AI-powered issue summarization, auto-labeling, and Q&A using gh-models with 88% effectiveness. Use when analyzing issue content, suggesting labels, or extracting insights.
Uses gh-models for AI-powered issue summarization, auto-labeling, and Q&A with 88% effectiveness. Trigger when analyzing issues, suggesting labels, or extracting insights from GitHub issues.
/plugin marketplace add terrylica/claude-code-skills-github-issues/plugin install github-issues-operations@github-issues-skillsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Capability: AI-assisted issue summarization, auto-labeling, Q&A, and documentation generation using gh-models
When to use: Leveraging LLMs for intelligent issue processing and automation
Installation Required: gh extension install github/gh-models
# Show all 29+ models
gh models list
# Popular models for issue operations:
# - openai/gpt-4.1
# - openai/gpt-4o-mini
# - anthropic/claude-3.5-sonnet
# Run AI model
gh models run "openai/gpt-4.1" "Your prompt here"
# With multi-line prompt
gh models run "openai/gpt-4.1" "$(cat <<'EOF'
Analyze this issue and suggest improvements:
- Title clarity
- Completeness
- Priority assessment
EOF
)"
# Get issue content
ISSUE_BODY=$(gh issue view 123 --json body --jq .body)
# Summarize
gh models run "openai/gpt-4.1" "$(cat <<'EOF'
Summarize this issue in 2-3 bullet points:
$ISSUE_BODY
EOF
)"
Use Case: Creating concise summaries for long issues, weekly reports
# Get issue content
ISSUE_CONTENT=$(gh issue view 123 --json title,body --jq '{title, body}')
# Available labels
LABELS="bug,feature,documentation,question,enhancement,wontfix,duplicate"
# Suggest labels
gh models run "openai/gpt-4.1" "$(cat <<'EOF'
Suggest 2-3 labels from this list: $LABELS
Issue:
$ISSUE_CONTENT
Respond with comma-separated label names only.
EOF
)"
# Apply suggested labels
gh issue edit 123 --add-label bug,priority:high
Use Case: Automating issue triage, maintaining consistent labeling
# Knowledge base Q&A
QUERY="How do I use Claude Code plan mode?"
# Search relevant issues
ISSUES=$(gh search issues "$QUERY" --repo=terrylica/claude-code-skills-github-issues --json number,title,body --jq '.')
# Ask AI
gh models run "openai/gpt-4.1" "$(cat <<'EOF'
Answer this question based on these GitHub Issues:
Question: $QUERY
Issues:
$ISSUES
Provide a concise answer with issue references.
EOF
)"
Use Case: Knowledge base Q&A, finding relevant information across issues
# Get related issues
ISSUES=$(gh search issues --label=feature-request --closed --json title,body --jq '.')
# Generate changelog
gh models run "openai/gpt-4.1" "$(cat <<'EOF'
Generate a user-facing changelog from these closed feature requests:
$ISSUES
Format:
## New Features
- Feature name: Brief description
Keep it concise and user-friendly.
EOF
)"
Use Case: Generating changelogs, release notes, feature documentation
# Get issue
ISSUE=$(gh issue view 123 --json title,body --jq '{title, body}')
# Classify
gh models run "openai/gpt-4.1" "$(cat <<'EOF'
Classify this issue into ONE category:
- Bug Report
- Feature Request
- Documentation
- Question
- Enhancement
Issue:
$ISSUE
Respond with category name only.
EOF
)"
| Operation | Effectiveness | Test Count |
|---|---|---|
| Issue Summarization | 88% | 5 tests |
| Auto-Label Suggestion | 89% | 5 tests |
| Issue Q&A | 91% | 5 tests |
| Documentation Generation | 86% | 5 tests |
| Issue Classification | 88% | 5 tests |
Average Effectiveness: 88%
Detailed Results: GH-MODELS-POC-RESULTS.md
Fast & Cheap (Good for bulk operations):
openai/gpt-4o-mini - Fast, cost-effectiveopenai/gpt-3.5-turbo - BalancedHigh Quality (Complex analysis):
openai/gpt-4.1 - Best qualityanthropic/claude-3.5-sonnet - Long context, detailed analysisTesting: Try different models to find best quality/cost tradeoff
#!/bin/bash
# Auto-triage new issues
# Get new issues
gh issue list --label needs-triage --json number,title,body --jq '.[] | @json' | \
while read -r issue; do
# Extract fields
number=$(echo "$issue" | jq -r .number)
content=$(echo "$issue" | jq -r '{title, body}')
# Get AI suggestions
labels=$(gh models run "openai/gpt-4o-mini" "$(cat <<EOF
Suggest 2-3 labels: bug,feature,documentation,question,enhancement
Issue: $content
Respond with comma-separated labels only.
EOF
)")
# Apply labels
gh issue edit "$number" --add-label "$labels" --remove-label needs-triage
echo "Triaged issue #$number: $labels"
done
Installation: gh extension install github/gh-models
Full Extension Guide: GITHUB_CLI_EXTENSIONS.md
Complete POC Results: GH-MODELS-POC-RESULTS.md
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.