Agent skill
opencode-ralph-loop
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/opencode-ralph-loop
SKILL.md
OpenCode Ralph Loop - 反復開発支援
opt-in、既定OFF、乱用禁止の反復開発スキルです。
使用前チェック(すべて満たすこと)
- 仕様が明確に固まっている
- 反復可能なタスク
- 上限設定が可能
- コスト許容範囲内
実行手順
1. 一時的に有効化
.opencode/oh-my-opencode.json:
{
"ralph_loop": {
"enabled": true,
"default_max_iterations": 10
}
}
2. ディレクトリ準備
mkdir -p .opencode/state .opencode/runs
3. Ralph Loop 実行
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
opencode /ralph-loop "Implement feature X" \
--max-iterations=10 \
--completion-promise="All tests pass and coverage > 80%" \
> .opencode/runs/ralph_${TIMESTAMP}.log 2>&1
4. ログ退避(memory_add)
memory_add で .opencode/runs/ralph_${TIMESTAMP}.log を保存
→ referenceId を取得
5. 設定を元に戻す(重要)
{
"ralph_loop": {
"enabled": false
}
}
禁止事項
- 無制限実行 - 必ず max-iterations を設定
- 曖昧な仕様 - completion-promise が不明確な場合
- 常時有効化 - 使用後は必ず無効化
- 大量ログの投稿 - 会話/Issueに全文を貼る
推奨運用
- 最初は小さく - max-iterations=5 から開始
- 監視しながら - ログを tail -f で確認
- 使用後は無効化 - enabled: false に戻す
- ログは退避 - memory_add で保存
- 要約のみ投稿 - refId 運用を徹底
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?