skills/copilot-coding-agent/SKILL.md
GitHub Copilot Coding Agent automation. Apply the ai-copilot label to an issue → GitHub Actions auto-assigns Copilot via GraphQL → Copilot creates a Draft PR. One-click issue-to-PR pipeline.
npx skillsauth add jyjeanne/ai-setup-forge copilot-coding-agentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
If you add the
ai-copilotlabel to an issue, GitHub Actions automatically assigns it to Copilot, and Copilot creates a branch → writes code → opens a Draft PR.
repo scope# One-click setup (register token + deploy workflow + create label)
bash scripts/copilot-setup-workflow.sh
This script does:
COPILOT_ASSIGN_TOKEN as a repo secret.github/workflows/assign-to-copilot.ymlai-copilot label# Create issue + ai-copilot label → auto-assign Copilot
gh issue create \
--label ai-copilot \
--title "Add user authentication" \
--body "Implement JWT-based auth with refresh tokens. Include login, logout, refresh endpoints."
# Add label to issue #42 → trigger Actions
gh issue edit 42 --add-label ai-copilot
export COPILOT_ASSIGN_TOKEN=<your-pat>
bash scripts/copilot-assign-issue.sh 42
Issue created/labeled
↓
GitHub Actions triggered (assign-to-copilot.yml)
↓
Look up Copilot bot ID via GraphQL
↓
replaceActorsForAssignable → set Copilot as assignee
↓
Copilot Coding Agent starts processing the issue
↓
Create branch → write code → open Draft PR
↓
Auto-assign you as PR reviewer
Required GraphQL header:
GraphQL-Features: issues_copilot_assignment_api_support,coding_agent_model_selection
| Workflow | Trigger | Purpose |
|---------|--------|------|
| assign-to-copilot.yml | Issue labeled ai-copilot | Auto-assign to Copilot |
| copilot-pr-ci.yml | PR open/update | Run CI (build + tests) |
Copilot is treated like an external contributor.
copilot-pr-ci.yml CI runs normally# Check CI after manual approval
gh pr list --search 'head:copilot/'
gh pr view <pr-number>
Review the issue spec in planno before assigning to Copilot (independent skill, not required):
Review and approve this issue spec in planno
After approval, add the ai-copilot label → trigger Actions.
PM writes an issue → add ai-copilot label
→ Actions auto-assigns → Copilot creates Draft PR
→ Team only performs PR review
Follow-up issues created by Vibe Kanban:
refactors/docs cleanup/add tests
→ ai-copilot label → Copilot handles
→ Team focuses on main feature development
Jira issue → Zapier/webhook → auto-create GitHub Issue
→ ai-copilot label → Copilot PR
→ Fully automated pipeline
# Bulk-add label to backlog issues
gh issue list --label "tech-debt" --json number \
| jq '.[].number' \
| xargs -I{} gh issue edit {} --add-label ai-copilot
# List PRs created by Copilot
gh pr list --search 'head:copilot/'
# Specific issue status
gh issue view 42
# PR CI status
gh pr checks <pr-number>
=== Setup ===
bash scripts/copilot-setup-workflow.sh one-time setup
=== Issue assignment ===
gh issue create --label ai-copilot ... new issue + auto-assign
gh issue edit <num> --add-label ai-copilot existing issue
bash scripts/copilot-assign-issue.sh <num> manual assign
=== Verify results ===
gh pr list --search 'head:copilot/' Copilot PR list
gh pr view <num> PR details
gh pr checks <num> CI status
=== Constraints ===
Copilot Pro+/Business/Enterprise required
First PR requires manual approval (treated as an external contributor)
PAT: repo scope required
development
Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic component placements, draw breadboard diagrams, mockup 6502 builds, generate retro computer schematics, or design vintage electronics projects. Supports 555 timers, W65C02S microprocessors, 28C256 EEPROMs, W65C22 VIA chips, 7400-series logic gates, LEDs, resistors, capacitors, switches, buttons, crystals, and wires.
development
Apply lean thinking to UX: hypothesis-driven design, collaborative sketching, and rapid experiments instead of heavy deliverables. Use when the user mentions "Lean UX", "design hypothesis", "UX experiment", "collaborative design", or "outcome over output". Covers hypothesis statements, MVPs for UX, and cross-functional collaboration. For Build-Measure-Learn, see lean-startup. For usability audits, see ux-heuristics.
development
Design MVPs, validated learning experiments, and pivot-or-persevere decisions using Build-Measure-Learn. Use when the user mentions "MVP scope", "validated learning", "pivot or persevere", "vanity metrics", or "test assumptions". Covers innovation accounting and actionable metrics. For 5-day prototype testing, see design-sprint. For customer motivation analysis, see jobs-to-be-done.
tools
Instrument, trace, evaluate, and monitor LLM applications and AI agents with LangSmith. Use when setting up observability for LLM pipelines, running offline or online evaluations, managing prompts in the Prompt Hub, creating datasets for regression testing, or deploying agent servers. Triggers on: langsmith, langchain tracing, llm tracing, llm observability, llm evaluation, trace llm calls, @traceable, wrap_openai, langsmith evaluate, langsmith dataset, langsmith feedback, langsmith prompt hub, langsmith project, llm monitoring, llm debugging, llm quality, openevals, langsmith cli, langsmith experiment, annotate llm, llm judge.