Token导航 LogoToken导航

Agent Skill · 研究检索

mediation-analysis(中介分析)

mediation-analysis 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。

mediation-analysis 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,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 55,945。

总安装 466周安装 20GitHub Stars 103下载 163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
unknown

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:mediation-analysis(中介分析)
来源仓库:https://github.com/borghei/claude-skills
仓库路径:skills/mediation-analysis
安装命令:
npx skills add https://github.com/borghei/claude-skills --skill mediation-analysis
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。

skills.shnpx skills
npx skills add https://github.com/borghei/claude-skills --skill mediation-analysis

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。

mediation-analysis 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景定位候选结果。适用于需要快速获取信息或线索的场景,如研究分析或数据筛选。通过关键词、来源仓库或任务描述触发检索,返回结构化候选列表。

安装前需确认权限范围,注意是否会触发联网或文件操作,建议检查维护状态。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/mediation-analysis

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 https://github.com/borghei/claude-skills --skill mediation-analys…;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

mediation-analysis 怎么安装?

在终端执行 npx skills add https://github.com/borghei/claude-skills --skill mediation-analysis。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

mediation-analysis 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。

mediation-analysis 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

mediation-analysis 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

mediation-analysis 用的人多吗?

公开数据是累计安装 466 次,近一周安装 20 次,下载 163 次,GitHub 103 星。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。

mediation-analysis 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 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
mediation-analysis

中介分析 · 本页

466103只读未明确通过

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

⚠️ EXPERIMENTAL — This skill is provided for educational and informational purposes only. It does NOT constitute legal advice. All responsibility for usage rests with the user. Consult qualified legal professionals before acting on any output.

Mediation Analysis

Production-ready framework for analyzing disputes and preparing mediation strategy. Covers the full cycle from dispute assessment through settlement calculation, interest mapping, and mediation readiness.


Table of Contents


Operating Modes

Mode 1: Guided Information Gathering

Use when starting from scratch without structured materials.

Step 1 -- Dispute Overview:

  • Who are the parties? (names, roles, relationship)
  • What is the dispute about? (summary in neutral terms)
  • When did the dispute arise? (timeline of key events)
  • What is the current status? (pre-litigation, filed, discovery, trial date)

Step 2 -- Positions and Claims:

  • What does each party want? (stated positions)
  • What are the claimed amounts? (monetary and non-monetary)
  • What evidence supports each side?
  • What are the weaknesses in each side's case?

Step 3 -- Context and Constraints:

  • Is there an ongoing relationship? (employment, commercial, family)
  • Are there power imbalances? (resources, information, leverage)
  • Are there time pressures? (deadlines, statute of limitations)
  • What has been tried so far? (direct negotiation, prior mediation)

Mode 2: Direct Analysis

Use when dispute materials are already available (pleadings, correspondence, statements).

Provide the materials and specify which analysis sections are needed. The framework will extract the structured analysis from the raw materials.


Tools

Dispute Analyzer

Extracts structured dispute data from text descriptions.

# Analyze a dispute description
python scripts/dispute_analyzer.py --input dispute.txt

# Analyze with JSON output
python scripts/dispute_analyzer.py --input dispute.txt --json

# Analyze inline text
python scripts/dispute_analyzer.py --text "Party A claims breach of contract for failure to deliver..."

# Save structured analysis
python scripts/dispute_analyzer.py --input dispute.txt --output analysis.json

Settlement Calculator

Calculates BATNA, WATNA, ZOPA, and settlement scenarios.

# Calculate from parameters file
python scripts/settlement_calculator.py --input params.json

# Calculate with JSON output
python scripts/settlement_calculator.py --input params.json --json

# Quick inline calculation
python scripts/settlement_calculator.py \
  --claimed 500000 \
  --litigation-cost-a 80000 \
  --litigation-cost-b 120000 \
  --probability 0.65 \
  --time-to-trial 18

# Save settlement analysis
python scripts/settlement_calculator.py --input params.json --output settlement.json

Core Analysis Framework

The analysis produces 6 sections. Each section builds on the previous.

Section 1: Case Summary

Write a neutral chronological summary covering:

ElementDescription
PartiesNames, roles, and relationship
TimelineKey events in chronological order
Dispute triggerThe event that escalated to a dispute
Current statusProcedural posture (pre-suit, filed, discovery)
Prior resolution attemptsWhat has been tried

Neutrality check: The summary should be acceptable to both parties. Avoid characterizing conduct as "wrong" or "unreasonable."

Section 2: Issues in Dispute

For each issue, document:

ComponentDescription
Issue statementNeutral framing of the disputed question
Party A positionWhat Party A asserts and why
Party B positionWhat Party B asserts and why
Key evidenceEvidence supporting each side
Strength assessmentStrong / Moderate / Weak for each side
Legal basisApplicable law, contract terms, or principles

Section 3: Underlying Interests Analysis

Move beyond positions to interests. See detailed section below.

Section 4: Legal Analysis

Per-issue assessment of legal merits. See detailed section below.

Section 5: Mediation Strategy and Settlement Directions

BATNA/WATNA, ZOPA, and settlement scenarios. See detailed section below.

Section 6: Mediation Readiness Checklist

ItemStatusNotes
All parties agreed to mediate
Mediator selected and confirmed
Decision-makers attending or available
Key documents exchanged or available
Opening statement prepared
Settlement authority established
BATNA/WATNA analysis complete
Non-monetary interests identified
Creative options brainstormed
Authority limits clarified with client

Underlying Interests Analysis

Interests are the needs, concerns, and motivations behind stated positions.

Interest Categories

CategoryDescriptionExamples
LegalRights, entitlements, obligationsContract rights, statutory claims, precedent
CommercialBusiness and financial concernsRevenue, costs, market position, reputation
RelationalRelationship preservationOngoing business, employment, community ties
EmotionalPersonal feelings and valuesFairness, respect, acknowledgment, vindication
ProceduralHow the process unfoldsSpeed, privacy, control, voice, transparency

Interest Mapping

For each party, map interests by category and priority:

PartyInterestCategoryPriorityCompatible?
APreserve business reputationCommercialHighYes -- shared
ARecover financial lossesLegal/CommercialHighNegotiable
BAvoid setting precedentLegalHighNegotiable
BMaintain relationship with ARelationalMediumYes -- shared

Shared and Compatible Interests

Identify interests both parties share or that do not conflict:

  • Shared: Both want confidentiality, speed, cost control
  • Compatible: A wants acknowledgment, B wants no public admission -- private acknowledgment possible
  • Conflicting: A wants maximum payment, B wants minimum payment -- negotiation zone needed

Barriers to Resolution

BarrierDescriptionMitigation
Reactive devaluationOffers seem less attractive because they come from the other sideHave mediator propose options
AnchoringFirst number distorts all subsequent negotiationUse objective criteria to anchor
Loss aversionParties feel losses more than equivalent gainsFrame in terms of gains vs current state
Principal-agentParty's representative may have different interestsEnsure decision-makers participate
Information asymmetryOne party knows more than the otherStructured disclosure through mediator

Legal Analysis

For each disputed issue, assess:

FactorAssessment
Applicable lawStatute, regulation, contract term, or common law
Strength of claimStrong (>70%) / Moderate (40-70%) / Weak (<40%)
Key uncertaintiesFactual disputes, legal ambiguities, evidentiary gaps
Likely trial outcomeBest case, worst case, most likely
Damages rangeIf claimant prevails, likely award range
Costs to trialAttorney fees, expert fees, opportunity costs per party
Time to resolutionMonths/years to trial and potential appeal

Settlement Strategy

BATNA / WATNA Analysis

MetricParty AParty B
Best Alternative (BATNA)Win at trial, recover full claim + costsWin at trial, pay nothing + recover costs
Worst Alternative (WATNA)Lose at trial, recover nothing, pay own costsLose at trial, pay full claim + costs
Most Likely AlternativePartial recovery minus litigation costsPartial liability minus litigation costs
Litigation cost estimate$X over Y months$X over Y months
Net expected value(Probability x Award) - Litigation costs-(Probability x Award) - Litigation costs

ZOPA Identification

The Zone of Possible Agreement exists when Party A's minimum acceptable settlement is less than Party B's maximum they would pay.

Party A minimum = Expected trial value - litigation costs - risk discount
Party B maximum = Expected trial liability + litigation costs + risk premium

ZOPA exists when: A minimum < B maximum
ZOPA range: [A minimum ... B maximum]

Settlement Scenarios

ScenarioDescriptionWhen Appropriate
Straightforward CompromiseSplit the difference on monetary claimsSimple disputes with clear monetary value
Interest-Based SolutionAddress underlying interests beyond moneyOngoing relationships, non-monetary concerns
Package DealBundle monetary and non-monetary elementsComplex disputes with multiple issues and interests

Reference Guides

GuidePathDescription
Mediation Processreferences/mediation_process.md12 stages of mediation with roles and techniques
Negotiation Conceptsreferences/negotiation_concepts.mdBATNA, WATNA, ZOPA, interest-based negotiation, barriers

Workflows

Workflow 1: Full Mediation Preparation

  1. Gather dispute information (Mode 1 or Mode 2).
  2. Run scripts/dispute_analyzer.py on available materials.
  3. Complete the 6-section Core Analysis Framework.
  4. Run scripts/settlement_calculator.py with dispute parameters.
  5. Prepare opening statement and settlement proposals.
  6. Complete Mediation Readiness Checklist.
  7. Validation: All 6 sections complete, BATNA/ZOPA calculated, proposals prepared.

Workflow 2: Quick Settlement Range

  1. Identify claimed amount, litigation costs, and success probability.
  2. Run scripts/settlement_calculator.py with parameters.
  3. Review ZOPA range and three scenarios.
  4. Adjust parameters for sensitivity analysis.
  5. Validation: Settlement range established with supporting rationale.

Workflow 3: Multi-Party Mediation

  1. Map all parties and their relationships.
  2. Run dispute analysis for each bilateral relationship.
  3. Identify coalition possibilities and shared interests.
  4. Calculate settlement ranges for each party pair.
  5. Design package deals that address all parties' core interests.
  6. Validation: Each party pair analyzed, coalitions mapped, package options developed.

Troubleshooting

ProblemLikely CauseResolution
ZOPA appears negativeParties' expectations unrealistic or litigation costs understatedReality-test each party's BATNA; increase cost estimates
Cannot identify interestsParties stuck on positionsUse "why" questions; explore consequences of winning/losing
Power imbalance distorting negotiationResource or information asymmetryRecommend process adjustments; structured information sharing
Decision-maker absentRepresentative lacks authorityAdjourn until decision-maker available; confirm authority in advance
Emotional barriers dominantUnresolved relational issuesAddress emotional interests first; consider apology or acknowledgment
Multi-party complexityToo many bilateral dynamicsBreak into sub-mediations; use single-text procedure

Success Criteria

CriterionTarget
Dispute issues identifiedAll contested issues listed with positions
Interests mappedAt least 3 interests per party, categorized
Legal strength assessedEach issue rated with rationale
BATNA/WATNA calculatedBoth parties' alternatives quantified
ZOPA identifiedSettlement range established or confirmed negative
Settlement scenariosMinimum 3 scenarios with rationale
Readiness checklistAll items addressed before mediation

Scope & Limitations

In scope: Dispute analysis, interest mapping, settlement calculation, mediation preparation, negotiation strategy.

Out of scope: Acting as mediator, providing legal advice, predicting judicial outcomes with certainty, drafting settlement agreements, representing parties.

Disclaimer: This skill provides an analytical framework for mediation preparation. It does not constitute legal advice. Settlement calculations are estimates based on inputs provided and should be validated by qualified counsel.


Anti-Patterns

Anti-PatternWhy It FailsBetter Approach
Positional bargaining onlyFocuses on what parties demand, ignoring why they want it; leaves value on the tableMap interests first, then generate options that satisfy underlying needs
Ignoring litigation costs in settlement mathParties anchor on the claim amount without factoring in costs to pursue it; produces unrealistic expectationsAlways include full litigation costs (fees, time, opportunity cost) in BATNA calculation
Assuming equal bargaining powerPower imbalances distort negotiation; weaker party may accept unfavorable terms under pressureIdentify imbalances early; recommend process protections (separate caucuses, information sharing, independent advice)
Skipping emotional interestsEmotional needs (respect, acknowledgment, fairness) often drive dispute more than money; ignoring them produces impasseInclude emotional and relational interests in the analysis alongside legal and commercial interests

Tool Reference

ToolInputOutputUse Case
dispute_analyzer.pyDispute description textStructured analysis with parties, issues, interests, timelineFirst-pass dispute structuring
settlement_calculator.pyDispute parameters (amounts, costs, probability)BATNA/WATNA, ZOPA, 3 settlement scenariosQuantitative settlement range analysis

平台分布

Codex

34.73%
按下载量换算57

Claude

27.68%
按下载量换算45

Cursor

20.87%
按下载量换算34

Gemini CLI

10.31%
按下载量换算17

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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