Translate specification files to Japanese while preserving technical accuracy and formatting
/plugin marketplace add teliha/dev-workflows/plugin install dev-workflows@dev-workflowsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
README.mdThis skill automatically activates when:
Check environment variables for configuration:
# Source path pattern (default: specs/**/*.md)
$TRANSLATE_SOURCE_PATH
# Target base directory (default: docs/ja)
$TRANSLATE_TARGET_BASE_PATH
Find all markdown files matching the source pattern:
# Default
find specs/ -name "*.md" -type f
# Custom path from environment
find ${TRANSLATE_SOURCE_PATH} -type f
Map source paths to target paths:
| Source | Target |
|---|---|
specs/vault/spec.md | docs/ja/specs/vault/spec.md |
docs/architecture.md | docs/ja/docs/architecture.md |
README.md | docs/ja/README.md |
Keep in English (with Japanese explanation on first use):
Example:
# English
The vault implements the IVault interface.
# Japanese
Vault(ボールト)はIVaultインターフェースを実装します。
Example:
// English
// Check if the account is healthy
function checkAccountHealth(address account) external view returns (bool);
// Japanese
// アカウントが健全かチェックする
function checkAccountHealth(address account) external view returns (bool);
Translate labels, keep formulas:
# English
Collateral Value = Balance × Price × Collateral Factor
# Japanese
担保価値 = 残高 × 価格 × 担保係数
| English | Japanese |
|---|---|
| Vault | ボールト |
| Collateral | 担保 |
| Liability | 負債 |
| Liquidation | 清算 |
| Controller | コントローラー |
| Account | アカウント |
| Health Factor | ヘルスファクター |
| Oracle | オラクル |
| Governor | ガバナー |
| Interest Rate | 金利 |
| Deposit | 預け入れ |
| Withdraw | 引き出し |
| Borrow | 借り入れ |
| Repay | 返済 |
| Position | ポジション |
| Margin | マージン |
| Leverage | レバレッジ |
| Slippage | スリッページ |
| Transaction | トランザクション |
| Block | ブロック |
| Gas | ガス |
| Fee | 手数料 |
For each file:
Ensure links work in translated structure:
# English
See [Vault Spec](./vault/spec.md)
# Japanese (same relative path works)
[Vault仕様](./vault/spec.md)を参照してください
After translation:
After translation:
## Translation Summary
### Configuration
- Source pattern: `specs/**/*.md`
- Target base: `docs/ja`
### Files Translated
| Source | Target | Status |
|--------|--------|--------|
| `specs/vault/spec.md` | `docs/ja/specs/vault/spec.md` | Done |
| `specs/api/spec.md` | `docs/ja/specs/api/spec.md` | Done |
### Statistics
- Total files: 5
- Total lines translated: 1,234
- Technical terms standardized: 45
### Glossary Used
| English | Japanese | Count |
|---------|----------|-------|
| Vault | ボールト | 23 |
| Collateral | 担保 | 18 |
### Notes
- [Any special considerations or decisions made]
Before completing:
name: Translate Specs
on:
push:
paths:
- 'specs/**/*.md'
workflow_dispatch:
jobs:
translate:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: anthropics/claude-code-action@v1
with:
claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
prompt: /translate-specs
env:
TRANSLATE_SOURCE_PATH: "specs/**/*.md"
TRANSLATE_TARGET_BASE_PATH: "docs/ja"
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.