GitHub Copilot CLI Operator
name: copilot-cli-operator
by cecwxf · published 2026-03-22
$ claw add gh:cecwxf/cecwxf-copilot-cli-skill---
name: copilot-cli-operator
description: Run GitHub Copilot CLI from OpenClaw for coding tasks in a target project directory. Use when the user asks OpenClaw to use Copilot for implementation, debugging, refactoring, review, or scripted coding workflows.
---
# GitHub Copilot CLI Operator
Use this skill to reliably call Copilot CLI from OpenClaw.
Core rules
1. Verify Copilot CLI exists (`copilot --version`) before first task.
2. Always run Copilot through OpenClaw `exec` with `pty:true`.
3. Always set explicit `workdir` to the target repository.
4. For long tasks, use `background:true` and track via `process`.
5. Report clear milestones: started, waiting-input, finished/failed.
Execution patterns
One-shot coding task
Use:
Scoped tool approval
Use `--allow-tool` and `--deny-tool` to control what Copilot can do:
To block dangerous operations:
Interactive session
Use:
Long-running background task
1. Start with `exec(background:true, pty:true, workdir, command:"copilot -p '...' --allow-all-tools")`
2. Record returned `sessionId`.
3. Poll with `process action:poll`.
4. Read output with `process action:log`.
5. If Copilot asks for input, use `process action:submit`.
Resume a previous session
Use:
Recommended prompts
Guardrails
References
More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...