triforce-sync-check
Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
Best use case
triforce-sync-check is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "triforce-sync-check" skill to help with this workflow task. Context: Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/triforce-sync-check/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How triforce-sync-check Compares
| Feature / Agent | triforce-sync-check | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Verify 3-Mirror skill sync consistency across .public/skills, .codex/skills, and .claude/skills. Use after skill changes, before commits, or for CI validation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Triforce Sync Check
3-Mirror 스킬 동기화 일관성을 검증하는 스킬입니다.
## Architecture
```
.public/skills/ (SSOT - Single Source of Truth)
│
├──► .codex/skills/ (Mirror - Antigravity/Codex)
│
└──► .claude/skills/ (Mirror - Claude Code)
```
## When to Use
- 스킬 추가/수정/삭제 후
- 커밋 전 검증
- CI/CD 파이프라인
- 배포 전 확인
## Quick Check
```bash
# 1. 스킬 수 확인
ls -1d .public/skills/*/ | wc -l
ls -1d .codex/skills/*/ | wc -l
ls -1d .claude/skills/*/ | wc -l
# 2. 콘텐츠 해시 비교
find .public/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5
find .codex/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5
find .claude/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5
```
## Full Verification Checklist
### 1. Count Verification
```bash
public_count=$(ls -1d .public/skills/*/ | wc -l)
codex_count=$(ls -1d .codex/skills/*/ | wc -l)
claude_count=$(ls -1d .claude/skills/*/ | wc -l)
echo "SSOT: $public_count"
echo "Codex: $codex_count"
echo "Claude: $claude_count"
```
**Pass Criteria**: 3개 값이 모두 동일
### 2. Structure Verification
```bash
# 디렉토리 목록 비교
diff <(ls -1 .public/skills | sort) <(ls -1 .codex/skills | sort)
diff <(ls -1 .public/skills | sort) <(ls -1 .claude/skills | sort)
```
**Pass Criteria**: diff 출력 없음 (빈 결과)
### 3. Content Verification
```bash
# SKILL.md 파일 해시 비교
public_hash=$(find .public/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5)
codex_hash=$(find .codex/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5)
claude_hash=$(find .claude/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5)
[ "$public_hash" = "$codex_hash" ] && [ "$public_hash" = "$claude_hash" ]
```
**Pass Criteria**: 3개 해시가 모두 동일
### 4. YAML Validation
```bash
# 각 SKILL.md의 frontmatter 유효성
for skill in .public/skills/*/SKILL.md; do
name=$(grep "^name:" "$skill" | head -1)
desc=$(grep "^description:" "$skill" | head -1)
if [ -z "$name" ] || [ -z "$desc" ]; then
echo "INVALID: $skill"
fi
done
```
**Pass Criteria**: INVALID 출력 없음
### 5. Duplicate Check
```bash
# name 필드 중복 확인
grep -h "^name:" .public/skills/*/SKILL.md | sort | uniq -c | grep -v "^ *1 "
```
**Pass Criteria**: 출력 없음 (중복 없음)
## Sync Command
불일치 발견 시 재동기화:
```bash
node scripts/sync-skills.js
```
## CI Integration
```yaml
# .github/workflows/skills-check.yml
- name: Triforce Sync Check
run: |
public=$(ls -1d .public/skills/*/ | wc -l)
codex=$(ls -1d .codex/skills/*/ | wc -l)
claude=$(ls -1d .claude/skills/*/ | wc -l)
if [ "$public" != "$codex" ] || [ "$public" != "$claude" ]; then
echo "❌ Mirror count mismatch"
exit 1
fi
pub=$(find .public/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5)
cx=$(find .codex/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5)
cl=$(find .claude/skills -name "SKILL.md" -exec md5 -q {} \; | sort | md5)
if [ "$pub" != "$cx" ] || [ "$pub" != "$cl" ]; then
echo "❌ Content hash mismatch"
exit 1
fi
echo "✅ Triforce sync verified"
```
## Troubleshooting
| 증상 | 원인 | 해결 |
|------|------|------|
| 수 불일치 | sync 미실행 | `node scripts/sync-skills.js` |
| 해시 불일치 | 직접 미러 수정 | SSOT 수정 후 sync |
| YAML 오류 | frontmatter 형식 | name/description 확인 |
| 중복 name | 복사 붙여넣기 실수 | 고유한 name으로 수정 |
## Pass/Fail Summary
```
✅ PASS 조건:
- Count: github = codex = claude
- Structure: 동일한 디렉토리 목록
- Content: 동일한 해시값
- YAML: 모든 스킬에 name + description
- Unique: 중복 name 없음
❌ FAIL 시:
1. 오류 유형 식별
2. SSOT (.public/skills) 수정
3. sync-skills.js 실행
4. 재검증
```Related Skills
doc-sync-tool
自动同步项目中的 Agents.md、claude.md 和 gemini.md 文件,保持内容一致性。支持自动监听和手动触发。
shellcheck-configuration
Master ShellCheck static analysis configuration and usage for shell script quality. Use when setting up linting infrastructure, fixing code issues, or ensuring script portability.
security-compliance-compliance-check
You are a compliance expert specializing in regulatory requirements for software systems including GDPR, HIPAA, SOC2, PCI-DSS, and other industry standards. Perform compliance audits and provide implementation guidance.
rust-async-patterns
Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns. Use when building async Rust applications, implementing concurrent systems, or debugging async code.
pentest-checklist
This skill should be used when the user asks to "plan a penetration test", "create a security assessment checklist", "prepare for penetration testing", "define pentest scope", "follow security testing best practices", or needs a structured methodology for penetration testing engagements.
code-review-checklist
Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability
aws-compliance-checker
Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks
doc-sync
Keeps IdeaVim documentation in sync with code changes. Use this skill when you need to verify documentation accuracy after code changes, or when checking if documentation (in doc/, README.md, CONTRIBUTING.md) matches the current codebase. The skill can work bidirectionally - from docs to code verification, or from code changes to documentation updates.
async-sync-advisor
Guides users on choosing between async and sync patterns for Lambda functions, including when to use tokio, rayon, and spawn_blocking. Activates when users write Lambda handlers with mixed workloads.
async-patterns-guide
Guides users on modern async patterns including native async fn in traits, async closures, and avoiding async-trait when possible. Activates when users work with async code.
ghe-checkpoint
Posts a progress checkpoint to the currently active GitHub Issue thread. Saves work state including completed tasks, in-progress items, files changed, commits, and blockers without changing workflow phases. Requires an already-claimed in-progress thread. Use when user wants to save progress, record milestones, document blockers, or preserve state before ending a session.
quick-quality-check
Lightning-fast quality check using parallel command execution. Runs theater detection, linting, security scan, and basic tests in parallel for instant feedback on code quality.