agentleFS
Eleven-MEleven-M/flowmind/skills/requirement-analyst/SKILL.md

requirement-analyst

Skill1 starsChanged 3 months agoMITView on GitHub

Requirement analyst skill for FlowMind. Six-dimensional analysis: historical design principles, iteration rationale, extensibility, market roadmap, requirement-code deviation, and upgrade vulnerabilities.

The file

Files
SKILL.md

Requirement Analyst Skill

Comprehensive requirement analysis combining code reality with requirement intent. Acts as a senior requirement analyst (需求分析师) evaluating from six dimensions.

Features

Historical Design Principle Evaluation

  • Evaluate why historical designs were made
  • Assess design validity in current context
  • Identify design debt and knowledge gaps

Iteration Rationale Assessment

  • Analyze iteration driving forces
  • Evaluate iteration quality and pace
  • Identify anomalous iterations (rollback, rework, over-design)

Extensibility Assessment

  • Development extensibility (modularity, interfaces, configurability)
  • Requirement upgrade extensibility (data model, API compatibility)
  • User growth extensibility (performance, caching, horizontal scaling)

Market Roadmap Planning

  • Feature coverage analysis
  • Requirement trend analysis
  • Short/mid/long-term development roadmap

Requirement-Code Deviation Analysis

  • Feature gaps (required but not implemented)
  • Over-implementation (implemented but not required)
  • Understanding gaps (implementation doesn't match intent)
  • Documentation lag (code changed, docs not updated)

Upgrade Vulnerability Identification

  • Data model fragility
  • API incompatibility risks
  • Hardcoded traps
  • Test blind spots
  • Dependency coupling

Trigger Patterns

"需求分析", "需求评审", "需求评估"
"设计评审", "设计评估", "设计原理分析"
"迭代评估", "迭代分析", "迭代回顾"
"扩展性评估", "扩展性分析", "架构评估"
"市场规划", "产品规划", "发展路线"
"需求偏差", "需求偏差分析", "代码与需求对比"
"升级风险", "升级漏洞", "技术债务评估"
"全面分析", "需求分析师"
"requirement analysis", "design review"
"iteration review", "extensibility assessment"
"market roadmap", "requirement deviation"
"upgrade risk", "technical debt"

Output Format

Comprehensive Report

┌─────────────────────────────────────────────────────┐
│ Requirement Analysis Report                         │
├─────────────────────────────────────────────────────┤
│ Project: {project_name}                             │
│ Analysis Scope: {dimensions}                        │
│ Overall Score: {score}/100                          │
├─────────────────────────────────────────────────────┤
│ Dimension Scores:                                   │
│ • Historical Design:  {score}/100                   │
│ • Iteration Rationale: {score}/100                  │
│ • Extensibility:       {score}/100                  │
│ • Market Roadmap:      {score}/100                  │
│ • Req-Code Deviation:  {score}/100                  │
│ • Upgrade Vulnerability: {score}/100                │
├─────────────────────────────────────────────────────┤
│ Key Findings:                                       │
│ • {finding_1}                                       │
│ • {finding_2}                                       │
├─────────────────────────────────────────────────────┤
│ Priority Actions:                                   │
│ P0: {action_1}                                      │
│ P1: {action_2}                                      │
│ P2: {action_3}                                      │
└─────────────────────────────────────────────────────┘

Single Dimension Report

┌─────────────────────────────────────────────────────┐
│ {Dimension} Assessment Report                       │
├─────────────────────────────────────────────────────┤
│ Score: {score}/100                                  │
│ Status: {status}                                    │
├─────────────────────────────────────────────────────┤
│ Findings:                                           │
│ 1. {finding} - {severity}                           │
│ 2. {finding} - {severity}                           │
├─────────────────────────────────────────────────────┤
│ Recommendations:                                    │
│ • {recommendation}                                  │
└─────────────────────────────────────────────────────┘

Analysis Dimensions Detail

Dimension 1: Historical Design Principles

ItemDescription
Design IntentWhat problem was the design solving?
Design BasisWhat data/assumptions/constraints was it based on?
Current ValidityIs the design still valid today?
Design DebtWhich decisions have become technical debt?
Knowledge TransferIs design knowledge effectively preserved?

Dimension 2: Iteration Rationale

ItemDescription
Driving ForceDemand-driven, tech-driven, or market-driven?
Evolution PathIs the iteration path logical?
Iteration QualityClean implementation or leftover debt?
Iteration PaceIs the frequency reasonable?
Anomalous IterationsRollbacks, reworks, over-design?

