Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

When effective agent workflows live only in individual developers' chat histories, team velocity stays uneven and crucial context is lost whenever work moves between sessions, agents or teammates. This course teaches how to turn individual AI habits into version-controlled team skills and structured handoff protocols.

Authoring modular SKILL.md packages and custom slash commands (/plan, /migration, /review, /release-notes), using progressive disclosure so skills do not bloat baseline context, bundling helper scripts and templates, and executing clean context handoffs across PM, backend, frontend and QA roles are practised hands-on.

Who Should Attend?

  • Software engineers and tech leads
  • Platform, DevEx and developer productivity engineers
  • Cross-functional product engineering squads
  • Prerequisite: experience with Git workflows and active use of coding agents

Key Takeaways

  • Package recurring team workflows into version-controlled slash commands and SKILL.md modules
  • Design skill metadata for progressive disclosure so idle skills consume almost zero context
  • Bundle deterministic helper scripts, checklists and templates inside skill directories
  • Execute lossless context handoffs across sessions, subagents and engineering roles using structured state files
  • Govern and evolve the team's shared skill library through standard pull-request workflows

Curriculum

From Personal Prompts to Shared Team Skills
  • Distinguishing always-loaded AGENTS.md rules from on-demand SKILL.md packages and slash commands
  • Auditing the squad's workflow to pick high-leverage skill candidates (new endpoint, DB migration, triage, PR prep)
Architecting SKILL.md Packages and Custom Slash Commands
  • Writing clear trigger descriptions, parameterised instructions and expected output schemas
  • Bundling deterministic helper scripts, templates and reference docs inside skill folders
Context Handoff Engineering Across Sessions and Subagents
  • What to preserve and what to discard when compacting or handing off a session (HANDOFF.md)
  • Structured state passing across Researcher → Planner → Implementer → Reviewer agents
Cross-Functional Squad Handoffs (PM → Backend → Frontend → QA)
  • Handing off verified OpenAPI/type contracts from backend tasks directly to frontend and QA agents
  • Shared acceptance criteria and end-to-end integration verification
Governing and Evolving an Internal Skill Library
  • Sharing skills across repositories, versioning and tracking adoption
  • Treating skills as production code with PR reviews and regression checks

Other Courses in This Category

  • Headless Coding Agents in CI/CD Pipelines

    Running headless coding agents inside GitHub Actions and GitLab CI pipelines for automated CI failure repair, issue-to-draft-PR workflows, dependency upgrades and strict security/cost guardrails.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • AI Coding Assistants for Software Engineers

    Practical training on using IDE coding assistants such as GitHub Copilot, Cursor and Windsurf effectively through context pinning, multi-file editing, test-backed verification and secure coding habits.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • Disciplined Vibe Coding: From Idea to Working Software

    Training on combining natural-language-driven software creation (vibe coding) in Cursor, Claude Code, Lovable and Bolt with modular architecture, Git checkpoints and security guardrails so prototypes stay maintainable.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • Agentic Coding for Software Engineering Teams

    Hands-on training in autonomous multi-file software engineering with Claude Code, Cursor Agent and OpenAI Codex CLI, covering Plan-Act-Verify loops, MCP tool integration and parallel development with Git worktrees.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View
  • From Requirements to Code: AI-Assisted Delivery Workflows

    End-to-end product-to-engineering workflow training that turns business requirements, PRDs, user stories and Figma designs into technical specs, task slices, acceptance criteria and verified code.

    AI-Assisted Software Development Corporate
    Live Course
    4 modules
    View
  • Harness Engineering for Reliable Coding Agents

    Advanced training on building execution harnesses around coding agents—fast test/typecheck/lint feedback, custom tool wrappers, AST/LSP verifiers and internal eval benchmarks—so agents succeed reliably in enterprise repos.

    AI-Assisted Software Development Corporate
    Live Course
    5 modules
    View

Get in touch