Agent skill

User Flow Mapping

by seb1n in seb1n/awesome-ai-agent-skills

Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys.

MITAuto-check passedFrontend & Design

Install User Flow Mapping

skills CLI
$ npx skills add seb1n/awesome-ai-agent-skills --skill user-flow-mapping -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install seb1n/awesome-ai-agent-skills user-flow-mapping --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/design-and-ui-ux/user-flow-mapping .claude/skills/user-flow-mapping && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
user-flow-mapping
GitHub stars
206
Token cost
~2.6k tokens
SKILL.md length
988 words
Files
1
Skills in repo
92
Repo updated
First seen
Licence
MIT

At a glance

Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys.

  • Works in 6 steps: Define the Flow Objective and Scope:… → Identify All Steps and Decision Points:… → Map Happy Path First, Then Edge Paths:… → …
  • The user requests user flow mapping
  • SKILL.md covers Workflow, Usage, Examples and Best Practices, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

User Flow Mapping is an agent skill from seb1n/awesome-ai-agent-skills. Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys. Use when the user requests user flow mapping or provides relevant inputs for this workflow.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering UX design. The repository describes itself as: 103 ready-to-use AI agent skills for Claude Code, OpenAI Codex, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and other Agent Skills-compatible tools. Complete SKILL.md… The licence is MIT.

When your agent uses it

  • The user requests user flow mapping
  • Provides relevant inputs for this workflow

Example prompts

  • “/user-flow-mapping”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Define the Flow Objective and Scope: Identify the specific user goal being mapped (e.g., "Complete a purchase," "Reset a password")…
  2. Identify All Steps and Decision Points: List every screen, action, and system response in sequence. Mark decision points where the user or…
  3. Map Happy Path First, Then Edge Paths: Draw the ideal path from entry to success first. Then layer in alternative paths: what happens if…
  4. Annotate with Metrics and Risk Points: At each step, note the relevant metric: page view count, click-through rate, form completion rate…
  5. Generate the Mermaid Diagram: Produce a clean Mermaid graph TD diagram using consistent node shapes: rounded rectangles () for…
  6. Review and Iterate: Walk through the diagram with the user to verify completeness. Check that every branch terminates, that no orphan…

What it can do on your machine

Read from SKILL.md and the folder at commit 75865a5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

User Flow Mapping loads about 2.6k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 988 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from seb1n/awesome-ai-agent-skills at commit 75865a5, republished under its MIT licence (© seb1n). 988 words, ~2,568 tokens.

Download SKILL.mdSave it as .claude/skills/user-flow-mapping/SKILL.md (or your agent's skills folder).
name
user-flow-mapping
description
Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys. Use when the user requests user flow mapping or provides relevant inputs for this workflow.
license
MIT
metadata.author
AI Agent Skills Community
metadata.version
1.0.0

User Flow Mapping

This skill enables the agent to create detailed user flow diagrams that map every step, decision point, error state, and success path a user encounters while completing a task in a product. The agent produces three types of flows — task flows (single path, no decisions), user flows (multiple paths with decision branches), and wire flows (flows annotated with screen wireframes) — using Mermaid diagram syntax for portability. Each flow includes annotations for conversion metrics, drop-off risk points, and optimization opportunities.

Workflow

  1. Define the Flow Objective and Scope: Identify the specific user goal being mapped (e.g., "Complete a purchase," "Reset a password"). Determine the entry points — how the user arrives at the start of the flow (direct link, homepage navigation, email CTA, push notification). Establish the success criteria and the scope boundary so the diagram does not expand indefinitely.

  2. Identify All Steps and Decision Points: List every screen, action, and system response in sequence. Mark decision points where the user or the system branches (e.g., "Is the user logged in?" or "Did payment succeed?"). Include error states, validation failures, and retry loops. For each step, note whether it is a user action (click, type, swipe) or a system action (redirect, API call, email sent).

  3. Map Happy Path First, Then Edge Paths: Draw the ideal path from entry to success first. Then layer in alternative paths: what happens if the user is not logged in, if validation fails, if the session times out, if the payment is declined. Each branch should terminate in either a success state, an error recovery path, or an exit point.

  4. Annotate with Metrics and Risk Points: At each step, note the relevant metric: page view count, click-through rate, form completion rate, drop-off percentage. Flag high-friction steps where users are likely to abandon (multi-field forms, account creation walls, payment pages). Suggest specific optimizations for each risk point.

  5. Generate the Mermaid Diagram: Produce a clean Mermaid graph TD diagram using consistent node shapes: rounded rectangles () for pages/screens, diamonds {} for decisions, rectangles [] for actions, and double-circles (()) for start/end states. Use descriptive labels and color annotations via style directives to highlight error paths in red and success paths in green.

