Token导航 LogoToken导航

Agent Skill · 研究检索

business-analyst(商业分析师)

business-analyst 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。

business-analyst 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 50,973。

总安装 599周安装 24GitHub Stars 公开资料未说明下载 194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:business-analyst(商业分析师)
来源仓库:https://github.com/duc01226/easyplatform
仓库路径:skills/business-analyst
安装命令:
npx skills add duc01226/easyplatform --skill "business-analyst"
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 duc01226/easyplatform --skill "business-analyst"

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。

business-analyst 用于发现并安装 AI 代理的技能。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。

通过 github 安装,命令为 npx skills add duc01226/easyplatform --skill "business-analyst"。使用前需确认权限范围和维护状态,注意是否会触发联网或文件读写操作。

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/business-analyst

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 duc01226/easyplatform --skill "business-analyst";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

business-analyst 怎么安装?

在终端执行 npx skills add duc01226/easyplatform --skill "business-analyst"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

business-analyst 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。

business-analyst 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。

business-analyst 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。

business-analyst 用的人多吗?

公开数据是累计安装 599 次,近一周安装 24 次,下载 194 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。

business-analyst 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。
  • 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

  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

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
business-analyst

商业分析师 · 本页

599—只读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

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
AI Mistake Prevention — Failure modes to avoid on every task: - Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. - Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. - Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. - Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. - When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. - Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. - Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. - Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. - Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. - Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Quick Summary

Goal: Refine requirements into actionable user stories with BDD acceptance criteria and business rule traceability.

Workflow:

  1. Extract Business Rules — Locate feature docs, extract BR-{MOD}-XXX rules, reference in stories
  2. Investigate Entities — Load feature docs, extract domain model and query patterns
  3. Write User Stories — Use "As a / I want / So that" format, validate with INVEST criteria
  4. Define Acceptance Criteria — BDD format (GIVEN/WHEN/THEN), gap analysis for missing scenarios

Key Rules:

  • Always reference existing business rules from docs/business-features/ before creating new ones
  • User stories must pass INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable)
  • Include entity context and related domain model in every story
  • MUST ATTENTION include story_points and complexity in all PBI/story outputs

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

  • docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (content auto-injected by hook — check for [Injected:...] header before reading)

Business Analyst Assistant

Help Business Analysts refine requirements into actionable user stories with clear acceptance criteria using BDD format.


Business Rules Extraction (Project Domain)

When refining domain-related PBIs, automatically extract and reference existing business rules.

Step 1: Locate Related Feature Docs

Dynamic Discovery:

  1. Run: Glob("docs/business-features/{module}/detailed-features/*.md") for feature docs
  2. Or: Glob("docs/business-features/{module}/detailed-features/**/*.md") for nested features

From PBI frontmatter or module detection:

  1. Check module field
  2. Identify related feature from related_features list
  3. Read discovered feature documentation

Step 2: Extract Existing Business Rules

From feature doc "Business Rules" section:

  • Format: BR-{MOD}-XXX: Description
  • Example: BR-GRO-001: Goals must have measurable success criteria
  • Note conflicting rules if found

Step 3: Add to User Story

Include section:

## Related Business Rules

**From Feature Docs:**

- BR-GRO-001: Goals must have measurable success criteria
- BR-GRO-005: Only goal owner and manager can edit progress

**New Business Rules (if applicable):**

- BR-GRO-042: {New rule description}

**Conflicts/Clarifications:**

- {Note any conflicts with existing rules}

Token Budget

Target 8-12K tokens total (validated decision: prefer completeness):

  • Module README: 2K tokens
  • Full feature doc sections: 3-5K tokens per feature
  • Multi-module support: Load all detected modules (may increase total)

Entity Domain Investigation

When refining domain-related PBIs, investigate related entities using feature docs.

Step 1: Load Feature Doc

Glob("docs/business-features/{module}/detailed-features/*.md")

Select file matching feature from PBI context.

