← 返回 Skills 市场
133
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install prompt-design-tuning
功能描述
Collaboratively design, evaluate, iterate on, and recommend a final launch candidate for a target prompt under the principle of “human-gated, agent-executed”...
安全使用建议
This skill is an instruction-only workflow for designing and iterating prompts and appears coherent. Before using it in Execution Mode, remember: (1) only provide API keys or credentials if you expect the agent to actually call models — do not paste secrets unless you trust the human-approved run; (2) review any scripts or code the agent generates before executing them in your environment; (3) approve high-cost evaluation loops explicitly as the skill requests; and (4) if you need the agent to access private data or systems, confirm that it’s necessary and scope the data tightly. If you want extra assurance, ask the skill to produce a dry-run plan (Design-Only Mode) before giving it permission to run evaluations.
功能分析
Type: OpenClaw Skill
Name: prompt-design-tuning
Version: 1.0.0
The skill bundle defines a structured, professional workflow for prompt engineering and evaluation using a 'human-gated, agent-executed' approach. It includes detailed instructions for task definition, automated evaluation scripts, and cost-controlled iteration cycles in SKILL.md. No indicators of malicious intent, data exfiltration, or unauthorized execution were found; the instructions emphasize transparency, human oversight, and standard engineering best practices.
能力评估
Purpose & Capability
The name and description (prompt design & tuning) match the SKILL.md: it describes a human-gated, agent-executed workflow for drafting prompts, judge prompts, evaluation plans, and producing script skeletons and reports. No unrelated capabilities, binaries, or credentials are requested.
Instruction Scope
The instructions stay within prompt-design and evaluation workflow boundaries: they ask the agent to gather task specs, produce drafts, prepare evaluation plans, and (if a runnable environment is provided) run batch generation and evaluation. Human approval is explicitly required for high-cost loops. The SKILL.md does not instruct the agent to read arbitrary system files or to exfiltrate data. It does assume that a model invocation method (curl/SDK/API) may be supplied by the user before execution — which is reasonable for an execution-capable mode.
Install Mechanism
There is no install spec and no code files — this is instruction-only, so nothing is written to disk by an installer. Recommended deliverables include scripts and docs the agent may draft, but no automatic downloads or installs are specified.
Credentials
The skill declares no required environment variables, credentials, or config paths. The instructions reference using a provided invocation method (which would require credentials supplied by the user in Execution Mode), but the skill itself does not request or demand any secrets — this is proportionate to its purpose.
Persistence & Privilege
always:false (default) and autonomous invocation is not disabled (also normal). The skill does not request permanent presence or system-wide configuration changes. Human gates are required for costly operations, limiting autonomous high-impact actions.
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 prompt-design-tuning - 安装完成后，直接呼叫该 Skill 的名称或使用
/prompt-design-tuning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: Provides a structured, human-gated workflow for prompt design and tuning.
- Defines two main working modes: Design-Only and Execution, adapting to different project readiness levels.
- Enforces separation between target prompts and judge prompts, with strict versioning and optimization logging requirements.
- Outlines mandatory human approval gates at key decision points (task definition, prompt directions, high-cost evaluations, final launch).
- Specifies required documentation, scripts, and reports for transparent, reusable prompt engineering.
- Recommends inputs to collect for each project, ensuring clear task specs, evaluation plans, and cost control.
元数据
常见问题
Prompt Design Tuning 是什么？
Collaboratively design, evaluate, iterate on, and recommend a final launch candidate for a target prompt under the principle of “human-gated, agent-executed”... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 133 次。
如何安装 Prompt Design Tuning？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install prompt-design-tuning」即可一键安装，无需额外配置。
Prompt Design Tuning 是免费的吗？
是的，Prompt Design Tuning 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Prompt Design Tuning 支持哪些平台？
Prompt Design Tuning 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 Prompt Design Tuning？
由 yuanjie（@abysscat-yj）开发并维护，当前版本 v1.0.0。
推荐 Skills