Skip to main content

Prompts Overview

Copilot Collections includes 13 public prompts — slash commands that trigger specific workflow actions across the full product lifecycle. Prompts are stored in .github/prompts/ and become available as /command shortcuts in VS Code chat.

How Prompts Work

Each prompt file defines:

  • Agent binding — Which agent executes the command, via the agent field. Model selection is inferred from that agent's own model array; public prompts do not declare a separate prompt-level model field.
  • Description — Shown in VS Code's command palette.
  • Instructions — Detailed workflow steps, required skills, and output format.

When you type /tsh-explore-materials, /tsh-implement, /tsh-review, etc. in the VS Code chat, the corresponding prompt file is loaded and executed by the bound agent.

Public Prompts

These are the user-facing commands available in VS Code chat.

📋 Product Ideation Commands

CommandAgentDescription
/tsh-explore-materialsBusiness AnalystExplore workshop materials before backlog extraction
/tsh-analyze-materialsBusiness AnalystProcess workshop materials into Jira-ready epics and stories

🛠 Development Commands

CommandAgentDescription
/tsh-implementEngineering ManagerOrchestrate the full cycle: research/context gathering if needed → plan → implementation

✅ Quality Commands

CommandAgentDescription
/tsh-reviewCode ReviewerReview implementation against plan and standards
/tsh-review-uiUI ReviewerSingle-pass Figma vs implementation comparison
/tsh-review-codebaseArchitectComprehensive code quality analysis

⚙️ Copilot Customization Commands

CommandAgentDescription
/tsh-create-custom-agentCopilot OrchestratorCreate a new custom agent
/tsh-create-custom-skillCopilot OrchestratorCreate a new custom skill
/tsh-create-custom-promptCopilot OrchestratorCreate a new custom prompt
/tsh-create-custom-instructionsCopilot OrchestratorCreate custom instruction files

🏗 Infrastructure & Cost Analysis Commands

CommandAgentDescription
/tsh-audit-infrastructureDevOps EngineerAudit infrastructure for security gaps, cost waste, and best practices
/tsh-analyze-aws-costsDevOps EngineerAWS cost optimization and tagging compliance audit
/tsh-analyze-gcp-costsDevOps EngineerGCP cost optimization and labeling compliance audit

Delegation via /tsh-implement

When you run /tsh-implement, the Engineering Manager automatically handles the full development cycle. Its four primary inputs are a task description, Jira ID, standalone *.research.md, or *.plan.md. Missing research or plan companions trigger preparation, never no-plan implementation. Before the first file-changing delegation in either flow, the manager requires Human approval of the exact current plan revision; automated Reviewer approval is readiness evidence only, not permission to implement. You don’t need to invoke individual agents — the orchestration is handled for you.

PhaseDelegated To
Research (context gathering)Context Engineer (via internal research prompt)
Planning (architecture)Architect (via internal plan prompt)
Plan validationArchitect Reviewer stress-test (via internal review-plan prompt)
Backend / general code (actionable, low-risk seam)Plan Implementor — DEFAULT
Backend / general code (complex, non-UI)Software Engineer — EXCEPTION
Frontend with FigmaUI Engineer (via internal UI prompt)
E2E testsE2E Engineer
LLM application promptsPrompt Engineer (via internal engineer-prompt)
Kubernetes, Terraform, CI/CD, observabilityDevOps Engineer
Repository documentationTechnical Writer
UI verificationUI Reviewer

Input Format

Most prompts accept either:

  • A Jira ticket ID: /tsh-implement PROJ-123
  • A task description: /tsh-implement Add pagination to the user list API

/tsh-implement additionally accepts a standalone *.research.md file or a *.plan.md implementation plan as a primary input. A missing research or plan companion routes to preparation; it never authorizes no-plan implementation.

The agent adapts its behavior based on the input type — pulling context from Jira/Confluence for ticket IDs, or working from the description and codebase for free-form text.