Agent skill

github-operations

GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.

Stars 143
Forks 15

Install this agent skill to your Project

npx add-skill https://github.com/yonatangross/orchestkit/tree/main/src/skills/github-operations

Metadata

Additional technical details for this skill

category
workflow-automation

SKILL.md

GitHub Operations

Comprehensive GitHub CLI (gh) operations for project management, from basic issue creation to advanced Projects v2 integration and milestone tracking via REST API.

Overview

  • Creating and managing GitHub issues and PRs
  • Working with GitHub Projects v2 custom fields
  • Managing milestones (sprints, releases) via REST API
  • Automating bulk operations with gh
  • Running GraphQL queries for complex operations

CRITICAL: Task Management is MANDATORY (CC 2.1.16)

BEFORE doing ANYTHING else, create tasks to track progress:

python
# 1. Create main task IMMEDIATELY
TaskCreate(
  subject="GitHub Operations: {target}",
  description="Managing GitHub issues, PRs, milestones, or Projects",
  activeForm="Managing GitHub resources"
)

# 2. Create subtasks matching the operation scope
TaskCreate(subject="Issue management", activeForm="Creating/updating issues")
TaskCreate(subject="PR management", activeForm="Managing pull requests")
TaskCreate(subject="Milestone tracking", activeForm="Updating milestones")

# 3. Set dependencies if operations are sequential
TaskUpdate(taskId="3", addBlockedBy=["2"])
TaskUpdate(taskId="4", addBlockedBy=["3"])

# 4. Before starting each task, verify it's unblocked
task = TaskGet(taskId="2")  # Verify blockedBy is empty

# 5. Update status as you progress
TaskUpdate(taskId="2", status="in_progress")  # When starting
TaskUpdate(taskId="2", status="completed")    # When done

Quick Reference

Issue Operations

bash
# Create issue with labels and milestone
gh issue create --title "Bug: API returns 500" --body "..." --label "bug" --milestone "Sprint 5"

# List and filter issues
gh issue list --state open --label "backend" --assignee @me

# Edit issue metadata
gh issue edit 123 --add-label "high" --milestone "v2.0"

PR Operations

bash
# Create PR with reviewers
gh pr create --title "feat: Add search" --body "..." --base dev --reviewer @teammate

# Watch CI status and auto-merge
gh pr checks 456 --watch
gh pr merge 456 --auto --squash --delete-branch

# Resume a session linked to a PR (CC 2.1.27)
claude --from-pr 456           # Resume session with PR context (diff, comments, review status)
claude --from-pr https://github.com/org/repo/pull/456

Tip (CC 2.1.27): Sessions created via gh pr create are automatically linked to the PR. Use --from-pr to resume with full PR context.

Milestone Operations (REST API)

Footgun: gh issue edit --milestone takes a NAME (string), not a number. The REST API uses a NUMBER (integer). Never pass a number to --milestone. Load Read("${CLAUDE_SKILL_DIR}/references/cli-vs-api-identifiers.md").

bash
# List milestones with progress
gh api repos/:owner/:repo/milestones --jq '.[] | "\(.title): \(.closed_issues)/\(.open_issues + .closed_issues)"'

# Create milestone with due date
gh api -X POST repos/:owner/:repo/milestones \
  -f title="Sprint 8" -f due_on="2026-02-15T00:00:00Z"

# Close milestone (API uses number, not name)
MILESTONE_NUM=$(gh api repos/:owner/:repo/milestones --jq '.[] | select(.title=="Sprint 8") | .number')
gh api -X PATCH repos/:owner/:repo/milestones/$MILESTONE_NUM -f state=closed

# Assign issues to milestone (CLI uses name, not number)
gh issue edit 123 124 125 --milestone "Sprint 8"

Projects v2 Operations

bash
# Add issue to project
gh project item-add 1 --owner @me --url https://github.com/org/repo/issues/123

# Set custom field (requires GraphQL)
gh api graphql -f query='mutation {...}' -f projectId="..." -f itemId="..."

JSON Output Patterns

bash
# Get issue numbers matching criteria
gh issue list --json number,labels --jq '[.[] | select(.labels[].name == "bug")] | .[].number'

# PR summary with author
gh pr list --json number,title,author --jq '.[] | "\(.number): \(.title) by \(.author.login)"'

# Find ready-to-merge PRs
gh pr list --json number,reviewDecision,statusCheckRollupState \
  --jq '[.[] | select(.reviewDecision == "APPROVED" and .statusCheckRollupState == "SUCCESS")]'

Key Concepts

Milestone vs Epic

Milestones Epics
Time-based (sprints, releases) Topic-based (features)
Has due date No due date
Progress bar Task list checkbox
Native REST API Needs workarounds

Rule: Use milestones for "when", use parent issues for "what".

Projects v2 Custom Fields

Projects v2 uses GraphQL for setting custom fields (Status, Priority, Domain). Basic gh project commands work for listing and adding items, but field updates require GraphQL mutations.


Rules Quick Reference

Rule Impact What It Covers
issue-tracking-automation (load ${CLAUDE_SKILL_DIR}/rules/issue-tracking-automation.md) HIGH Auto-progress from commits, sub-task completion, session summaries
issue-branch-linking (load ${CLAUDE_SKILL_DIR}/rules/issue-branch-linking.md) MEDIUM Branch naming, commit references, PR linking patterns

Batch Issue Creation

When creating multiple issues at once (e.g., seeding a sprint), use an array-driven loop:

bash
# Define issues as an array of "title|labels|milestone" entries
SPRINT="Sprint 9"
ISSUES=(
  "feat: Add user auth|enhancement,backend|$SPRINT"
  "fix: Login redirect loop|bug,high|$SPRINT"
  "chore: Update dependencies|maintenance|$SPRINT"
)

for entry in "${ISSUES[@]}"; do
  IFS='|' read -r title labels milestone <<< "$entry"
  NUM=$(gh issue create \
    --title "$title" \
    --label "$labels" \
    --milestone "$milestone" \
    --body "" \
    --json number --jq '.number')
  echo "Created #$NUM: $title"
done

Tip: Capture the created issue number with --json number --jq '.number' so you can reference it immediately (e.g., add to Projects v2, link in PRs).


Best Practices

  1. Always use --json for scripting - Parse with --jq for reliability
  2. Non-interactive mode for automation - Use --title, --body flags
  3. Check rate limits before bulk operations - gh api rate_limit
  4. Use heredocs for multi-line content - --body "$(cat <<'EOF'...EOF)"
  5. Link issues in PRs - Closes #123, Fixes #456 — GitHub auto-closes on merge
  6. Use ISO 8601 dates - YYYY-MM-DDTHH:MM:SSZ for milestone due_on
  7. Close milestones, don't delete - Preserve history
  8. --milestone takes NAME, not number - Load Read("${CLAUDE_SKILL_DIR}/references/cli-vs-api-identifiers.md")
  9. Never gh issue close directly - Comment progress with gh issue comment; issues close only when their linked PR merges to the default branch

Related Skills

  • ork:create-pr - Create pull requests with proper formatting and review assignments
  • ork:review-pr - Comprehensive PR review with specialized agents
  • ork:release-management - GitHub release workflow with semantic versioning and changelogs
  • stacked-prs - Manage dependent PRs with rebase coordination
  • ork:issue-progress-tracking - Automatic issue progress updates from commits

Key Decisions

Decision Choice Rationale
CLI vs API gh CLI preferred Simpler auth, better UX, handles pagination automatically
Output format --json with --jq Reliable parsing for automation, no regex parsing needed
Milestones vs Epics Milestones for time Milestones have due dates and progress bars, epics for topic grouping
Projects v2 fields GraphQL mutations gh project commands limited, GraphQL required for custom fields
Milestone lifecycle Close, don't delete Preserves history and progress tracking

References

Load on demand with Read("${CLAUDE_SKILL_DIR}/references/<file>"):

File Content
issue-management.md Bulk operations, templates, sub-issues
pr-workflows.md Reviews, merge strategies, auto-merge
milestone-api.md REST API patterns for milestone CRUD
projects-v2.md Custom fields, GraphQL mutations
graphql-api.md Complex queries, pagination, bulk operations
cli-vs-api-identifiers.md NAME vs NUMBER footguns, milestone/project ID mapping

Examples

Load: Read("${CLAUDE_SKILL_DIR}/examples/automation-scripts.md") - Ready-to-use scripts for bulk operations, PR automation, milestone management

Expand your agent's capabilities with these related and highly-rated skills.

yonatangross/orchestkit

expect

Diff-aware AI browser testing — analyzes git changes, generates targeted test plans, and executes them via agent-browser. Reads git diff to determine what changed, maps changes to affected pages via route map, generates a test plan scoped to the diff, and runs it with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, running regression checks on changed components, or validating that recent code changes don't break the user-facing experience.

143 15
Explore
yonatangross/orchestkit

chain-patterns

Chain patterns for CC 2.1.71 pipelines — MCP detection, handoff files, checkpoint-resume, worktree agents, CronCreate monitoring. Use when building multi-phase pipeline skills. Loaded via skills: field by pipeline skills (fix-issue, implement, brainstorm, verify). Not user-invocable.

143 15
Explore
yonatangross/orchestkit

storybook-mcp-integration

Storybook MCP server integration for component-aware AI development. Covers 6 tools across 3 toolsets (dev, docs, testing): component discovery via list-all-documentation/get-documentation, story previews via preview-stories, and automated testing via run-story-tests. Use when generating components that should reuse existing Storybook components, running component tests via MCP, or previewing stories in chat.

143 15
Explore
yonatangross/orchestkit

component-search

Search 21st.dev component registry for production-ready React components. Finds components by natural language description, filters by framework and style system, returns ranked results with install instructions. Use when looking for UI components, finding alternatives to existing components, or sourcing design system building blocks.

143 15
Explore
yonatangross/orchestkit

ai-ui-generation

AI-assisted UI generation patterns for json-render, v0, Bolt, and Cursor workflows. Covers prompt engineering for component generation, review checklists for AI-generated code, design token injection, refactoring for design system conformance, and CI gates for quality assurance. Use when generating UI components with AI tools, rendering multi-surface MCP visual output, reviewing AI-generated code, or integrating AI output into design systems.

143 15
Explore
yonatangross/orchestkit

presentation-builder

Creates zero-dependency, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web slides, or create a slide deck for a talk, pitch, or tutorial. Generates single self-contained HTML files with inline CSS/JS.

143 15
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results