uipath-automation-discovery

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Automation Discovery

自动化发现

Investigate how employees actually work, then identify and prioritize internal automation opportunities backed by real behavioral evidence. Produces a UiPath-ready backlog with recommended implementation paths.

调查员工实际工作方式，然后基于真实行为证据识别并优先排序内部自动化机会。生成包含推荐实施路径的UiPath就绪待办事项清单。

When to Use This Skill

何时使用此技能

User asks to discover automation opportunities across their organization — before any specific automation project exists
User wants to find manual work to automate and build a UiPath implementation backlog
User asks "what should we automate?" while working with UiPath tools
User wants an internal automation audit to feed into UiPath Automation Hub or a UiPath pipeline
User asks to estimate / size / cost discovered opportunities — pack-hours, delivery effort, complexity bands, contingency
User explicitly invokes
```
/uipath-automation-discovery
```

用户要求在整个组织内发现自动化机会——此时尚未启动任何特定自动化项目
用户希望找到可自动化的手动工作并构建UiPath实施待办事项清单
用户在使用UiPath工具时询问“我们应该自动化什么？”
用户需要内部自动化审计结果，以导入UiPath Automation Hub或UiPath流水线
用户要求估算/评估/核算已发现机会的规模——打包工时、交付工作量、复杂度等级、应急预留
用户显式调用
```
/uipath-automation-discovery
```

Critical Rules

核心规则

Authorization and privacy first. Confirm the requester is authorized to analyze the selected systems and employee data. Avoid private channels, DMs, and special-category HR data (payroll, performance reviews) unless explicitly approved. Pseudonymize SPOFs by default (e.g., "Sales Ops Lead A"); use real names only when explicitly authorized. Maintain consistent pseudonyms across the entire report — assign each individual a stable label on first mention and reuse it throughout. Ask about jurisdiction constraints (GDPR, works council, internal policy); apply the stricter rule when uncertain.
Never assume — always ask first. Complete the full intake (Phase 0) before mining. You need company context, tool access, org structure, privacy scope, and scope agreement.
Verify access before mining. Test each data source with a minimal read-only operation. If access fails, note it and move on — don't block discovery.
Evidence over opinion. Every opportunity (Tiers 1-3) must cite a specific source, quantitative metric, and affected role or team. No unsupported claims. If a source yields fewer than 5 signals, mark all findings from that source as low-confidence. Do not promote low-confidence findings above Tier 3, except per Rule 5.
Replication is always Tier 1. A proven model backed by a working automation that could replicate elsewhere is the highest-value finding — this overrides Rule 4's Tier 3 cap. If the replicable model's source has fewer than 5 signals, classify as Tier 1 with a low-confidence flag until corroborated by a second source. Always lead with replicable models. Never skip the replicable-model search (Phase 2C).
Never invent pack-hours or complexity thresholds (Phase 4.5). When estimating build effort, the band→hours numbers and matrix thresholds come from the user-supplied Core RPA / Agentic complexity matrices and Pack-Hours catalogue. Do NOT recall or fabricate them — if they are not supplied, STOP and ask. Adjustment-factor and contingency percentages are
```
[CALIBRATE]
```
defaults the user confirms against actuals. Fabricated numbers recreate the estimation error this phase exists to prevent.

