Copilot Artifacts
GitHub Copilot extensibility artifacts provide AI-assisted workflows for dataset analysis, training job management, and coding standards enforcement. Committed artifacts activate automatically in VS Code. The cloud-agent setup workflow provisions the RPI skill suite at runtime.
📋 Artifact Inventory
| Type | Name | Description | Path |
|---|---|---|---|
| Agent | Dataviewer Developer | Interactive dataset analysis and tool development | .github/agents/dataviewer-developer.agent.md |
| Agent | OSMO Training Manager | LeRobot training lifecycle on OSMO with Azure ML | .github/agents/osmo-training-manager.agent.md |
| Instruction | Commit Messages | Conventional Commits format for all commit messages | .github/instructions/commit-message.instructions.md |
| Instruction | Dataviewer | Coding standards for dataviewer development | .github/instructions/dataviewer.instructions.md |
| Instruction | Docs Style and Conventions | Writing standards for all markdown files | .github/instructions/docs-style-and-conventions.instructions.md |
| Instruction | RPI Tracking | Shared RPI working-artifact conventions | .github/instructions/hve-core/copilot-tracking.instructions.md |
| Instruction | Shell Scripts | Implementation standards for bash scripts | .github/instructions/shell-scripts.instructions.md |
| Prompt | /chatlog | Create and maintain conversation logs | .github/prompts/chatlog.prompt.md |
| Prompt | /check-training-status | Monitor OSMO training job progress | .github/prompts/check-training-status.prompt.md |
| Prompt | /start-dataviewer | Launch Dataset Analysis Tool | .github/prompts/start-dataviewer.prompt.md |
| Prompt | /submit-lerobot-training | Submit LeRobot training job to OSMO | .github/prompts/submit-lerobot-training.prompt.md |
| Skill | dataviewer | Dataset browsing, annotation, and export | .github/skills/dataviewer/SKILL.md |
| Skill | environment-deployment | Generate and consume environment deployment bundles | .github/skills/environment-deployment/SKILL.md |
| Skill | fleet-deployment | Deploy trained policies through fleet GitOps | .github/skills/fleet-deployment/SKILL.md |
| Skill | fleet-intelligence | Monitor fleet telemetry and drift | .github/skills/fleet-intelligence/SKILL.md |
| Skill | infrastructure | Deploy and manage Azure infrastructure | .github/skills/infrastructure/SKILL.md |
| Skill | osmo-lerobot-training | Training submission, monitoring, and analysis | .github/skills/osmo-lerobot-training/SKILL.md |
| Skill | synthetic-data | Generate synthetic robotics training data | .github/skills/synthetic-data/SKILL.md |
| Skill | rpi-* | Cloud-agent research, plan, implement, review | .github/skills/rpi-*/ (runtime-provisioned, gitignored) |
🔗 Quick Reference
| Want to... | Use this artifact |
|---|---|
| Launch the Dataset Analysis Tool | /start-dataviewer prompt → Dataviewer Developer |
| Browse and annotate training episodes | Dataviewer Developer agent |
| Submit a LeRobot training job | /submit-lerobot-training prompt → OSMO Training Manager |
| Check training job status | /check-training-status prompt → OSMO Training Manager |
| Save a conversation log | /chatlog prompt |
| Run the full RPI lifecycle | rpi-quick skill |
| Enforce commit message standards | commit-message instruction (auto-applied) |
| Enforce coding standards in dataviewer | dataviewer instruction (auto-applied) |
| Enforce markdown writing standards | docs-style-and-conventions instruction (auto-applied) |
| Enforce shell script standards | shell-scripts instruction (auto-applied) |
🤖 Agents
Dataviewer Developer
Interactive agent for launching, browsing, annotating, and improving the Dataset Analysis Tool.
| Property | Value |
|---|---|
| Handoffs | Start Dataviewer, Browse Dataset, Annotate Episodes |
| Tools | All (no restrictions) |
| Skill | dataviewer |
| Prompts | /start-dataviewer |
Four-phase workflow: Launch/Configure → Interactive Browsing (Playwright) → Episode Annotation (API+UI) → Feature Development (React+FastAPI).
OSMO Training Manager
Multi-turn agent for managing LeRobot imitation learning training lifecycle on OSMO with Azure ML integration.
| Property | Value |
|---|---|
| Handoffs | Submit Training Job, Check Training Status, Run Inference Evaluation |
| Tools | 11 explicit (run_in_terminal, memory, runSubagent, ...) |
| Skill | osmo-lerobot-training |
| Prompts | /submit-lerobot-training, /check-training-status |
Five-phase workflow: Submit → Monitor → Analyze → Summarize → Inference Evaluation. Handles VM eviction recovery, CUDA errors, and KeyError failures.
📝 Instructions
Instructions activate automatically when files matching their applyTo
pattern appear in the chat context.
| Name | Applies To | Purpose |
|---|---|---|
| Commit Messages | ** | Conventional Commits format, scopes, line-length limits |
| Dataviewer | data-management/viewer/** | SOLID principles, test-first, validation commands |
| Docs Style and Conventions | **/*.md | Document hierarchy, tables, voice/tone, frontmatter |
| Shell Scripts | **/*.sh | Script template, library functions, deployment patterns |
⚡ Prompts
Prompts are slash commands invoked via / in the chat input. Each prompt
targets a specific agent.
| Command | Agent Target | Required Inputs |
|---|---|---|
/chatlog | Generic | None |
/check-training-status | OSMO Training Manager | workflowId (optional) |
/start-dataviewer | Dataviewer Developer | datasetPath |
/submit-lerobot-training | OSMO Training Manager | dataset (required) |
🛠️ Skills
Skills provide multi-file capabilities with progressive 3-level loading: discovery (frontmatter only) → instructions (SKILL.md body) → resources (bundled reference files).
dataviewer
| Property | Value |
|---|---|
| Directory | .github/skills/dataviewer/ |
| Resources | references/PLAYWRIGHT.md (selectors, interaction recipes, API endpoints) |
| Used by | Dataviewer Developer agent |
osmo-lerobot-training
| Property | Value |
|---|---|
| Directory | .github/skills/osmo-lerobot-training/ |
| Resources | references/DEFAULTS.md (env, datasets, GPU profiles), references/REFERENCE.md (CLI, inference, AzureML navigation) |
| Used by | OSMO Training Manager agent |
rpi-* skill suite
The cloud-agent setup workflow uses gh skill install to download eight explicit RPI skill paths from a pinned microsoft/hve-core commit into gitignored .github/skills/rpi-*/ directories. It also downloads the shared copilot-tracking.instructions.md from the same commit into .github/instructions/hve-core/.
Each skill is an immediate child of .github/skills/, as required for discovery. Local clones do not contain these runtime artifacts unless the setup workflow has provisioned them. Each skill retains its upstream references and templates, and the GitHub CLI injects the source commit and tree metadata into its SKILL.md front matter.
| Skill | Purpose |
|---|---|
rpi-quick | Coordinate the complete RPI lifecycle |
rpi-research | Gather evidence and produce planning-ready findings |
rpi-plan | Build and critique an implementation plan |
rpi-implement | Execute approved plan phases and validate changes |
rpi-review | Review implementation evidence and route follow-ups |
rpi-challenger | Challenge scope and assumptions |
rpi-plan-critique | Assess plans independently |
rpi-walkthrough | Walk through RPI artifacts and decisions |
🔄 Workflow Chains
Agents compose prompts and skills into end-to-end workflows:
OSMO Training Manager (agent)
├── /submit-lerobot-training (prompt)
├── /check-training-status (prompt)
└── osmo-lerobot-training (skill)
├── references/DEFAULTS.md
└── references/REFERENCE.md
Dataviewer Developer (agent)
├── /start-dataviewer (prompt)
└── dataviewer (skill)
└── references/PLAYWRIGHT.md
Standalone:
├── /chatlog (prompt, generic)
└── rpi-quick (skill)
├── rpi-research
├── rpi-plan
├── rpi-implement
└── rpi-review
➕ Adding New Artifacts
VS Code provides generator commands for scaffolding new artifacts:
/create-agent— Create a new custom agent/create-instruction— Create a new instruction file/create-prompt— Create a new prompt file/create-skill— Create a new agent skill
Place new artifacts in the corresponding .github/ subdirectory and update
this inventory page.
Related Documentation
For broader project context, see these companion guides:
- Contributing Guide — Development workflow and coding standards
- Architecture — System architecture and agent skills design
- Prerequisites — Required tools and VS Code settings
Crafted with precision by Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.