← 返回 Skills 市场
128
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install nm-attune-dorodango
功能描述
Iteratively polish code through successive quality passes run in fresh subagents
安全使用建议
This skill appears to do what it says: run iterative passes (tests, clarity, consistency, polish) and edit code until convergence, recording progress in .attune/dorodango-state.json. Before running: back up your code or run in a disposable branch/worktree, ensure tests can be executed safely in your environment, and review the edits produced by the skill. Note the skill may invoke other installed skills (e.g., pensive:code-refinement) for certain passes — those skills may introduce additional behavior you should review. If you require absolute isolation, run the workflow in a sandbox or CI environment rather than on a live repository.
能力评估
Purpose & Capability
Name/description (iterative polishing) align with the declared artifacts: pass-definitions, state persistence, and subagent-driven passes. The declared config dependency (night-market.modules/pass-definitions.md) is present and matches the described pass types.
Instruction Scope
SKILL.md instructs running tests (bash/pytest), reading and editing target files, and creating .attune/dorodango-state.json. These actions are expected for a code-polishing workflow but do mean the skill will execute test commands and modify source files in the target directory — review changes or run in a sandbox if you need to be cautious.
Install Mechanism
Instruction-only skill with no install spec and no code files. Lowest-risk install posture — nothing is downloaded or written by an installer beyond the described state file when run.
Credentials
No environment variables, credentials, or unrelated config paths are requested. The single declared config file is the included pass-definitions.md, which is appropriate for the skill's behavior.
Persistence & Privilege
Does not request always:true, does not modify other skills, and only persists a local state file (.attune/dorodango-state.json) to resume sessions. Autonomous invocation is allowed by default but is not combined with elevated privileges or extra credentials.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install nm-attune-dorodango - 安装完成后，直接呼叫该 Skill 的名称或使用
/nm-attune-dorodango触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of the dorodango skill for iterative code polishing.
- Introduces a four-pass workflow targeting correctness, clarity, consistency, and final polish
- Tracks convergence state per quality dimension for efficient, resumable operation
- Uses isolated subagents for each pass to ensure fresh context and reliable results
- Automatically halts after maximum 10 passes or when all dimensions are converged
- Designed for post-implementation code refinement and preparation for review or release
元数据
常见问题
Nm Attune Dorodango 是什么？
Iteratively polish code through successive quality passes run in fresh subagents. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 128 次。
如何安装 Nm Attune Dorodango？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install nm-attune-dorodango」即可一键安装，无需额外配置。
Nm Attune Dorodango 是免费的吗？
是的，Nm Attune Dorodango 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Nm Attune Dorodango 支持哪些平台？
Nm Attune Dorodango 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Nm Attune Dorodango？
由 athola（@athola）开发并维护，当前版本 v1.0.0。
推荐 Skills