← 返回 Skills 市场
harrylabsj

Decision Distiller

作者 haidong · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
238
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install decision-distiller
功能描述
Distill decision contexts, options, trade-offs, and outcomes into structured decision records. Use when the user is facing a choice, has made a decision they...
使用说明 (SKILL.md)

Decision Distiller

Overview

Decision Distiller helps capture, structure, and learn from decisions made during OpenClaw sessions. It transforms informal decision-making into documented, reviewable records that build organizational knowledge over time.

When to Use

Use this skill when:

  • A user is weighing multiple options and needs clarity
  • A decision has been made and should be documented
  • Past decisions need review or analysis
  • Decision patterns across sessions should be identified
  • The user asks to "document this decision" or "record why we chose X"

Core Concepts

Decision Record

A structured document capturing:

  • Context: Situation requiring a decision
  • Options: Alternatives considered
  • Criteria: How options were evaluated
  • Decision: The choice made
  • Rationale: Why this choice was made
  • Trade-offs: What was gained/lost
  • Outcome: Result of the decision (filled later)
  • Lessons: What was learned

Decision Status

  • pending: Decision not yet made
  • decided: Decision made, awaiting outcome
  • validated: Decision proven correct
  • revised: Decision changed based on new information
  • archived: Decision no longer relevant

Input

Accepts decision information in various forms:

  • Conversation about options
  • Pros/cons lists
  • Direct statements of choice
  • Retrospective analysis

Output

Produces:

  • Dated decision records (Markdown)
  • Decision summaries
  • Pattern analysis across decisions
  • Decision status reports

Workflow

Capturing a New Decision

  1. Identify Context

    • What situation required a decision?
    • What was at stake?
    • Who was involved?
  2. List Options

    • What alternatives were considered?
    • What was eliminated early?
    • What made it to final consideration?
  3. Define Criteria

    • How were options evaluated?
    • What mattered most?
    • Were there constraints?
  4. Record Decision

    • What was chosen?
    • When was it decided?
    • Who decided?
  5. Document Rationale

    • Why was this option selected?
    • What tipped the balance?
    • What assumptions were made?
  6. Note Trade-offs

    • What was sacrificed?
    • What risks were accepted?
    • What opportunities were passed?

Reviewing Past Decisions

  1. Gather Records

    • Collect relevant decision records
    • Filter by topic, date, or status
  2. Analyze Patterns

    • Common criteria used
    • Recurring trade-offs
    • Typical decision timelines
  3. Extract Lessons

    • What worked well?
    • What would change?
    • What patterns emerge?

Output Format

Decision Record

# Decision: [Title] - YYYY-MM-DD

**ID**: DEC-2024-001
**Status**: decided
**Decided By**: [Name/Role]
**Date**: YYYY-MM-DD

## Context
[Description of the situation requiring a decision]

## Options Considered

### Option 1: [Name]
- **Description**: 
- **Pros**: 
- **Cons**: 
- **Estimated Impact**: 

### Option 2: [Name]
- **Description**: 
- **Pros**: 
- **Cons**: 
- **Estimated Impact**: 

## Decision Criteria
1. [Criterion 1] - Weight: High/Medium/Low
2. [Criterion 2] - Weight: High/Medium/Low

## Decision
**Chosen**: [Option X]

## Rationale
[Why this option was selected over others]

## Trade-offs
- **Accepted**: [What we gave up]
- **Mitigated**: [How we reduced risks]

## Expected Outcome
[What we expect to happen]

## Actual Outcome
[Filled in later - what actually happened]

## Lessons Learned
[Filled in later - insights from the outcome]

## Related Decisions
- [Link to related decision]

Commands

Create Decision Record

decision create "Decision title" --status pending

Update Decision

decision update DEC-2024-001 --status validated

List Decisions

decision list --status decided --since 2024-01-01

Analyze Patterns

decision analyze --topic architecture

Quality Rules

  • Be specific: vague decisions teach no lessons
  • Include alternatives: decisions without options aren't decisions
  • Document rationale: future you needs to know why
  • Review outcomes: a decision isn't complete until its outcome is known
  • Link related decisions: build decision networks

Good Trigger Examples

  • "Document this decision: we're going with X"
  • "Help me decide between A and B"
  • "What decisions have we made about architecture?"
  • "Review our deployment decisions from last month"
  • "I decided to use Y instead of Z, record that"

Resources

references/

  • references/decision-templates.md: Variations for different decision types
  • references/analysis-frameworks.md: Tools for analyzing decisions
安全使用建议
This skill appears safe and does what it says: it helps you create, list, and template decision records locally. Before installing or running: 1) Note the docs show commands like 'decision create' but the shipped scripts are create-decision.sh and list-decisions.sh — either rename/create a wrapper or run the provided scripts directly. 2) Decide where records will be stored: by default scripts write to <skill>/data, or set DECISION_DATA_DIR to point elsewhere. 3) Review the scripts (they are short and readable) and make them executable if needed (chmod +x). 4) The skill performs no network access and requests no secrets, but it will write files on disk when you run the scripts — confirm you are comfortable with the storage location and permissions. 5) If you expect an automated 'decision analyze' command, note that analysis guidance exists in the reference docs but there is no dedicated analyze script implemented; you may need to run analysis manually or extend the skill.
功能分析
Type: OpenClaw Skill Name: decision-distiller Version: 1.0.0 The decision-distiller skill is a well-structured tool for documenting and analyzing decision-making processes. The shell scripts (create-decision.sh, list-decisions.sh) perform standard local file operations within a designated data directory, and the SKILL.md instructions provide clear, safe guidance for the AI agent without any signs of prompt injection or malicious intent.
能力评估
Purpose & Capability
Name and description match the provided artifacts: templates, guidance, and shell scripts that create and list decision records. The skill's functionality is local file creation/listing and analysis guidance, which fits the stated purpose.
Instruction Scope
SKILL.md stays within the decision-record domain and doesn't ask for unrelated files or credentials. One inconsistency: the SKILL.md command examples use a 'decision' CLI (e.g., 'decision create', 'decision analyze') but the shipped scripts are named create-decision.sh and list-decisions.sh; there is no wrapper that provides a 'decision' subcommand. That may confuse agents or users following the docs and could cause attempted execution of non-existent commands.
Install Mechanism
No install spec and no network downloads — the skill is instruction-only with bundled shell scripts and reference docs. Nothing is written to disk by an installer beyond what a user runs explicitly.
Credentials
No required environment variables or credentials. Scripts accept an optional DECISION_DATA_DIR env var to change where decision files are stored — this is reasonable and narrowly scoped.
Persistence & Privilege
always:false and no special privileges requested. Scripts create/read files under the skill's data directory by default and do not modify other skills or system-wide configuration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install decision-distiller
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /decision-distiller 触发
  4. 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.
元数据
Slug decision-distiller
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Decision Distiller 是什么?

Distill decision contexts, options, trade-offs, and outcomes into structured decision records. Use when the user is facing a choice, has made a decision they... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 238 次。

如何安装 Decision Distiller?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install decision-distiller」即可一键安装,无需额外配置。

Decision Distiller 是免费的吗?

是的,Decision Distiller 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Decision Distiller 支持哪些平台?

Decision Distiller 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 Distiller?

由 haidong(@harrylabsj)开发并维护,当前版本 v1.0.0。

💬 留言讨论