Step 2: Extract Domain Model

From ## Domain Model section (Section 5):

  • Entity inheritance: Entity: BaseClass
  • Property types: Property: Type
  • Navigation: NavigationProperty: List<Related>
  • Computed: Property: Type (computed: logic)

Step 3: Correlate with Codebase

From ## File Locations section:

  1. Read entity source file
  2. Verify properties match documentation
  3. Note any undocumented properties (flag for doc update)

Step 4: Identify Query Patterns

From ## Key Expressions section:

  • Static expressions for common queries
  • Validation rules with BR-* references

Step 5: Add to User Story

Include entity context:

## Entity Context

**Primary:** {Entity} - {description}
**Related:** {Entity1}, {Entity2}
**Key Queries:** {ExpressionName}
**Source:** {path}

This ensures implementation uses correct entities and patterns.


Core Capabilities

1. Requirements Refinement

  • Transform vague requests into specific requirements
  • Identify missing information and ambiguities
  • Document assumptions and constraints

2. User Story Writing

Format
As a {user role/persona}
I want {goal/desire}
So that {benefit/value}
INVEST Criteria
  • Independent: No dependencies on other stories
  • Negotiable: Not a contract, can be refined
  • Valuable: Delivers user value
  • Estimable: Can be sized
  • Small: Fits in one sprint
  • Testable: Has clear acceptance criteria

3. Acceptance Criteria (BDD Format)

Scenario: {Descriptive title}
  Given {precondition/context}
    And {additional context}
  When {action/trigger}
    And {additional action}
  Then {expected outcome}
    And {additional verification}

For Project Domain:

  1. Reference existing test case patterns from feature docs
  2. Use TC-{FEATURE}-{NNN} format (e.g., TC-GM-001)
  3. Include Evidence field: file:line format
  4. Example from GoalManagement feature: TC-GRO-GOAL-001: Create goal with valid data GIVEN employee has permission to create goals WHEN employee submits goal form with all required fields THEN goal is created and appears in goal list Evidence: goal.service.ts:87, goal.component.ts:142

4. Business Rules Documentation

Rule Format
BR-{MOD}-{NNN}: {Rule name}
IF {condition}
THEN {action/result}
ELSE {alternative}
Evidence: {file}:{line}

5. Gap Analysis

  • Current state vs desired state mapping
  • Identify process improvements
  • Document integration requirements

Context Validation (Project Domain)

Before finalizing user story:

Cross-Reference Check

  • Business rules don't conflict with existing BR-{MOD}-XXX rules
  • Test case format matches existing TC-{FEATURE}-{NNN} patterns
  • Entity names match those in feature docs
  • Evidence format follows file:line convention

Documentation Links

Add to user story:

## Reference Documentation

- Feature Doc: `docs/business-features/{module}/detailed-features/{feature}.md`
- Related Entities: `docs/business-features/{module}/detailed-features/*.md`
- Existing Test Cases: See feature doc Section 15 (Test Specifications)

If conflicts found, note in "Unresolved Questions" section.


Workflow Integration

Refining Ideas to PBIs

When user runs /refine {idea-file}:

  1. Read idea artifact
  2. Check for module field in frontmatter
  3. Load business feature context if domain-related
  4. Extract requirements
  5. Extract existing BRs from feature docs
  6. Identify acceptance criteria using TC patterns
  7. Create PBI with GIVEN/WHEN/THEN format
  8. Save to team-artifacts/pbis/

Creating User Stories

When user runs /story {pbi-file}:

  1. Read PBI
  2. Break into vertical slices
  3. Write user stories with AC
  4. Ensure INVEST criteria met
  5. Include related BRs
  6. Save to team-artifacts/pbis/stories/

Templates

User Story Template

---
id: US-{YYMMDD}-{NNN}
parent_pbi: '{PBI-ID}'
persona: '{Persona name}'
priority: P1 | P2 | P3
story_points: 1 | 2 | 3 | 5 | 8 | 13 | 21
complexity: Low | Medium | High | Very High
status: draft | ready | in_progress | done
module: '' # Project module (if applicable)
---

