Token导航 LogoToken导航

Agent Skill · 研究检索

negotiated-decision-framework(协商决策框架)

negotiated-decision-framework 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

negotiated-decision-framework 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为权限未标注;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 56,324。

总安装 456周安装 19GitHub Stars 公开资料未说明下载 152核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:negotiated-decision-framework(协商决策框架)
来源仓库:https://github.com/kimasplund/claude_cognitive_reasoning
仓库路径:skills/negotiated-decision-framework
安装命令:
npx skills add kimasplund/claude_cognitive_reasoning --skill "negotiated-decision-framework"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add kimasplund/claude_cognitive_reasoning --skill "negotiated-decision-framework"

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。支持基于关键词、任务场景或来源线索进行智能匹配与过滤。

通过 npx skills add kimasplund/claude_cognitive_reasoning --skill "negotiated-decision-framework" 安装。安装前应确认权限范围,注意潜在联网与文件操作风险。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/negotiated-decision-framework

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add kimasplund/claude_cognitive_reasoning --skill "negotiated-decisio…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    权限没有明确标注,第一次使用时只给一个无关紧要的任务,观察它到底读了哪些文件和网络。

常见问题

6 条

negotiated-decision-framework 怎么安装?

在终端执行 npx skills add kimasplund/claude_cognitive_reasoning --skill "negotiated-decision-framewor…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

negotiated-decision-framework 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

negotiated-decision-framework 需要什么权限?

权限级别没有明确标注。第一次使用时建议只给无关紧要的任务,观察它实际读写了哪些内容。

negotiated-decision-framework 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

negotiated-decision-framework 用的人多吗?

公开数据是累计安装 456 次,近一周安装 19 次,下载 152 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

negotiated-decision-framework 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
negotiated-decision-framework

协商决策框架 · 本页

456—权限未标注MIT未收录

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
negotiated-decision-framework
description
Multi-stakeholder coordination for decisions involving competing interests, different value systems, or organizational politics. Use when multiple parties must agree, when power dynamics affect decisions, or when consensus is required but perspectives diverge. Unlike DR (resolves conceptual tensions), NDF resolves stakeholder tensions.
license
MIT

Negotiated Decision Framework (NDF)

Purpose: Navigate multi-stakeholder decisions where different parties have legitimate but competing interests. NDF helps find decisions that stakeholders can live with, even if no one gets everything they want.

When to Use NDF

Use NDF when:

  • Multiple stakeholders must agree (or at least not block)
  • Different parties have different success criteria
  • Power dynamics or politics affect the decision
  • Past decisions created winners/losers who remember
  • "Best technical answer" won't get adopted due to stakeholder resistance
  • Need buy-in for implementation success

Don't use NDF when:

  • Single decision-maker with clear authority (use ToT)
  • Stakeholders agree on criteria (use ToT with shared criteria)
  • Conceptual tension, not stakeholder tension (use DR)
  • Time pressure prevents negotiation (use RTR, negotiate later)

NDF vs Other Patterns:

  • DR: Resolves conceptual/philosophical tensions (NDF: resolves people tensions)
  • ToT: Finds optimal given criteria (NDF: finds optimal given stakeholders)
  • BoT: Explores solution space (NDF: explores stakeholder space)

Core Methodology: ALIGN Framework

A - Analyze Stakeholder Landscape

Goal: Map who matters and what they care about

Process:

  1. Identify all stakeholders (not just vocal ones)
  2. Assess their power and interest
  3. Understand their underlying interests (not just stated positions)
  4. Map relationships and alliances

Stakeholder Mapping Template:

## Stakeholder Analysis

### Power-Interest Grid

|           | Low Interest | High Interest |
|-----------|--------------|---------------|
| **High Power** | Keep Satisfied | Key Players |
| **Low Power** | Monitor | Keep Informed |

### Stakeholder Profiles

#### [Stakeholder 1]
- **Role**: [Title/Function]
- **Power Level**: [High/Medium/Low]
- **Interest Level**: [High/Medium/Low]
- **Stated Position**: [What they say they want]
- **Underlying Interest**: [Why they want it - the deeper need]
- **Success Criteria**: [How they'll judge the decision]
- **Potential Blockers**: [What would make them oppose]
- **Potential Sweeteners**: [What would win their support]
- **Relationships**: [Allies, conflicts with other stakeholders]

#### [Stakeholder 2]
...

Interest Archeology: Don't just accept stated positions. Dig deeper:

  • "We need feature X" → Why? What problem does X solve?
  • "This must be done by Q2" → Why? What happens if Q3?
  • "We can't change the database" → Why? What's the actual constraint?

L - Locate Zones of Agreement

Goal: Find common ground before addressing differences

Process:

  1. Identify shared goals (even if approaches differ)
  2. Find overlapping interests
  3. Establish agreed constraints
  4. Build on areas of alignment

Agreement Mapping:

## Zones of Agreement

### Shared Goals
- [Goal that all stakeholders want]
- [Another shared goal]

### Overlapping Interests
| Interest | Stakeholders Who Share |
|----------|------------------------|
| [Interest 1] | A, B, C |
| [Interest 2] | A, D |
| [Interest 3] | B, C, D |

### Agreed Constraints
- [Constraint everyone accepts]
- [Another constraint]

### Foundation Statement
"We all agree that [shared goal], within [constraints],
and we all want [overlapping interest]."

Use agreement zones to:

  • Frame discussions positively
  • Remind stakeholders of shared purpose when tensions rise
  • Build solutions that honor common ground first

I - Identify Irreducible Conflicts

Goal: Understand where genuine conflicts exist (not all conflicts are real)

Conflict Classification:

TypeDescriptionResolution Approach
False ConflictMisunderstanding, same goal different wordsClarify, reframe
Resource ConflictCompeting for same limited resourceExpand pie, prioritize, take turns
Value ConflictDifferent fundamental valuesAcknowledge, find higher-order value
Interest ConflictDifferent parties want different outcomesTrade, compromise, or escalate
Relational ConflictHistory/politics, not the actual issueAddress relationship separately

Conflict Analysis Template:

## Conflict Analysis

### Conflict 1: [Name]
- **Parties**: [Stakeholder A] vs [Stakeholder B]
- **Type**: [False/Resource/Value/Interest/Relational]
- **A's Position**: [What A wants]
- **B's Position**: [What B wants]
- **Underlying Interests**:
  - A really needs: [Deeper interest]
  - B really needs: [Deeper interest]
- **Compatible?**: [Can both interests be met?]
- **Resolution Path**: [How to address]

Key Insight: Many conflicts are about HOW, not WHAT. If underlying interests are compatible, the conflict is solvable.


G - Generate Integrative Options

Goal: Create solutions that satisfy multiple stakeholders' interests

Integrative Strategies:

  1. Expand the Pie: Find resources to satisfy everyone

- "Can we get more budget/time/people?" - "Can we do both sequentially instead of choosing?"

  1. Trade Across Issues: Give on low-priority, get on high-priority

- "You care more about X, we care more about Y - swap?" - "We'll accept your timeline if you accept our approach"

  1. Add Issues: Bring in new elements to enable trades

- "What if we also addressed Z, which you care about?" - "Can we package this with the other decision?"

  1. Compensate: Make up for losses elsewhere

- "You lose on this, but gain on that" - "This time your priority, next time ours"

  1. Reframe: Find higher-order framing everyone can support

- "We all want customer success - here's how this achieves it" - "This isn't A vs B, it's achieving C"

Option Generation Template:

## Integrative Options

### Option 1: [Name]
- **How it works**: [Description]
- **Satisfies [Stakeholder A]**: [How it meets their interest]
- **Satisfies [Stakeholder B]**: [How it meets their interest]
- **Trade-offs**: [What each party gives up]
- **Feasibility**: [Can we actually do this?]

### Option 2: [Name]
...

### Comparison Matrix
| Option | Stakeholder A | Stakeholder B | Stakeholder C | Feasibility |
|--------|---------------|---------------|---------------|-------------|
| Opt 1  | [Score 1-5]   | [Score 1-5]   | [Score 1-5]   | [High/Med/Low] |
| Opt 2  | [Score 1-5]   | [Score 1-5]   | [Score 1-5]   | [High/Med/Low] |

N - Negotiate Commitment

Goal: Move from options to agreement with genuine buy-in

Negotiation Principles:

  1. BATNA Awareness: Know each party's Best Alternative To Negotiated Agreement

- If their BATNA is better than your offer, they won't agree - Improve your offer or worsen their BATNA (ethically)

  1. Commitment Levels: Not all agreement is equal

- Comply: Will do it if required (weak) - Accept: Can live with it (moderate) - Endorse: Will support it (strong) - Champion: Will advocate for it (strongest)

  1. Legitimate Process: Stakeholders accept outcomes better when process felt fair

- Were they heard? Were their interests considered? - Is the decision-making process transparent?

Commitment Template:

## Negotiated Agreement

### Decision Summary
[The agreed decision in clear terms]

### Stakeholder Commitments
| Stakeholder | Commitment Level | What They Get | What They Give |
|-------------|------------------|---------------|----------------|
| A | [Comply/Accept/Endorse/Champion] | [Their gain] | [Their concession] |
| B | [Comply/Accept/Endorse/Champion] | [Their gain] | [Their concession] |

### Conditions and Contingencies
- [Condition 1]: If [X], then [Y]
- [Review point]: Revisit at [date/milestone]

### Dispute Resolution
If disagreement arises: [How to handle]

Power Dynamics Navigation

When Power is Unequal:

SituationStrategy
You have low powerBuild coalition, appeal to higher values, make strong case
You have high powerUse power sparingly, seek genuine input, explain reasoning
Power is unclearClarify decision rights before negotiating
Power is contestedEscalate to clarify, or negotiate decision process first

Political Patterns to Watch:

  1. End-Run: Stakeholder goes around you to higher authority

- Prevention: Keep sponsors informed, address concerns early

  1. Pocket Veto: Stakeholder agrees but doesn't implement

- Prevention: Explicit commitment, visible milestones

  1. Relitigating: Stakeholder reopens "settled" decisions

- Prevention: Clear closure process, document agreements

  1. Coalition Building: Stakeholders ally against you

- Response: Build your own coalition, address their concerns


Special Scenarios

Scenario: Consensus Required but Not Achievable

When true consensus isn't possible:

  1. Consent-based: "Can everyone live with this?" (not "Does everyone love it?")
  2. Disagree and Commit: Document disagreement, commit to decision
  3. Conditional Agreement: "I'll support this if [condition]"
  4. Escalation: Transparent escalation to decision-maker with recommendation

Scenario: Hidden Agendas

When you suspect unstated interests:

  1. Ask "What would success look like for you?"
  2. Observe what they fight for vs. what they say
  3. Consider their incentives and pressures
  4. Test hypotheses about real interests

Scenario: Past Wounds

When history poisons current negotiation:

  1. Acknowledge the history explicitly
  2. Separate the people from the problem
  3. Focus on future, not past blame
  4. Consider symbolic gestures of recognition

Common Mistakes

  1. Assuming Single Decision-Maker: Not recognizing stakeholder complexity

- Fix: Always do stakeholder analysis first

  1. Positional Bargaining: Arguing positions instead of interests

- Fix: Ask "Why?" five times to find real interest

  1. Ignoring Relationship: Focusing only on this decision

- Fix: Consider ongoing relationship, not just this transaction

  1. Winner-Take-All: Trying to maximize one party's outcome

- Fix: Seek integrative solutions that create value for all

  1. Premature Commitment: Locking in before exploring options

- Fix: Generate options before evaluating them

  1. Ignoring Implementation: Agreement that can't be executed

- Fix: Include implementers in negotiation, test feasibility


Integration with Other Patterns

Before NDF:

  • BoT: Explore full solution space before stakeholder negotiation
  • DR: Resolve conceptual tensions first, then negotiate

After NDF:

  • ToT: Optimize implementation details within agreed framework
  • AR: Stress-test agreed solution before full commitment

Parallel with NDF:

  • RTR: If time pressure, do quick stakeholder check, negotiate later
  • SRC: Trace implementation steps after agreement reached

Output Template

# NDF Decision Record: [Decision Topic]

## Stakeholder Landscape
[Summary of key stakeholders and interests]

### Key Stakeholders
| Stakeholder | Interest | Power | Support Level |
|-------------|----------|-------|---------------|
| [Name] | [What they want] | [H/M/L] | [Champion/Endorse/Accept/Oppose] |

## Zones of Agreement
- [Shared goal 1]
- [Shared goal 2]

## Conflicts Addressed
| Conflict | Type | Resolution |
|----------|------|------------|
| [Conflict 1] | [Type] | [How resolved] |

## Negotiated Solution
[Description of agreed solution]

### Value Distribution
| Stakeholder | What They Get | What They Give |
|-------------|---------------|----------------|
| [A] | [Gain] | [Concession] |
| [B] | [Gain] | [Concession] |

## Commitments and Conditions
- [Commitment 1]
- [Condition/Contingency]

## Implementation Notes
[How to execute with stakeholder buy-in]

## Confidence: [X]%
[Based on commitment strength and alignment quality]

Version History

V1.0 (Current):

  • Initial release
  • ALIGN framework (Analyze, Locate, Identify, Generate, Negotiate)
  • Stakeholder mapping and interest analysis
  • Integrative bargaining strategies
  • Power dynamics navigation
  • Special scenario handling

平台分布

Antigravity

29.83%
按下载量换算45

Claude Code

25.73%
按下载量换算39

Gemini CLI

17.77%
按下载量换算27

OpenCode

12.15%
按下载量换算18

windsurf

8.02%
按下载量换算12

github-copilot

3.72%
按下载量换算6

安全审计

暂无安全审计结果可展示。

权限和风险

权限未标注

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills