Skill Claude

Convert to Copilot

convert-to-copilot/

4 views 0 downloads

Port a Claude Code agent, with its command and skills, to one GitHub Copilot agent. Maps tools, models and sub-agent calls, validates the result and ships scripts for both directions.

Convert to Copilot: Brain Lab skill for Claude Code

Port a Claude Code agent, with its command and skills, to one GitHub Copilot agent that works the same way.

Why use it

Your team uses both Claude Code and GitHub Copilot, and every agent has to be written twice.
Copilot has no skills or commands: a straight copy loses the knowledge and the triggers the agent depends on.
Hand-ported agents drift, wrong tool aliases (fetch instead of web), dead file paths, task tracking that fails silently.

What it does

Merges the agent + its launch command into one .github/agents/{name}.agent.md, with the command's trigger phrases in the description.
Splits every skill into .copilot_utils/{name}/context/ (what to use) and trees/ (how to decide), and rewrites each skill reference to a file path.
Maps tools, models and frontmatter: WebFetch → web, TaskCreate → manage_todo_list, opus → Claude Opus 4.5, drops color / memory / isolation / skills / allowed-tools.
Converts sub-agent calls to handoffs (VS Code) or runSubagent() (GitHub Copilot).
Validates the result, every referenced path exists, aliases are correct, body under 30,000 characters, and prints a conversion report.
Ships scaffold scripts for both directions (claude-to-copilot, copilot-to-claude) and a full worked example.

Benefits

Write the agent once. Claude Code stays the source; Copilot gets a faithful port.
No lost knowledge. Skills become referenced context files, not a pasted wall of text.
Correct on the first run. The tool and model tables catch the aliases that break Copilot agents.
Reviewable. Each phase writes its output to .copilot-convert-results/, so you can see every decision.

Install

Download this skill and copy the convert-to-copilot folder to .claude/skills/convert-to-copilot/ in your project, or to ~/.claude/skills/convert-to-copilot/ to use it in every project. Claude Code finds it on its own; you can also call it with /convert-to-copilot.

Part of the Agent Engineering bundle. To get the whole set as a Claude Code plugin: /plugin marketplace add endorphin-ai/hasbrains-agent-kit, then /plugin install agent-engineering@hasbrains-agent-kit.

Source: endorphin-ai/hasbrains-agent-kit. License: MIT.

Files (17)

# Conversion Phases 5–7: Write, Validate, Report

See also: `conversion-phases.md` (phases 1–3) · `conversion-body.md` (phase 4)

---

## Phase 5: Write Output Files

Write all files in this order:

1. `.github/agents/{agent_name}.agent.md`
    - Frontmatter from Phase 3
    - PROGRESS TRACKING section (from Phase 4.3) at top of body
    - Converted body from Phase 4

2. All `.copilot_utils/{agent_name}/context/*.md` — knowledge files
3. All `.copilot_utils/{agent_name}/trees/*.md` — decision tree files
4. Any `.copilot_utils/{agent_name}/scripts/*` — script files
5. `.copilot_utils/{agent_name}/memory/` — copy memory files found in Phase 1

---

## Phase 6: Validate → `{output_folder}/6-validation.md`

Run the full checklist. Write PASS/FAIL for each item:

```markdown
# Validation Results

| Check                                              | Status | Notes         |
| -------------------------------------------------- | ------ | ------------- |
| {output_agent} exists                              | ✅/❌  |               |
| Frontmatter: description with triggers             | ✅/❌  |               |
| Frontmatter: tools array (no "fetch")              | ✅/❌  |               |
| Frontmatter: model (expanded)                      | ✅/❌  |               |
| No separate command file created                   | ✅/❌  |               |
| No .prompt.md or .instructions.md                  | ✅/❌  |               |
| Task tracking uses manage_todo_list with operation | ✅/❌  |               |
| All .copilot_utils/ refs resolve to real files     | ✅/❌  |               |
| Scripts executable + paths correct                 | ✅/❌  |               |
| Memory paths updated                               | ✅/❌  |               |
| MCP calls preserved                                | ✅/❌  |               |
| Agent body ≤ 30,000 chars                          | ✅/❌  | {count} chars |
```

If any check FAILS, fix before proceeding to Phase 7.

---

## Phase 7: Conversion Report (console output)

```markdown
## Conversion Report

### Agent Created

- ✅ .github/agents/{name}.agent.md — {N} phases, tools: [{tools}], model: {model}

### Command Absorbed

- 🔗 /{command-name} → merged into agent description + argument-hint

### Skill Context Created (.copilot_utils/{agent-name}/)

| File                         | Type          | Source skill        |
| ---------------------------- | ------------- | ------------------- |
| context/{skill}.md           | knowledge     | {skill} SKILL.md    |
| trees/{skill}.md             | decision tree | {skill} SKILL.md    |
| context/{skill}-templates.md | templates     | {skill} references/ |

### Memory

- 📝 .copilot_utils/{agent-name}/memory/ — {N files copied / none}

### Task Tracking

- 🔄 TaskCreate/TaskUpdate → manage_todo_list ({N} todos)

### Preserved As-Is

- ✅ MCP tool calls
- ✅ Bash commands and git workflow
- ✅ Phase structure and numbering
- ✅ Error handling
- ✅ ALWAYS_DO / NEVER_DO rules
- ✅ Final report format

### Not Created (by design)

- ❌ No .prompt.md (command absorbed into agent)
- ❌ No .instructions.md
- ❌ No .github/skills/
```