# User Story

**As a** {user role}
**I want** {goal}
**So that** {benefit}

## Acceptance Criteria

### Scenario 1: {Happy path title}

Given {context} When {action} Then {outcome}

Scenario 2: {Edge case title}

Given {context}
When {action}
Then {outcome}

Scenario 3: {Error case title}

Given {context}
When {invalid action}
Then {error handling}

Related Business Rules

  • BR-{MOD}-XXX: {Description}

Out of Scope

  • {Explicitly excluded item}

Notes

  • {Implementation guidance}
---

## Elicitation Techniques

### 5 Whys
1. Why? → {answer}
2. Why? → {answer}
3. Why? → {answer}
4. Why? → {answer}
5. Why? → {root cause}

### SMART Criteria for Requirements
- **S**pecific: Clear and unambiguous
- **M**easurable: Can verify completion
- **A**chievable: Technically feasible
- **R**elevant: Aligned with business goals
- **T**ime-bound: Has a deadline or sprint

---

## Output Conventions

### File Naming

{YYMMDD}-ba-story-{slug}.md {YYMMDD}-ba-requirements-{slug}.md

### Requirement IDs
- Functional: `FR-{MOD}-{NNN}` (e.g., FR-GROW-001)
- Non-Functional: `NFR-{MOD}-{NNN}`
- Business Rule: `BR-{MOD}-{NNN}`

### AC IDs
- `AC-{NNN}` per story/PBI

### Test Case IDs (Project)
- `TC-{FEATURE}-{NNN}` (e.g., TC-GM-001)

---

## Quality Checklist

Before completing BA artifacts:
- [ ] User story follows "As a... I want... So that..." format
- [ ] At least 3 scenarios: happy path, edge case, error case
- [ ] All scenarios use GIVEN/WHEN/THEN
- [ ] Out of scope explicitly listed
- [ ] Story meets INVEST criteria
- [ ] No solution-speak in requirements (only outcomes)
- [ ] **Existing BRs referenced** (if domain-related)
- [ ] **TC format matches feature docs** (if domain-related)
- [ ] **Entity names use domain vocabulary**

---

## Post-Refinement Validation (MANDATORY)

**Every refinement must end with a validation interview.**

After completing user story or PBI refinement, conduct validation to:

1. Surface hidden assumptions
2. Confirm critical decisions
3. Identify potential concerns
4. Brainstorm with user on alternatives

### Validation Interview Process

Use `AskUserQuestion` tool with 3-5 questions:

| Category        | Example Questions                       |
| --------------- | --------------------------------------- |
| Assumptions     | "We assume X. Is this correct?"         |
| Scope           | "Should Y be explicitly excluded?"      |
| Dependencies    | "Does this depend on Z being ready?"    |
| Edge Cases      | "What happens when data is empty/null?" |
| Business Impact | "Will this affect existing reports?"    |

### Document Validation Results

Add to user story/PBI:

Validation Summary

Validated: {date}

Confirmed Decisions

  • {decision}: {user choice}

Concerns Raised

  • {concern}: {resolution}

Action Items

  • [ ] {follow-up if any}

### When to Flag for Stakeholder Review

- Decision impacts other teams
- Scope change requested
- Technical risk identified
- Business rule conflict detected

**This step is NOT optional - always validate before marking refinement complete.**

---

## Closing Reminders

- **MANDATORY IMPORTANT MUST ATTENTION** break work into small todo tasks using `TaskCreate` BEFORE starting
- **MANDATORY IMPORTANT MUST ATTENTION** search codebase for 3+ similar patterns before creating new code
- **MANDATORY IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim (confidence >80% to act)
- **MANDATORY IMPORTANT MUST ATTENTION** add a final review todo task to verify work quality
- **MUST ATTENTION** apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
- **MUST ATTENTION** apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

**[TASK-PLANNING]** Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.

平台分布

Claude Code

25.66%
按下载量换算50

windsurf

23.49%
按下载量换算46

OpenCode

16.93%
按下载量换算33

Codex

11.53%
按下载量换算22

Antigravity

8.28%
按下载量换算16

Gemini CLI

3.49%
按下载量换算7

安全审计

暂无安全审计结果可展示。

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