Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.
EnglishCreates PhD-grade expert agents when no suitable agent exists. Produces highly specialized agents with deep domain expertise.
EnglishMANDATORY workflow for creating new agents. Enforces -01-agent-formatting standards from inception, ensuring every new agent is properly designed, researched, and curated before deployment.
EnglishArchitect code review with DRY, YAGNI, abstraction, and test coverage principle…
EnglishOPTIONAL: Analyzes TaskMaster subtasks to determine if they are tightly coupled (share code/models) or loosely coupled (independent modules).
EnglishOrchestrates deployment to production after all validations pass. Activates via codeword [ACTIVATE:DEPLOYMENTORCHESTRATORV1] injected by hooks automatically after Phase 10 completes.
EnglishValidates end-to-end user workflows and system behavior. Activates via codeword [ACTIVATE:E2EVALIDATORV1] injected by hooks when entering Phase 10 E2E testing.
EnglishValidates integration points and ensures components work together correctly. Activates via codeword [ACTIVATE:INTEGRATIONVALIDATORV1] injected by hooks when entering Phase 9 integration testing.
EnglishIncludes Agent Curator, Agent Inventor, Agent Provisioner, and other workflows.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Agent Curator
Deep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona refinement, tooling optimization, and instruction quality improvement. One agent at a time, with due care.
Agent Inventor
Creates PhD-grade expert agents when no suitable agent exists. Produces highly specialized agents with deep domain expertise.
Agent Provisioner
MANDATORY workflow for creating new agents. Enforces -01-agent-formatting standards from inception, ensuring every new agent is properly designed, researched, and curated before deployment.
Code Review Gate
Architect code review with DRY, YAGNI, abstraction, and test coverage principle enforcement
Coupling Analysis
OPTIONAL: Analyzes TaskMaster subtasks to determine if they are tightly coupled (share code/models) or loosely coupled (independent modules). This analysis provides RECOM
Deployment Orchestrator
Orchestrates deployment to production after all validations pass. Activates via codeword [ACTIVATE:DEPLOYMENTORCHESTRATORV1] injected by hooks automatically after Phase 10 completes.
Deployment Rollback
Safe deployment rollback with health checks and database migration reversal
E2E Validator
Validates end-to-end user workflows and system behavior. Activates via codeword [ACTIVATE:E2EVALIDATORV1] injected by hooks when entering Phase 10 E2E testing. Activation trigger: [ACTIVATE:E2EVALIDATORV1]
Integration Validator
Validates integration points and ensures components work together correctly. Activates via codeword [ACTIVATE:INTEGRATIONVALIDATORV1] injected by hooks when entering Phase 9 integration testing. Activation trigger: [ACTIVATE:INTEGRATIONVALIDATORV1]
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Agent Curator skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.