본문으로 건너뛰기
cccskills
무료GitHub에 공개

process-mapper

Map business processes as-is and to-be. Use when the user says "map the process", "draw the workflow", "BPMN diagram", "process flow", "swimlane", "how does this process work", "document the current process", "redesign this process", "process improvement", "value stream map", "workflow analysis" - even if they don't explicitly say "process mapper".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md5.5 KB
  • references/bpmn-notation.md3.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Reference Files

  • references/bpmn-notation.md - BPMN 2.0 symbol reference table with events, activities, gateways, flows, and swimlanes. Read this in Step 3 when mapping processes using BPMN notation.

Overview

Based on Business Process Change by Paul Harmon - the BPTrends 3-level process architecture (Enterprise, Business Process, Implementation) that prevents the most common process mapping mistake: starting at the wrong level of detail. Also draws on Business Analysis Techniques by James Cadle for BPMN notation and swimlane techniques, and Rummler-Brache's 3-level analysis (Organization, Process, Performer). The key insight from Harmon: before you draw a single box or arrow, locate the process within the enterprise value chain. A process mapped at the wrong level is either too abstract to act on or too detailed to see the real problems.

Workflow

Step 1: Identify the process level (Harmon's 3 levels)

Determine which level you are mapping:

  • Level 1 - Enterprise: Value chain view - how this process fits into the organization's end-to-end value delivery
  • Level 2 - Business Process: The process itself - trigger to outcome, with subprocesses
  • Level 3 - Implementation: Detailed task-level steps within a subprocess

Most BA process mapping operates at Level 2. Start at Level 1 to establish context, then zoom into Level 2.

Step 2: Define process boundaries

PROCESS NAME: [name]
TRIGGER: [what starts this process - event, request, schedule]
END EVENT: [what marks completion - output delivered, decision made, state changed]
IN SCOPE: [subprocesses included]
OUT OF SCOPE: [adjacent processes excluded]
OWNER: [who is accountable for this process]

Step 3: Map the AS-IS process (current state)

Using BPMN notation (see references/bpmn-notation.md):

  1. Draw the happy path first (main success flow from trigger to end)
  2. Add swimlanes for each role, department, or system involved
  3. Mark gateways (decision points) with labeled conditions
  4. Add exception paths branching from gateways
  5. Note handoffs between swimlanes - these are where delays and errors concentrate

Step 4: Measure the current process (Rummler-Brache)

Apply metrics at each of Rummler-Brache's 3 levels:

  • Organization level: Does this process align with business goals?
  • Process level: Cycle time, error rate, cost per transaction, throughput
  • Performer level: Handoff count, wait time between lanes, rework loops

Annotate the AS-IS map with actual metrics. Highlight pain points: bottlenecks, rework loops, unnecessary approvals, manual steps that could be automated.

Step 5: Map the TO-BE process (future state)

Apply Harmon's redesign principles:

  • Eliminate: Remove steps that add no value (approvals for low-risk items, duplicate data entry)
  • Simplify: Reduce complexity (merge steps, standardize variations)
  • Integrate: Combine handoffs between roles or systems
  • Automate: Replace manual steps with system actions where ROI justifies it

Step 6: Document the gap between AS-IS and TO-BE

| Change | AS-IS | TO-BE | Impact | Owner |
|--------|-------|-------|--------|-------|
| [description] | [current state] | [future state] | [who/what is affected] | [responsible] |

Step 7: Output the process map with change summary

Deliver: process diagrams (AS-IS and TO-BE), metrics comparison, change register, and recommended implementation sequence.

Anti-Patterns

1. Mapping at the wrong level of detail Bad: Starting with Level 3 task-level detail before understanding where the process sits in the value chain. Good: Start at Level 1 (context), zoom to Level 2 (process), drill into Level 3 only where pain points exist.

2. Missing swimlane handoffs Bad: Process flow with all steps in a single lane - hides the cross-functional complexity. Good: Every role or system gets its own lane; every arrow crossing a lane boundary is a handoff worth examining.

3. AS-IS without metrics Bad: Drawing the current process without measuring it. ("We think it takes about a week.") Good: Annotate with actual cycle time, error rates, and throughput. If data doesn't exist, that's a finding.

4. TO-BE that's just "automate everything" Bad: Future state where every manual step is replaced by a system. Good: Apply Harmon's sequence: eliminate first, then simplify, then integrate, then automate. Many problems are solved by removing steps, not by building software.

5. No trigger or end event Bad: Process map that starts with "Step 1" and ends with "Done." Good: BPMN start event (what triggers this?) and end event (what state marks completion?).

Quality Checklist

  • Process level identified (Enterprise / Business Process / Implementation)
  • Trigger event and end event explicitly defined
  • Swimlanes represent all participating roles and systems
  • Every gateway has labeled decision paths
  • No orphan activities (every activity has an incoming and outgoing flow)
  • AS-IS process annotated with actual metrics
  • TO-BE process applies eliminate/simplify/integrate/automate in that order
  • Handoffs between lanes are explicitly marked
  • Gap register documents every change between AS-IS and TO-BE

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Generate A/B copy variants grounded in Eugene Schwartz's awareness and market-sophistication stages and John Caples' tested-headline discipline. Every variant declares its angle, the awareness stage it targets, and a falsifiable hypothesis, and the skill recommends which pair to test first and what delta counts as signal. Use when the user says "A/B test this", "write variants", "give me options", "test different angles", "copy variants", "ab copy", "test this headline", "multiple versions", "which version is better", or wants to test copy before publishing. For reviewing copy that already exists, see copy-review. For sample size and stopping rules, see growth-experiment. For diagnosing a page rather than its words, see page-cro. For full paid ad sets by platform, see ad-campaign-writer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Design statistically rigorous experiments to test data science hypotheses. Use when the user says "design an A/B test", "run an experiment", "test this hypothesis", "is this difference significant", "how many samples do I need", "randomized controlled trial", "causal inference", "uplift test", "holdout group", "significance test", "power calculation", "avoid p-hacking", or needs to determine whether an observed effect is real before making a product or model decision. For lean build-measure-learn product experiments without the statistics, use experiment-design instead.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Write measurable acceptance criteria for requirements or user stories. Use when the user says "write acceptance criteria", "definition of done", "how do we test this", "fit criteria", "given when then", "Gherkin scenarios", "what does done look like", "testable conditions", "how will we know this works" - even if they don't explicitly say "acceptance criteria".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Build a strategic account plan for winning, retaining, or expanding a named account. Use when the user says "build an account plan", "strategic account planning", "how do I grow this account", "account expansion strategy", "whitespace analysis", "QBR prep", "key account review", "map the stakeholders in this account", "land and expand plan", "how do I break into [company]", or wants a structured strategy for a specific account.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

Write paid ad copy for LinkedIn, Google, Meta, and YouTube. Produces multiple variants per platform, each targeting a different Eugene Schwartz awareness level and Cialdini persuasion principle. Use when the user asks for ad copy, ad variants, "write LinkedIn ads", Google ads, Meta ads, paid social copy, ad headlines, or wants creative for a paid campaign. Reads brand voice, ICP, and positioning from knowledge/. For organic social posts, see linkedin-post or social-calendar. For the landing page the ad points at, see landing-page-writer. For testing variants, see ab-copy-writer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

qa-aman/claude-skills212026년 10월 19일 업데이트

qa-aman의 스킬 모두 보기

이 스킬의 문제 신고