprint summary and prepare to begin work.
Execute the implementation plan step by step with task tracking.
Self-review changed files against a quality checklist before committing.
Clean code, run linters, and create a Pull Request document in .blackbox/prs/.
Create a GitHub Pull Request from the Pull Request document.
Update an existing GitHub Pull Request from the Pull Request document.
Developer — Review & Status
Commands to monitor progress and maintain quality.
Review someone else's Pull Request to ensure blueprint alignment.
List blueprints and their overall progress in the current project.
Package the current session data into a compressed archive for sharing or later analysis.
Parse a session export to extract factual corrections, research gaps, and protocol violations.
Developer — Project Setup
Commands to configure the project for all roles.
Generate personalized CLAUDE.md files for PO and DESIGN roles. Spawns parallel agents to research the codebase, then writes role-specific configurations to .blackbox/roles/.
Developer — Skill Toolkit
Commands to maintain and improve skills themselves.
Validate skill files against Anthropic's guide. Checks frontmatter, naming, description triggers, required sections, and instruction quality.
Structure, Not Automation
Skills don't replace the developer. They keep Claude focused on what was agreed — the ticket, the blueprint, the plan. Every decision still goes through you.