← 返回 Skills 市场
83
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install decision-forest
功能描述
Map a decision into options, non-negotiables, criteria, best/base/worst cases, reversibility, and a review checkpoint. Use when the user is comparing multipl...
使用说明 (SKILL.md)
Decision Forest
Overview
Use this skill to slow a messy decision down enough to see what actually matters. It helps the user define the real question, compare options branch by branch, separate facts from assumptions and fears, and end with either a provisional choice or a clearly bounded next test.
This skill is descriptive only. It does not provide legal, medical, or financial advice, and it does not predict outcomes.
Trigger
Use this skill when the user wants to:
- compare two or more life, work, or project options
- stop mixing facts, fears, and imagined outcomes together
- add reversibility and future-regret checks to a decision
- narrow a crowded option set
- choose a small test instead of forcing immediate certainty
Example prompts
- "Help me decide whether to stay in my job or start a small consulting business"
- "Build a decision tree for moving, waiting, or testing a smaller version"
- "I am stuck between two options and I cannot see what matters most"
- "Map best case, base case, and worst case for this decision"
Workflow
- Define the decision in one sentence.
- List the visible options and the hidden option of delaying or testing a smaller version.
- Identify non-negotiables and decision criteria.
- Build branches for each option.
- Sketch best case, base case, and worst case outcomes.
- Check reversibility and future regret.
- Recommend a provisional choice and a review checkpoint.
Inputs
The user can provide any mix of:
- the decision question
- visible options
- deadline or time pressure
- constraints and non-negotiables
- known facts or data points
- fears, hopes, or gut reactions
- practical criteria, such as cost, time, energy, meaning, family impact, or reversibility
Outputs
Return a markdown decision brief with:
- decision trunk summary
- non-negotiables and criteria
- branch review for each option
- best, base, and worst cases
- reversibility and key unknowns
- provisional choice logic and review date
Safety
- Keep facts, assumptions, and fears visibly separate.
- High-stakes legal, medical, or financial decisions may need expert advice beyond heuristics.
- Do not claim certainty the information cannot support.
- When uncertainty is high, prefer a smaller reversible test over forced confidence.
Acceptance Criteria
- Return markdown text.
- Include at least three meaningful criteria.
- Show reversibility for each branch.
- End with either a provisional choice or a very clear next test.
安全使用建议
This skill appears to do exactly what it says: parse your decision text and produce a structured markdown decision brief. It only reads its own SKILL.md and the user input; it does not access environment variables, remote endpoints, or install additional software. Be aware the decision logic uses simple text heuristics (keyword matching), so outputs may be blunt or miss nuance; treat its recommendations as a structured prompt for your own judgment rather than expert legal/medical/financial advice.
功能分析
Type: OpenClaw Skill
Name: decision-forest
Version: 1.0.0
The 'decision-forest' skill is a text-processing utility designed to help users structure complex decisions. The Python logic in handler.py uses basic regex and keyword matching to categorize user input into facts, fears, and options, and the SKILL.md instructions are strictly aligned with this decision-aid purpose without any high-risk behaviors or prompt-injection risks.
能力评估
Purpose & Capability
Name/description match the implementation: the handler parses user text into a decision brief, extracts options/criteria/fears/etc., and renders markdown. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
SKILL.md instructs the agent to build a decision tree and return markdown. The code follows those instructions. The only non-user data access is reading the local SKILL.md file for metadata, which is consistent with the skill packaging.
Install Mechanism
There is no install specification (instruction-only from a platform perspective). The package includes source files but does not declare downloads or external installers. No archives or remote URLs are fetched in the code.
Credentials
The skill requires no environment variables, credentials, or config paths. The code does not access os.environ beyond locating its own SKILL.md and has no network calls or secret-handling behavior.
Persistence & Privilege
The skill is not always-enabled and does not modify other skills or system-wide settings. It does not write files or persist credentials; its file I/O is limited to reading its own SKILL.md.
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 decision-forest - 安装完成后，直接呼叫该 Skill 的名称或使用
/decision-forest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 Decision Forest skill.
- Guides users through structured decision-making with options, criteria, and non-negotiables.
- Separates facts, assumptions, and fears to clarify thinking.
- Maps best, base, and worst case outcomes for each option.
- Evaluates reversibility and future-regret for each path.
- Outputs a clear, markdown decision brief with a provisional choice or next test.
元数据
常见问题
Decision Forest 是什么？
Map a decision into options, non-negotiables, criteria, best/base/worst cases, reversibility, and a review checkpoint. Use when the user is comparing multipl... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 83 次。
如何安装 Decision Forest？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install decision-forest」即可一键安装，无需额外配置。
Decision Forest 是免费的吗？
是的，Decision Forest 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Decision Forest 支持哪些平台？
Decision Forest 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 Decision Forest？
由 haidong（@harrylabsj）开发并维护，当前版本 v1.0.0。
推荐 Skills