메뉴
Create and manage Claude Code skills. Use when creating skills, modifying skill-rules.json, or debugging activation.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Add a selectable planner keyword end-to-end across FE, BE, and i18n with the proper in-game translation. Use when adding a plan keyword, synergy keyword, faction keyword, or a value to the planner keyword filter.
Synchronize patterns from docs/**/findings.md to CLAUDE.md and skill documentation. Use when updating specs, consolidating learnings, preventing outdated documentation, or running /findings-sync command.
Add a new announcement to all 5 JSON files with auto-translation, commit, and tag. Use when adding announcements, writing update notices, or posting new content.
Full commit workflow — pre-commit validation, branch creation, commit message writing, staging, and checkout. Use this skill whenever the user asks to commit, create a commit, write a commit message, stage changes, finalize work, or prepare code for a PR. Also triggers on phrases like "commit the change", "ready to commit", "let's commit this", "wrap this up", or any git commit-related request.
Interview simulator that tests understanding of architectural decisions. Asks "why" questions, gives hints instead of answers, probes deeper on correct responses. Supports topic-based and random code quiz modes.
| name | skill-developer |
| description | Create and manage Claude Code skills. Use when creating skills, modifying skill-rules.json, or debugging activation. |
my-new-skillreferences/| Level | Location | Loads When | Purpose |
|---|---|---|---|
| L1 | YAML frontmatter | Always (every request) | Trigger detection only |
| L2 | SKILL.md body | Skill matches | Instructions + templates |
| L3 | references/*.md | Explicitly linked | Deep detail, tables, examples |
skill-name/
├── SKILL.md (required — L1 + L2)
├── references/ (optional — L3 detail files)
│ ├── trigger-guide.md
│ └── test-patterns.md
├── scripts/ (optional — executable helpers)
└── assets/ (optional — images, data files)
Location: .claude/skills/{skill-name}/SKILL.md
---
name: my-skill
description: Brief description with trigger keywords.
---
# My Skill
## Rules
- Rule 1
- Rule 2
## Forbidden → Use Instead
| Forbidden | Use Instead |
|-----------|-------------|
| Bad pattern | Good pattern |
## Template
\`\`\`typescript
// One example per pattern
\`\`\`
## Reference
- Triggers: `references/trigger-guide.md`
- Tests: `references/test-patterns.md`
- Pattern: `ExistingFile.tsx`
- Why: `docs/learning/topic.md`
{
"my-skill": {
"type": "guardrail",
"enforcement": "block",
"priority": "high",
"description": "What this skill does",
"promptTriggers": {
"keywords": ["keyword1", "keyword2"],
"intentPatterns": ["(create|add).*?something"]
},
"fileTriggers": {
"pathPatterns": ["src/**/*.tsx"],
"contentPatterns": ["import.*from"]
}
}
}
See references/trigger-guide.md for full trigger types, enforcement levels, priority levels, and agentConfig fields.
Three areas — run in order:
# Trigger test
echo '{"prompt":"your test prompt"}' | npx tsx .claude/hooks/skill-activation-prompt.ts
# Validate JSON
jq . .claude/skills/skill-rules.json
See references/test-patterns.md for functional checklist and comparison test table.
| File | Purpose |
|---|---|
.claude/skills/{name}/SKILL.md | Skill content (L1 + L2) |
.claude/skills/{name}/references/ | Detail files (L3) |
.claude/skills/{name}/scripts/ | Helper scripts |
.claude/skills/skill-rules.json | Trigger config |
.claude/hooks/ | Hook implementations |
.claude/settings.json | Hook registration |
.claude/skills/skill-rules.json.claude/hooks/skill-activation-prompt.tsreferences/trigger-guide.mdreferences/test-patterns.mddocs/learning/skill-development.md