授权与隐私优先。确认请求者有权分析所选系统和员工数据。除非获得明确批准，否则避免访问私人频道、私信和特殊类别HR数据（薪资、绩效评估）。默认对SPOFs使用匿名化处理（例如“销售运营主管A”）；仅在获得明确授权时使用真实姓名。在整个报告中保持一致的匿名标识——首次提及为每个个体分配稳定标签并在全文复用。询问管辖约束（GDPR、工会规定、内部政策）；不确定时遵循更严格的规则。
绝不假设——始终先询问。在挖掘前完成完整的准入流程（第0阶段）。你需要了解公司背景、工具访问权限、组织架构、隐私范围和范围协议。
挖掘前验证访问权限。通过最小化只读操作测试每个数据源。如果访问失败，记录后继续——不要阻碍发现流程。
证据优先于主观判断。每个机会（1-3级）必须引用特定来源、量化指标以及受影响的角色或团队。不接受无依据的主张。如果某个来源产生的信号少于5个，标记该来源的所有发现为低可信度。除非符合规则5，否则不得将低可信度发现提升至3级以上。
可复制模型始终为1级。已在某一领域验证可行、可复制到其他领域的自动化模型是最高价值的发现——这会覆盖规则4的3级上限。如果可复制模型的来源信号少于5个，归类为1级并标记低可信度，直到有第二个来源佐证。始终优先展示可复制模型。绝不跳过可复制模型搜索（第2C阶段）。
绝不编造打包工时或复杂度阈值（第4.5阶段）。估算构建工作量时，等级→工时的数值和矩阵阈值来自用户提供的Core RPA/Agentic复杂度矩阵和打包工时目录。不得回忆或编造这些数据——如果未提供，立即停止并询问用户。调整系数和应急预留百分比为
```
[CALIBRATE]
```
默认值，需用户根据实际情况确认。编造数据会重现本阶段旨在避免的估算误差。

Workflow Overview

工作流概述

Phase 0: INTAKE    → Gather context, verify access, agree on scope and privacy
Phase 1: MINE      → Gather raw data from all verified sources
Phase 2: ANALYZE   → Extract patterns, SPOFs, replicable models, gaps
Phase 3: REFLECT   → Layer on business strategy for strategic gaps
Phase 4: REPORT    → Produce prioritized report with 4 tiers
Phase 4.5: ESTIMATE→ Size build effort (band → pack-hours → contingency) — on request
Phase 5: HANDOFF   → Map opportunities to UiPath implementation skills

Stop conditions: Quick scan caps at 10 findings, Standard at 25, Deep dive at 35. Max 2 retries per failed source. Phase 1 timeboxed at 3 hours for deep dives. See references/intake-guide.md §0G for details.

Phase 0: INTAKE    → 收集背景信息、验证访问权限、确认范围与隐私规则
Phase 1: MINE      → 从所有已验证来源收集原始数据
Phase 2: ANALYZE   → 提取模式、SPOFs、可复制模型、差距
Phase 3: REFLECT   → 结合业务战略识别战略差距
Phase 4: REPORT    → 生成包含4个优先级等级的报告
Phase 4.5: ESTIMATE→ 评估构建工作量（等级→打包工时→应急预留）——按需执行
Phase 5: HANDOFF   → 将机会映射到UiPath实施技能

停止条件：快速扫描最多10个发现，标准扫描最多25个，深度挖掘最多35个。每个失败来源最多重试2次。深度挖掘的第1阶段限时3小时。详情请见references/intake-guide.md §0G。

Phase 0: INTAKE (interactive)

第0阶段：准入（交互式）

Build a complete picture before mining. Ask — don't assume.

See references/intake-guide.md for detailed steps covering company context, tool inventory, access verification, org structure, output preferences, user hypotheses, scope control, and privacy authorization.

Key outputs from intake:

Company context and department list
Tool & system inventory with verified access
Agreed scope (quick scan / standard / deep dive) with finding caps
Privacy scope (pseudonymize by default, jurisdiction constraints)

挖掘前构建完整的认知。主动询问——不要假设。

详细步骤请见references/intake-guide.md，涵盖公司背景、工具清单、访问权限验证、组织架构、输出偏好、用户假设、范围控制和隐私授权。

准入阶段关键输出：

公司背景和部门列表
已验证访问权限的工具与系统清单
已确认的范围（快速扫描/标准扫描/深度挖掘）及发现数量上限
隐私范围（默认匿名化、管辖约束）

Phase 1: MINE

第1阶段：挖掘

Cast a wide net. Prioritize by signal density. Use parallel agents (Agent tool with

subagent_type: general-purpose

, one agent per source category).

See references/mining-guide.md for detailed per-source guidance on what to look for and how to search.

Source priority when time is limited:

Messaging help channels — highest signal, fastest to mine
Email patterns — reveals hidden recurring work
CRM/ERP — reveals structured process bottlenecks
Wiki/docs — reveals existing automation landscape
Issue tracker — reveals service desk patterns
HRIS — reveals people-process friction
Web research — reveals strategic gaps

Note: Web research (priority 7) feeds Phase 3 strategic analysis. Even under time pressure, do a brief web search for the company's public financials and strategy — this takes minutes and enables Tier 4 findings.

Work with whatever access is verified. Even messaging channels alone can yield 15+ opportunities. Each additional source adds depth, not changes the methodology.

Checkpoint: After Phase 1, share a raw signal summary with the user: "I found X help channels, Y existing automation projects, Z departments. Want me to go deeper on anything before I analyze?" If the user requests deeper mining, run at most 1 additional targeted pass, then proceed.

广泛收集数据。按信号密度优先排序。使用并行代理（Agent工具，

subagent_type: general-purpose

，每个来源类别分配一个代理）。

每个来源的详细搜索指南请见references/mining-guide.md。

时间有限时的来源优先级：

消息帮助频道——信号最强，挖掘速度最快
邮件模式——揭示隐藏的重复性工作
CRM/ERP——揭示结构化流程瓶颈
维基/文档——揭示现有自动化格局
问题跟踪器——揭示服务台模式
HRIS——揭示人员流程摩擦
网络调研——揭示战略差距

注意：网络调研（优先级7）为第3阶段战略分析提供数据。即使时间紧张，也要对公司公开财务数据和战略进行简短网络搜索——这仅需几分钟，可支持4级发现。

基于已验证的访问权限开展工作。仅消息频道即可产生15+个机会。每个新增来源都会增加分析深度，不会改变方法。

检查点：第1阶段结束后，向用户分享原始信号摘要： “我发现了X个帮助频道、Y个现有自动化项目、Z个部门。在分析前需要我深入挖掘某些内容吗？”如果用户要求深入挖掘，最多执行1次额外定向挖掘，然后继续流程。

Phase 2: ANALYZE

第2阶段：分析

Transform raw data into structured findings.

将原始数据转化为结构化发现。

2A. Behavioral Patterns

2A. 行为模式

Per department, answer: What's manual? What questions repeat? What approvals stall? What reports are compiled by hand? What data is swivel-chaired between systems? What handoffs break? What scheduled tasks are done by humans?

按部门回答：哪些工作是手动的？哪些问题重复出现？哪些审批停滞？哪些报告是手动编制的？哪些数据需要在系统间手动转移？哪些交接环节出现问题？哪些定时任务由人工完成？

2B. Single Points of Failure

2B. 单点故障（SPOFs）

Identify roles that are sole responders. If they're out, the process stops. Pseudonymize by default — use role/team labels unless naming is authorized.

| Role/Pseudonym | System/Channel | Function | Risk |

These are the highest-urgency targets.

识别唯一响应者角色。如果他们缺席，流程将停滞。默认使用匿名化处理——除非获得命名授权，否则使用角色/团队标签。

| 角色/匿名标识 | 系统/频道 | 职能 | 风险 |

这些是最高优先级的自动化目标。

2C. Proven Replicable Models

2C. 已验证的可复制模型

The most important finding. Look for automation already working in one area that could replicate to others:

Bot in one channel but not others
Auto-routing in one team but manual elsewhere
Dashboard auto-generated for one dept but compiled by hand for another

| Working Model | Where It's Missing | Addressable Volume |

Greenfield case: If no existing automations are found (nothing to replicate), Tier 1 will be empty. Promote the highest-volume Tier 2 finding to the headline slot and note that the company has no proven models to replicate yet.

最重要的发现。寻找已在某一领域运行、可复制到其他领域的自动化：

某一频道部署了机器人但其他频道未部署
某一团队使用自动路由但其他团队仍手动操作
某一部门自动生成仪表盘但其他部门手动编制

| 已验证模型 | 缺失场景 | 可覆盖规模 |

全新场景：如果未发现现有自动化（无可复制内容），1级机会将为空。将最高规模的2级发现提升至 headline 位置，并注明公司目前无可复制的已验证模型。

2D. Department Coverage Map

2D. 部门覆盖地图

| Department | Existing Automations | Key Gap |

Flag ZERO-coverage departments as biggest blind spots.

| 部门 | 现有自动化 | 核心差距 |

将零覆盖部门标记为最大盲区。

2E. Process Deep Reads

2E. 流程深度解读

For promising existing projects, extract: pain point, manual process today, volume/frequency, ROI if documented, systems involved, dev status.

Apply low-confidence handling per Critical Rule 4.

Checkpoint: Share analysis summary with user before reflecting: "Here are the top patterns, SPOFs, and replicable models. Anything surprise you? Anything I should investigate further?" If the user requests deeper analysis, run at most 1 additional targeted pass, then proceed to Phase 3.

针对有潜力的现有项目，提取：痛点、当前手动流程、规模/频率、已记录的ROI、涉及的系统、开发状态。

根据核心规则4处理低可信度内容。

检查点：在进入反思阶段前向用户分享分析摘要： “以下是主要模式、SPOFs和可复制模型。有没有让你惊讶的内容？需要我进一步调查某些内容吗？”如果用户要求深入分析，最多执行1次额外定向分析，然后进入第3阶段。

Phase 3: REFLECT

第3阶段：反思

Identify gaps behavioral data won't reveal.

识别行为数据无法揭示的差距。

3A. Business Context

3A. 业务背景

Research via web search, investor docs, or internal strategy pages: revenue, growth, strategic priorities, competitive challenges, key metrics.

通过网络搜索、投资者文档或内部战略页面调研：收入、增长、战略优先级、竞争挑战、关键指标。

3B. Strategic Gaps

3B. 战略差距

For each of the company's documented strategic priorities, ask: "Is there an internal automation that accelerates this?" Only include Tier 4 opportunities that map to both a documented strategic priority and an observed Phase 1-2 gap.

Use this table as a starting prompt (covers common enterprise priorities) — adapt to the company's actual strategy and do not include rows where no gap was observed:

Priority	Potential Automation
Revenue growth	Lead scoring, pipeline acceleration, renewal prediction
Cost reduction	Self-service portals, report automation, process standardization
Customer retention	Health scoring, churn prediction, proactive outreach
Market expansion	Localization, compliance automation, partner enablement
Compliance	Audit trails, policy enforcement, automated reporting
Talent retention	Onboarding, engagement monitoring, career pathing

针对公司每个已记录的战略优先级，询问：“是否存在可加速该目标的内部自动化？”仅包含同时映射到已记录战略优先级和第1-2阶段观察到的差距的4级机会。

使用以下表格作为起始提示（涵盖常见企业优先级）——根据公司实际战略调整，不包含未观察到差距的行：

优先级	潜在自动化方向
收入增长	线索评分、 pipeline加速、续约预测
成本降低	自助服务门户、报告自动化、流程标准化
客户留存	健康度评分、流失预测、主动触达
市场扩张	本地化、合规自动化、合作伙伴赋能
合规性	审计追踪、政策执行、自动化报告
人才留存	入职流程、敬业度监控、职业路径规划

3C. Dogfooding Check (skip unless the company sells automation/AI/productivity tools)

3C. 自用检查（仅当公司销售自动化/AI/生产力工具时执行）

Does the company use its own product internally? Is there a coverage metric? What's the narrative gap between what they sell and what they do internally?

公司是否在内部使用自己的产品？是否有覆盖指标？他们销售的产品与内部实际使用情况之间存在哪些叙事差距？

Phase 4: REPORT

第4阶段：报告

Produce a prioritized report in the user's preferred platform. See references/report-template.md for structure, tier definitions, evidence standards, and platform-specific guidance.

在用户偏好的平台生成优先级报告。结构、等级定义、证据标准和平台特定指南请见references/report-template.md。

Quality Bar

质量标准

Every opportunity has specific evidence (source, metric, affected role/team)
No unsupported claims (except Tier 4, which references strategy docs)
SPOFs identified by role (or name if authorized)
Replicable models highlighted as Tier 1
Department map is complete (all departments, not just gapped ones)
ROI benchmarks from existing projects included
Strategic analysis ties to real financials

每个机会都有特定证据（来源、指标、受影响的角色/团队）
无无依据的主张（4级机会除外，其引用战略文档）
通过角色（或授权后的姓名）识别SPOFs
可复制模型标记为1级
部门地图完整（覆盖所有部门，不仅是有差距的部门）
包含现有项目的ROI基准
战略分析关联真实财务数据

Phase 4.5: ESTIMATE (optional — on request)

第4.5阶段：估算（可选——按需执行）

Run only when the user wants build-effort sizing (pack-hours, delivery estimate, complexity bands, contingency). Sizes each prioritized opportunity: opportunity → complexity band → pack-hours → adjustment factors → contingency → total. This is delivery/pre-sales sizing — distinct from the ROI/hours-saved impact already in the report.

The band→hours numbers and matrix thresholds are authoritative references the user supplies (Core RPA + Agentic complexity matrices, Pack-Hours catalogue) — never invented (Critical Rule 6). Ask for them if absent. The method adds the pieces that were missing: an above-ceiling/decompose rule (>7 apps / >8 variations), a multi-entity redeploy factor, an existing-automation rebuild discount, confidence-tiered contingency, and one unified band→hours mapping that resolves the Tool vs Process-Automation grain.

See references/estimation-guide.md and assets/templates/estimation-worksheet-template.md.

仅当用户需要评估构建工作量（打包工时、交付估算、复杂度等级、应急预留）时执行。为每个优先级机会评估规模：机会→复杂度等级→打包工时→调整系数→应急预留→总计。这是交付/售前阶段的规模评估——与报告中已有的ROI/节省工时影响不同。

等级→工时的数值和矩阵阈值是用户提供的权威参考资料（Core RPA + Agentic复杂度矩阵、打包工时目录）——绝不编造（核心规则6）。如果缺失，向用户索要。该方法补充了缺失的部分：上限分解规则（>7个应用 / >8个变体）、多实体重新部署系数、现有自动化重建折扣、基于可信度的应急预留，以及统一的等级→工时映射，解决了工具与流程自动化的粒度差异。

详情请见references/estimation-guide.md和assets/templates/estimation-worksheet-template.md。

Phase 5: HANDOFF

第5阶段：交接

Map each Tier 1-2 opportunity to a UiPath implementation path. Add a "Next Step" column to the report's Tier 1-2 tables.

Opportunity Type	Recommended Skill	Artifact
Desktop/app automation (UI, data entry)	→uipath-rpa	Coded workflow (.cs) or XAML
Multi-step automation or orchestration	→uipath-maestro-flow	Flow (.flow)
Scheduled / triggered automation	→uipath-maestro-flow	Flow with trigger
Agent-based (conversational, reasoning)	→uipath-agents	Coded agent
Approval / human review gate	→uipath-human-in-the-loop	HITL node in Flow
Cross-system integration	→uipath-platform	Integration Service connector

For complex or multi-component opportunities, hand off to →uipath-planner for full solution design.

将每个1-2级机会映射到UiPath实施路径。在报告的1-2级表格中添加“下一步”列。

机会类型	推荐技能	产物
桌面/应用自动化（UI、数据录入）	→uipath-rpa	编码工作流(.cs)或XAML
多步骤自动化或编排	→uipath-maestro-flow	Flow(.flow)
定时/触发式自动化	→uipath-maestro-flow	带触发器的Flow
基于Agent的自动化（对话式、推理型）	→uipath-agents	编码Agent
审批/人工审核环节	→uipath-human-in-the-loop	Flow中的HITL节点
跨系统集成	→uipath-platform	Integration Service连接器

对于复杂或多组件机会，交接给→uipath-planner进行完整解决方案设计。

Execution Strategy

执行策略

Parallelize Phases 1-3 (Phase 0 is interactive — do not parallelize intake). Max 3 concurrent agents using the Agent tool with

subagent_type: general-purpose

Phase 1: 3 agents — messaging, wiki/tracker, systems of record
Phase 2: department-specific behavioral agents (max 3 concurrent)
Multiple process doc reads in parallel
Web research concurrent with internal mining

Always share interim findings. Don't disappear for hours. Check in after each phase with a brief summary and ask if the user wants to adjust scope.

并行执行第1-3阶段（第0阶段为交互式——不要并行执行准入流程）。最多使用3个并发Agent工具（

subagent_type: general-purpose

）：

第1阶段：3个代理——消息类、维基/追踪器类、记录系统类
第2阶段：部门特定行为代理（最多3个并发）
并行读取多个流程文档
网络调研与内部挖掘并行执行

始终分享阶段性发现。不要长时间无反馈。每个阶段结束后向用户发送简短摘要并询问是否需要调整范围。

Reference Navigation

参考导航

references/intake-guide.md — Phase 0 detailed steps (company context, tool inventory, access verification, privacy)
references/mining-guide.md — Per-source search guidance (load during Phase 1)
references/report-template.md — Output structure, tier definitions, and evidence standards (load during Phase 4)
references/estimation-guide.md — Estimation accelerator: opportunity → band → pack-hours → contingency (load during Phase 4.5, on request)

references/intake-guide.md ——第0阶段详细步骤（公司背景、工具清单、访问权限验证、隐私）
references/mining-guide.md ——按来源划分的搜索指南（第1阶段加载）
references/report-template.md ——输出结构、等级定义和证据标准（第4阶段加载）
references/estimation-guide.md ——估算加速器：机会→等级→打包工时→应急预留（按需在第4.5阶段加载）

Anti-patterns

反模式

Mining before intake. Never start searching systems before completing Phase 0. Without context you'll waste time on irrelevant signals.
Naming individuals without consent. Always pseudonymize SPOFs unless the requester explicitly authorizes naming.
Fabricating metrics. If a source returns sparse data, mark findings as low-confidence. Never invent volume numbers.
Promising ROI without source citations. Every ROI estimate must reference an existing project benchmark or explicit data point.
Skipping the replicable-model search. The highest-value findings are always proven models that can replicate. Never skip Phase 2C.
Speculating from insufficient evidence. Below signal threshold → mark low confidence. Insufficient evidence → don't promote to Tier 1-3.
Fabricating pack-hours or matrix thresholds (Phase 4.5). The band→hours numbers are authoritative user-supplied references. Guessing them recreates the estimation error the accelerator exists to prevent — stop and ask for the catalogue and matrices.
Clamping oversized opportunities at "High". A cluster over the matrix ceiling (>7 apps / >8 variations) must be decomposed and summed, not sized as a single "High" unit — this was the largest source of under-estimation.

先挖掘后准入。绝不跳过第0阶段直接开始搜索系统。没有背景信息会浪费时间在无关信号上。
未经同意命名个人。始终对SPOFs使用匿名化处理，除非请求者明确授权命名。
编造指标。如果某来源数据稀疏，标记发现为低可信度。绝不编造规模数据。
无来源引用承诺ROI。每个ROI估算必须引用现有项目基准或明确数据点。
跳过可复制模型搜索。最高价值的发现始终是可复制的已验证模型。绝不跳过第2C阶段。
基于不足证据推测。低于信号阈值→标记低可信度。证据不足→不得提升至1-3级。
编造打包工时或矩阵阈值（第4.5阶段）。等级→工时数值是用户提供的权威参考资料。猜测这些数据会重现本加速器旨在避免的估算误差——停止并索要目录和矩阵。
将超大规模机会归为“高”等级。超过矩阵上限的集群（>7个应用 / >8个变体）必须分解后求和，不得作为单个“高”等级评估——这是低估的最大原因。