Dimension 3: Extensibility

CategoryAssessment Items
DevelopmentModularity, interface abstraction, configurability, readability, test coverage
Requirement UpgradeData model extensibility, API compatibility, business rule flexibility, state machine extension
User GrowthPerformance bottlenecks, data volume capacity, caching strategy, horizontal scaling, degradation

Dimension 4: Market Roadmap

ItemDescription
Feature CoverageWhat's covered vs. uncovered?
Requirement TrendsHistorical trends and predictions
Technology TrendsCurrent stack evolution direction
Competitive PositioningGaps vs. industry standards
Short-term (1-3mo)Immediate action items
Mid-term (3-6mo)Strategic initiatives
Long-term (6-12mo)Vision and goals

Dimension 5: Requirement-Code Deviation

Deviation TypeDescription
Feature GapRequired but not implemented
Over-implementationImplemented but not required
Understanding GapImplementation doesn't match intent
Technical CompromiseRequirement degraded due to tech limits
Requirement CreepRequirement silently expanded
Requirement ShrinkRequirement silently reduced
Documentation LagCode changed, docs not updated

Dimension 6: Upgrade Vulnerability

Vulnerability TypeDescription
Data Model FragilitySchema changes may cause migration issues
API IncompatibilityInterface changes may break clients
Hardcoded TrapsHardcoded rules need code changes to modify
State Machine DeadlockState transitions may create illegal states
Performance BottleneckFeature upgrades amplify existing perf issues
Test Blind SpotsUntested modules have highest upgrade risk
Dependency CouplingTight coupling causes cascade changes

Parallel Execution(全局唯一 → 维度各自并行 → 结果合并唯一)

用户要求 ≥3 个维度的综合分析时,六维度互相独立、读不同来源,按维度并行:全局唯一(一份综合报告、一个总评分,主 agent 汇总)→ 每维度一个只读单元并行分析(历史设计原理 / 迭代演进 / 扩展性 / 市场路线 / 需求偏差 / 升级漏洞,各自只读对应来源,返回该维度模板段落不展开长文)→ 合并唯一(主 agent 交叉验证冲突项并调和,产出唯一报告;子单元不出总评分、不单独沉淀知识)。并发 ≤ 4,六维全开时分两批。单一维度请求保持串行。

宿主支持并行子 agent 时按维度并行派发;flowmind 运行时内退化为串行逐维度执行,输出结构不变。

Learning Integration

This skill supports FlowMind learning:

  • Analysis Focus: Learns which dimensions you care about most
  • Severity Threshold: Learns your risk tolerance
  • Report Format: Learns preferred report detail level

Examples

Example 1: Full Requirement Analysis

User: 对当前项目做一次全面需求分析

FlowMind:
┌─────────────────────────────────────────────────────┐
│ Requirement Analysis Report                         │
├─────────────────────────────────────────────────────┤
│ Project: order-service                              │
│ Analysis Scope: All 6 dimensions                    │
│ Overall Score: 72/100                               │
├─────────────────────────────────────────────────────┤
│ Dimension Scores:                                   │
│ • Historical Design:  75/100                        │
│ • Iteration Rationale: 80/100                       │
│ • Extensibility:       65/100                       │
│ • Market Roadmap:      70/100                       │
│ • Req-Code Deviation:  68/100                       │
│ • Upgrade Vulnerability: 62/100                     │
├─────────────────────────────────────────────────────┤
│ Key Findings:                                       │
│ • Order state machine lacks extensibility           │
│ • 3 features have requirement-code deviation        │
│ • Redis caching strategy needs redesign for scale   │
├─────────────────────────────────────────────────────┤
│ P0: Fix state machine deadlocks in refund flow      │
│ P1: Align 3 deviated features with requirements     │
│ P2: Redesign Redis caching for 10x user growth      │
└─────────────────────────────────────────────────────┘

Example 2: Upgrade Risk Assessment

User: 评估一下需求升级的风险

FlowMind:
┌─────────────────────────────────────────────────────┐
│ Upgrade Vulnerability Report                        │
├─────────────────────────────────────────────────────┤
│ Vulnerabilities Found: 8                            │
│ • HIGH: 2                                           │
│ • MEDIUM: 3                                         │
│ • LOW: 3                                            │
├─────────────────────────────────────────────────────┤
│ 🔴 HIGH: Order status enum hardcoded (OrderService) │
│    Impact: All order operations                     │
│    Fix: Extract to configuration                    │
│                                                    │
│ 🔴 HIGH: No index on order_items.product_id         │
│    Impact: Query performance at scale               │
│    Fix: Add composite index                         │
│                                                    │
│ 🟡 MEDIUM: Payment API v1 deprecated                │
│    Impact: Payment processing                       │
│    Fix: Migrate to v2 API                           │
└─────────────────────────────────────────────────────┘

Configuration

{
  "requirement-analyst": {
    "dimensions": {
      "historicalDesign": true,
      "iterationRationale": true,
      "extensibility": true,
      "marketRoadmap": true,
      "reqCodeDeviation": true,
      "upgradeVulnerability": true
    },
    "scoringWeights": {
      "historicalDesign": 0.15,
      "iterationRationale": 0.15,
      "extensibility": 0.20,
      "marketRoadmap": 0.15,
      "reqCodeDeviation": 0.15,
      "upgradeVulnerability": 0.20
    },
    "reportFormat": "detailed"
  }
}

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.