  6. Review and Iterate: Walk through the diagram with the user to verify completeness. Check that every branch terminates, that no orphan nodes exist, and that the flow accurately reflects the actual product behavior including edge cases.

Usage

Provide the agent with the user goal, the product context (web app, mobile app, or cross-platform), and any known screens or steps. Optionally include analytics data (drop-off rates, conversion percentages) for the agent to annotate onto the diagram. The agent will produce a Mermaid diagram with annotations.

Examples

Example 1: E-Commerce Checkout Flow

User Request: "Map the complete checkout flow for our e-commerce site. Users can be logged in or guests. We support credit card and PayPal."

Agent Response:

mermaid
graph TD
    START(("Start: Cart Page")) --> REVIEW["Review Cart Items"]
    REVIEW --> EMPTY{Cart empty?}
    EMPTY -- Yes --> BROWSE["Redirect to Shop Page"]
    EMPTY -- No --> AUTH{User logged in?}

    AUTH -- Yes --> SHIPPING["Enter Shipping Address"]
    AUTH -- No --> CHOICE{Guest or Sign In?}
    CHOICE -- Sign In --> LOGIN["Login Page"]
    LOGIN --> LOGIN_OK{Login successful?}
    LOGIN_OK -- Yes --> SHIPPING
    LOGIN_OK -- No --> LOGIN_ERR["Show Error, Retry"]
    LOGIN_ERR --> LOGIN
    CHOICE -- Guest --> GUEST_EMAIL["Enter Email Address"]
    GUEST_EMAIL --> SHIPPING

    SHIPPING --> VALIDATE_ADDR{Address valid?}
    VALIDATE_ADDR -- No --> ADDR_ERR["Show Validation Errors"]
    ADDR_ERR --> SHIPPING
    VALIDATE_ADDR -- Yes --> DELIVERY["Select Delivery Method"]

    DELIVERY --> PAYMENT{Payment method?}
    PAYMENT -- Credit Card --> CC["Enter Card Details"]
    CC --> CC_VALID{Card valid?}
    CC_VALID -- No --> CC_ERR["Show Card Error"]
    CC_ERR --> CC
    CC_VALID -- Yes --> PROCESS

    PAYMENT -- PayPal --> PP["Redirect to PayPal"]
    PP --> PP_OK{PayPal authorized?}
    PP_OK -- No --> PP_ERR["PayPal Cancelled"]
    PP_ERR --> PAYMENT
    PP_OK -- Yes --> PROCESS

    PROCESS["Process Payment"] --> SUCCESS{Payment successful?}
    SUCCESS -- Yes --> CONFIRM["Order Confirmation Page"]
    CONFIRM --> END(("End: Order Complete"))
    SUCCESS -- No --> DECLINE["Show Decline Message"]
    DECLINE --> PAYMENT

    style BROWSE fill:#fef3c7,stroke:#f59e0b
    style LOGIN_ERR fill:#fee2e2,stroke:#ef4444
    style ADDR_ERR fill:#fee2e2,stroke:#ef4444
    style CC_ERR fill:#fee2e2,stroke:#ef4444
    style PP_ERR fill:#fee2e2,stroke:#ef4444
    style DECLINE fill:#fee2e2,stroke:#ef4444
    style CONFIRM fill:#d1fae5,stroke:#10b981
    style END fill:#d1fae5,stroke:#10b981

Metric annotations:

  • Cart → Shipping: ~72% proceed (28% abandon after viewing cart)
  • Shipping → Payment: ~85% proceed (address validation is low friction)
  • Payment → Confirmation: ~64% proceed (highest drop-off; consider saved payment methods)
  • Guest vs Sign In split: ~55% choose guest checkout (reduce friction by keeping guest option prominent)
Show full SKILL.md (459 more words)Show less
Example 2: SaaS Onboarding Flow with Decision Points

User Request: "Map the onboarding flow for our project management tool. New users sign up, verify email, choose a plan, create their first project, and invite team members."

Agent Response:

mermaid
graph TD
    START(("Entry: Landing Page")) --> SIGNUP["Sign Up Form"]
    SIGNUP --> VALIDATE{Form valid?}
    VALIDATE -- No --> FORM_ERR["Show Validation Errors"]
    FORM_ERR --> SIGNUP
    VALIDATE -- Yes --> EMAIL_SENT["Verification Email Sent"]

    EMAIL_SENT --> VERIFIED{Email verified?}
    VERIFIED -- No, 24h+ --> RESEND["Resend Verification"]
    RESEND --> VERIFIED
    VERIFIED -- Yes --> PLAN{Choose Plan}

    PLAN -- Free --> FREE["Free Plan Selected"]
    PLAN -- Pro --> BILLING["Enter Billing Info"]
    BILLING --> BILLING_OK{Payment valid?}
    BILLING_OK -- No --> BILL_ERR["Show Billing Error"]
    BILL_ERR --> BILLING
    BILLING_OK -- Yes --> PRO["Pro Plan Activated"]

    FREE --> PROFILE["Complete Profile"]
    PRO --> PROFILE

    PROFILE --> CREATE["Create First Project"]
    CREATE --> INVITE{Invite team members?}
    INVITE -- Yes --> TEAM["Enter Team Emails"]
    TEAM --> INVITES_SENT["Invitations Sent"]
    INVITES_SENT --> DASHBOARD
    INVITE -- Skip --> DASHBOARD["Dashboard - Onboarding Complete"]
    DASHBOARD --> END(("End: Active User"))

    style FORM_ERR fill:#fee2e2,stroke:#ef4444
    style BILL_ERR fill:#fee2e2,stroke:#ef4444
    style RESEND fill:#fef3c7,stroke:#f59e0b
    style DASHBOARD fill:#d1fae5,stroke:#10b981
    style END fill:#d1fae5,stroke:#10b981

Metric annotations and optimization notes:

  • Sign Up → Email Verified: ~68% verify within 1 hour. Send a reminder at 24 hours. Consider allowing limited access before verification to reduce early churn.
  • Plan Selection: ~80% choose Free initially. Offer a 14-day Pro trial without requiring billing info to increase Pro conversion.
  • Create First Project: Critical activation step. If the user does not create a project within 48 hours, trigger a guided tutorial email. Target: 60% activation within first session.
  • Invite Team: ~35% skip this step. Show the value of collaboration (e.g., "Teams complete projects 3x faster") to increase invite rates.

Best Practices

  • Always map the happy path before adding branches: Starting with the ideal path keeps the diagram readable. Layer in error states, edge cases, and alternative paths incrementally.
  • Use consistent node shapes: Reserve diamonds for decision points, rounded rectangles for screens/pages, and rectangles for user or system actions. This visual grammar makes flows scannable at a glance.
  • Terminate every branch: Every path in the diagram must end at a defined state — success, error recovery, or explicit exit. Orphan nodes indicate missing logic in the product.
  • Annotate with real data when available: Drop-off rates, conversion percentages, and session duration at each step transform a flow diagram from a planning artifact into an optimization tool.
  • Keep flows to one user goal per diagram: Combining "sign up," "purchase," and "manage account" in one diagram creates an unreadable mess. Map each goal separately, then link diagrams at shared entry/exit points.

Edge Cases

  • Circular flows (retry loops): Payment retries, form re-submissions, and re-authentication can create infinite loops in the diagram. Add a maximum retry count annotation (e.g., "Max 3 attempts, then redirect to support") and a terminal exit node for exhausted retries.
  • External system redirects (OAuth, PayPal, 3D Secure): When the user leaves the product for third-party authentication, mark the transition explicitly and account for three outcomes: success return, cancellation return, and timeout/no-return. Include a "user never returns" exit node.
  • A/B test variants: When the flow differs between test groups, create a decision node at the variant split labeled with the test name and variant identifiers, then map both paths to their respective outcomes.
  • Flows that span multiple sessions: Password reset (email → click link hours later) or email verification may not complete in one session. Mark the session boundary explicitly and indicate what triggers re-entry (email link, push notification, return visit).
  • Offline or degraded states in mobile apps: If the product works offline, map what happens when connectivity drops mid-flow: queued actions, error messages, and sync-on-reconnect behavior.

© seb1n, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in design-and-ui-ux/user-flow-mapping of seb1n/awesome-ai-agent-skills.

Open the folder on GitHubat commit 75865a5

Compare with similar skills

User Flow Mapping next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

User Flow Mapping compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
User Flow Mapping this skillseb1n/awesome-ai-agent-skills206—~2.6kAutomated safety check: PassMIT
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Interface Design for Dashboards and Appsholaboss-ai/holaOS11k3 repos~6kAutomated safety check: PassMIT
Animategrowupanand/ConvoForm1016 repos~1.9kAutomated safety check: PassApache-2.0
Migrate Content Iadocker/docs4.7k—~5.1kAutomated safety check: PassApache-2.0
UX WalkthroughXiaoMi/hiui877—~1.3kAutomated safety check: PassMIT

Similar skills

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.

    11k GitHub starsUsed in 3 repos~6k tokens
    Frontend & DesignAuto-check passed
  • Animate

    growupanand/ConvoForm

    Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight.

    101 GitHub starsUsed in 6 repos~1.9k tokens
    Frontend & DesignAuto-check passed
  • Official

    Handle Hugo docs information-architecture moves: discover old vs new URLs, add front matter aliases (Phase 1), update in-repo links (Phase 2), interactive List 2 resolution and fragment validation…

    4.7k GitHub stars~5.1k tokensUpdated today
    Frontend & DesignAuto-check passed
  • UX Walkthrough

    XiaoMi/hiui

    体验走查 skill。适用于代码库、URL、截图三种输入,输出结构化体验问题报告,并同步生成本地 docx 报告。触发词:体验走查、UX review、交互走查、界面审查、体验问题。

    877 GitHub stars~1.3k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed
  • Color Audit

    rome-os/rome

    Audit a design system's color palette against measurable color-science disciplines — WCAG/APCA contrast of declared token pairs, perceptual (OKLCH) ramp uniformity, color-blindness safety of…

    717 GitHub stars~2.7k tokensUpdated today
    Frontend & DesignAuto-check passed

More from seb1n/awesome-ai-agent-skills

All 92 skills in this repo
  • Agent Red Teaming

    seb1n/awesome-ai-agent-skills

    Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings.

    206 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Eu AI Act Readiness

    seb1n/awesome-ai-agent-skills

    Build a preliminary, evidence-based EU AI Act readiness assessment across AI-system inventory, territorial scope, operator roles, prohibited-practice screening, risk classification, transparency…

    206 GitHub stars~3.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Human In The Loop

    seb1n/awesome-ai-agent-skills

    Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows.

    206 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • MCP Server Building

    seb1n/awesome-ai-agent-skills

    Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests.

    206 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • PDF Processing

    seb1n/awesome-ai-agent-skills

    Inspect, extract, OCR, create, merge, split, reorder, rotate, annotate, fill, redact, compress, secure, and verify PDF documents while preserving source files and visual fidelity.

    206 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Skill Supply Chain Audit

    seb1n/awesome-ai-agent-skills

    Audit agent skills, plugins, prompts, manifests, scripts, dependencies, and bundled assets for provenance, prompt-injection, permission, execution, exfiltration, persistence, and update risk.

    206 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

Questions about User Flow Mapping

What does User Flow Mapping do?

Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys. User Flow Mapping is an agent skill from seb1n/awesome-ai-agent-skills. Visualize and map user flows with Mermaid diagrams, decision points, error states, and conversion metrics to optimize user journeys.

When should I use User Flow Mapping?

User Flow Mapping fits situations like: the user requests user flow mapping; provides relevant inputs for this workflow.

How do I install User Flow Mapping in Claude Code?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill user-flow-mapping -a claude-code`. Or copy the skill folder (design-and-ui-ux/user-flow-mapping in seb1n/awesome-ai-agent-skills) into .claude/skills/user-flow-mapping in your project. Claude Code loads it when a task matches its description.

How do I install User Flow Mapping in Codex?

Run `npx skills add seb1n/awesome-ai-agent-skills --skill user-flow-mapping -a codex`. Or copy the skill folder (design-and-ui-ux/user-flow-mapping in seb1n/awesome-ai-agent-skills) into .agents/skills/user-flow-mapping in your project. Codex loads it when a task matches its description.

Can I use User Flow Mapping in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add seb1n/awesome-ai-agent-skills --skill user-flow-mapping -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/user-flow-mapping, .gemini/skills/user-flow-mapping, .github/skills/user-flow-mapping and .opencode/skills/user-flow-mapping in your project.

What does User Flow Mapping need to run?

SKILL.md names no scripts, command-line tools or credentials: User Flow Mapping is instructions for the agent only.

Does User Flow Mapping access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is User Flow Mapping safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does User Flow Mapping use?

User Flow Mapping is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does User Flow Mapping use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to User Flow Mapping?

Skills that share tags, products or a category with User Flow Mapping: Impeccable (bestofjs/bestofjs, 3.1k stars), Interface Design for Dashboards and Apps (holaboss-ai/holaOS, 11k stars), Animate (growupanand/ConvoForm, 101 stars) and Migrate Content Ia (docker/docs, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains User Flow Mapping?

seb1n (a GitHub user) maintains it in seb1n/awesome-ai-agent-skills, which has 206 GitHub stars. The repository holds 92 skills in this directory. The repository was last updated on August 9, 2026.

Source: seb1n/awesome-ai-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.