aboylabs/ai-agent-skills / skills/github/public-repo-creation
public-repo-creation
UnverifiedCreate production-ready public GitHub repositories with comprehensive documentation, automated setup, and quality assurance
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.1 KB |
| references/critical-bugs-mnemosyne-obsidian.md | markdown | 5.0 KB |
| references/deep-analysis-workflow.md | markdown | 5.7 KB |
| references/repo-maximization-checklist.md | markdown | 14.9 KB |
| references/setup-script-patterns.md | markdown | 11.6 KB |
references/deep-analysis-workflow.md
View on GitHub# Deep Analysis Workflow for Public Repos
When user requests "analisa ulang" / "cek ulang" / "pastikan lengkap dan perfect", perform comprehensive deep analysis.
## Analysis Checklist
### 1. Syntax Validation
```bash
# Bash scripts
bash -n setup.sh
# Expected: No output = valid
# Python scripts (if any)
python3 -m py_compile script.py
```
### 2. Link Validation
```bash
# Internal markdown links
grep -o '\[.*\](.*\.md)' *.md | while read link; do
file=$(echo "$link" | sed 's/.*(\\(.*\\))/\\1/')
[ -f "$file" ] && echo "✅ $link" || echo "❌ Broken: $link"
done
# External links (manual check recommended)
grep -o 'https://[^)]*' *.md | sort -u
```
### 3. File Permissions
```bash
# Check executable files
find . -type f -executable ! -path "./.git/*"
# Expected: Only setup.sh (or similar)
# Check setup.sh permissions
ls -la setup.sh
# Expected: -rwxrwxr-x (755)
```
### 4. Template Placeholders
```bash
# Check for valid placeholder syntax
grep -r "{{" templates/
# Expected: Obsidian Templater syntax ({{date}}, {{PROJECT_NAME}}, etc.)
```
### 5. Bundled Dependencies Integrity
```bash
# Check if all expected files present
find bundled-deps/ -name "SKILL.md" -o -name "README.md"
# Count should match expected number
# Check for nested .git (should be removed)
find bundled-deps/ -name ".git"
# Expected: No output
```
### 6. TODO/FIXME Check
```bash
# Find any TODO/FIXME comments
grep -ri "TODO\|FIXME\|XXX\|HACK" . --include="*.md" --include="*.sh" ! -path "./.git/*"
# Expected: No output for production repos
```
### 7. Cross-Reference Check
```bash
# Check wikilinks reference existing notes
grep -o '\[\[.*\]\]' *.md | sort -u
# Verify each referenced note exists or is example-only
```
### 8. Setup Script Logic Check
```bash
# Check for duplicate append patterns
grep -n ">> ~/\." setup.sh
# Each should have duplicate-prevention check
# Check heredoc quotes
grep -n "<<" setup.sh
# Verify 'EOF' vs EOF based on expansion needs
```
### 9. Title Consistency Check
```bash
# Extract all main titles
grep -h "^# " README.md EXAMPLE.md CONTRIBUTING.md
grep "^# " setup.sh | head -1
# All should mention same components (e.g., "Tool A + Tool B + Feature C")
```
### 10. Character/Word Count (for social posts)
```bash
# Character count (for Twitter/X)
cat post.txt | tr -d '\n' | wc -c
# Should be ≤260 for Twitter
# Word count (for other platforms)
wc -w post.txt
```
## Simulation Test
Create dry-run simulation to validate setup.sh logic:
```bash
#!/bin/bash
# Simulate setup.sh execution (dry-run)
echo "=== SETUP SIMULATION ==="
# Check prerequisites
echo "✓ Git check"
echo "✓ Snap check"
# Simulate each major step
GITHUB_USER="testuser"
VAULT_NAME="test-vault"
GITHUB_TOKEN="ghp_test123"
echo "✓ User input: $GITHUB_USER, $VAULT_NAME"
echo "✓ Would create: $HOME/path/to/vault"
echo "✓ Would install dependencies"
echo "✓ Would save token (with duplicate check)"
echo "✓ Would init Git repo"
echo "✓ Would create initial files with date: $(date +%Y-%m-%d)"
echo "✓ Would create GitHub repo: $VAULT_NAME (private)"
echo "✓ Would push initial commit"
echo "=== SIMULATION COMPLETE ==="
echo "All steps validated ✅"
```
## Critical Bug Patterns to Check
### Pattern 1: Config File Duplication
**Look for:**
```bash
echo "SETTING=value" >> ~/.config
```
**Should be:**
```bash
if ! grep -q "SETTING=" ~/.config 2>/dev/null; then
echo "SETTING=value" >> ~/.config
else
sed -i "s|SETTING=.*|SETTING=value|" ~/.config
fi
```
### Pattern 2: Heredoc Variable Expansion
**Look for:**
```bash
cat > file.txt << 'EOF'
date: $(date +%Y-%m-%d)
EOF
```
**Should be:**
```bash
cat > file.txt << EOF # No quotes!
date: $(date +%Y-%m-%d)
EOF
```
### Pattern 3: Missing Fallback
**Look for:**
```bash
git clone https://github.com/repo.git
```
**Should be:**
```bash
if git clone https://github.com/repo.git 2>/dev/null; then
echo "✅ Cloned from GitHub"
else
echo "⚠️ GitHub failed, using bundled copy..."
cp -r bundled/ destination/
fi
```
## Quality Score Calculation
**Scoring criteria (0-10):**
- Documentation completeness: 2 points
- Setup automation: 2 points
- Error handling: 1 point
- Fallback mechanisms: 1 point
- Security practices: 1 point
- Code quality: 1 point
- Testing/validation: 1 point
- User experience: 1 point
**Deductions:**
- Critical bugs: -1 point each
- Missing required sections: -0.5 points each
- Broken links: -0.2 points each
- No error handling: -1 point
- Hardcoded paths: -0.5 points
**Target:** 9.5+/10 for production-ready
## Output Format
Create `DEEP_ANALYSIS.md` with:
1. **Executive Summary**
- Result (PASS/FAIL)
- Critical issues found
- Quality score
2. **Critical Bugs Found & Fixed**
- Severity (🔴 CRITICAL, 🟡 MEDIUM, 🟢 LOW)
- Before/after code
- Impact explanation
- Commit reference
3. **Quality Checks Performed**
- Each check with ✅/❌ result
- Details for failures
4. **Metrics**
- Files, size, lines, commits
- Before/after comparison
5. **Recommendations**
- High/medium/low priority improvements
- Optional enhancements
6. **Final Verdict**
- Production ready? Yes/No
- Blocking issues (if any)
- Next steps
## When to Perform Deep Analysis
**Triggers:**
- User says "analisa ulang" / "cek ulang" / "pastikan lengkap"
- User says "perfect" / "maksimal" / "gak ada masalah"
- Before tagging v1.0.0
- Before sharing publicly
- After major changes (5+ commits)
- When user expresses doubt ("yakin udah bener?")
**Don't perform if:**
- User just wants quick check
- Repo is work-in-progress
- User explicitly says "skip analysis"
## Time Estimate
- Quick check (5 items): 2 minutes
- Standard analysis (10 items): 5 minutes
- Deep analysis (all items + simulation): 10 minutes
- Full audit (analysis + AUDIT.md): 15 minutes
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |