Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计通过

conflict-detection冲突检测

Agent Skill

conflict-detection 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。

总安装

186

周安装

8

GitHub Stars

2

下载量

65
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:conflict-detection(冲突检测)
来源仓库:https://github.com/doubleslashse/claude-marketplace
仓库路径:skills/conflict-detection
安装命令:
npx skills add https://github.com/doubleslashse/claude-marketplace --skill conflict-detection
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/doubleslashse/claude-marketplace --skill conflict-detection

简介

冲突检测用于识别需求、决策与计划间的潜在矛盾。

  • 适合在讨论阶段发现互斥目标或资源竞争问题。
  • 提供早期预警、停止流程与记录归因的机制。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。
  • 不自动解决冲突,需人工介入并保留决策依据。
  • conflict-detection 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Conflict Detection Skill

This skill provides patterns for detecting and resolving conflicts between requirements, decisions, and plans throughout the workflow.

Core Principles

  1. Early Detection: Catch conflicts as soon as they arise
  2. Immediate Stop: Halt workflow when conflict detected
  3. User Resolution: Never auto-resolve conflicts
  4. Documented Rationale: Record why resolutions were chosen

Conflict Types

Requirement vs Requirement

Two requirements that cannot both be satisfied.

Detection Point: DISCUSS phase Example: "User wants real-time updates AND offline mode"

Indicators:

  • Mutually exclusive features
  • Resource contention
  • Contradictory behaviors

Decision vs Decision

A new decision contradicts an earlier decision.

Detection Point: DISCUSS phase Example: "Earlier said 'no database', now requesting PostgreSQL"

Indicators:

  • Opposite stance on same topic
  • Changed constraints
  • Reversed priorities

New vs Existing Plan

Proposed work conflicts with pending tasks.

Detection Point: PLAN phase Example: "This change conflicts with TASK-003 in current ITEM-XXX.md"

Indicators:

  • Same files modified differently
  • Contradicting goals
  • Circular dependencies

Scope vs Timeline

Requested features exceed achievable scope.

Detection Point: DISCUSS phase Example: "Features exceed what's achievable in stated timeline"

Indicators:

  • Too many must-haves
  • Complex features with tight deadline
  • Dependencies on unavailable resources

Tech vs Requirement

Chosen technology cannot support a requirement.

Detection Point: PLAN phase Example: "Chosen tech doesn't support requested feature"

Indicators:

  • Technical limitations
  • Incompatible versions
  • Missing capabilities

Detection Protocol

On Each New Input

┌─────────────────────────────────────────────────────────────────┐
│              CONFLICT DETECTION FLOW                             │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  1. EXTRACT assertions from new input                           │
│     ├─ Requirements stated                                      │
│     ├─ Decisions made                                           │
│     ├─ Constraints imposed                                      │
│     └─ Priorities expressed                                     │
│                                                                 │
│  2. SCAN for contradictions                                     │
│     ├─ Compare against ITEM-XXX.md decisions                    │
│     ├─ Compare against ITEM-XXX.md requirements                 │
│     ├─ Compare against existing tasks in ITEM-XXX.md            │
│     └─ Check implicit assumptions                               │
│                                                                 │
│  3. IF CONFLICT DETECTED:                                       │
│     ├─ STOP workflow immediately                                │
│     ├─ Document conflict in ITEM-XXX.md                         │
│     ├─ Present conflict clearly to user                         │
│     └─ Wait for resolution before continuing                    │
│                                                                 │
│  4. IF NO CONFLICT:                                             │
│     └─ Continue workflow normally                               │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

Comparison Matrix

For each new assertion, check against:

Compare AgainstLooking For
Previous decisionsContradictions
Stated requirementsIncompatibilities
Technical choicesCapability gaps
Implicit assumptionsHidden conflicts
Pending tasksExecution conflicts

Conflict Documentation

In ITEM-XXX.md

## Conflicts

### CONFLICT-001: [Descriptive Title]
**Status**: ACTIVE | RESOLVED | DEFERRED
**Detected**: [TIMESTAMP]
**Type**: Requirement | Decision | Plan | Technical | Scope

**What conflicts:**
- A: [First item with reference]
- B: [Second item with reference]

**Why they conflict:**
[Clear explanation of why both cannot coexist]

**Resolution options:**
1. [Option 1 - description and implications]
2. [Option 2 - description and implications]
3. [Option 3 - description and implications]

**User choice**: [PENDING | Option N]
**Rationale**: [Why user chose this option]
**Resolved**: [TIMESTAMP]
**Actions taken**: [What changed as a result]

Automatic Triggers

The system MUST stop and present conflict when detecting:

Contradictory Statements

Trigger: "You said X earlier, now saying not-X"
Example: "Earlier you said no database needed, but now you're
         asking for PostgreSQL integration"

Mutually Exclusive Features

Trigger: "Feature A requires condition C, Feature B requires not-C"
Example: "Real-time sync requires constant internet, but you also
         want full offline functionality"

Resource Conflicts

Trigger: "Both items need exclusive access to same resource"
Example: "Two tasks both want to restructure the database schema
         in incompatible ways"

Timeline Impossibilities

Trigger: "Features exceed reasonable scope for constraints"
Example: "You're asking for 15 major features with a 2-week deadline"

Technical Incompatibilities

Trigger: "Technologies don't work together"
Example: "You want to use Library A and Library B, but they have
         conflicting peer dependencies"

Resolution Options

Option 1: Prioritize One

Choose one item over the other.

Resolution: Prioritize A over B
- A remains as requirement
- B is removed or deferred
- Rationale recorded

Option 2: Modify One

Adjust one item to remove conflict.

Resolution: Modify B to accommodate A
- A remains unchanged
- B is adjusted: [specific changes]
- Both now compatible

Option 3: Modify Both

Adjust both items to find middle ground.

Resolution: Adjust both for compromise
- A adjusted: [changes]
- B adjusted: [changes]
- Trade-off documented

Option 4: Accept with Trade-off

Keep both, document the trade-off.

Resolution: Accept both with trade-off
- Both remain
- Trade-off: [what is sacrificed]
- Risk documented

Option 5: Defer

Postpone resolution.

Resolution: Deferred
- Marked as DEFERRED
- Reason: [why can't resolve now]
- Blocker for: [what can't proceed]
- Revisit: [when/condition]

Cross-Plan Verification

Before creating tasks, verify:

## Cross-Plan Verification Checklist

**Against ITEM-XXX.md requirements:**
- [ ] All requirements have at least one task
- [ ] No tasks contradict requirements
- [ ] Priority order respected
- [ ] No requirements orphaned

**Against ITEM-XXX.md decisions:**
- [ ] Tasks align with recorded decisions
- [ ] No tasks contradict decisions
- [ ] Deferred items not accidentally included

**Against existing tasks in ITEM-XXX.md:**
- [ ] New tasks don't conflict with pending tasks
- [ ] File modifications don't overlap dangerously
- [ ] Dependency order preserved
- [ ] No circular dependencies created

**Against FLOW.md backlog:**
- [ ] Tasks fit within item scope
- [ ] No scope creep detected
- [ ] Dependencies on other items documented

**Conflicts found**: [List or "None"]

Integration Points

  • State Management: Document conflicts in ITEM-XXX.md
  • Exploration Tracking: Flag areas with detected conflicts
  • Interviewer Agent: Stop and present conflicts during discussion
  • Planner Agent: Verify cross-plan consistency
  • Workflow Orchestration: Block phase transitions on active conflicts

See resolution.md for detailed resolution strategies.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.34%
按下载量换算22

Claude

28.99%
按下载量换算19

Cursor

18.84%
按下载量换算12

Gemini CLI

9.71%
按下载量换算6

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills