Skip to content
Development
Skill

/walkthrough

Present final screenshots or rendered artifacts as an annotated walkthrough when visual evidence is requested.

From plugin
dotai
1.2k12 skills

Claude Code

$ npx -y skills add udecode/dotai --skill walkthrough --agent claude-code

SKILL.md

walkthrough.SKILL.md
name: walkthrough
description: "Present final screenshots or rendered artifacts as an annotated walkthrough when visual evidence is requested."

Walkthrough

Explain a completed change with a few annotated visuals. Run this after final verification. A walkthrough explains proof; it does not replace proof. Reuse the final verified frames. Do not repeat the browser walk or send a message to a customer or anyone outside the team without explicit authorization.

Honor The Caller Contract

The caller decides whether the walkthrough is required. Follow the stricter repo rule when one exists.

The caller chooses scope and whether an artifact is required. Workflow, docs, and backend changes do not create a visual obligation on their own.

When the caller requires a walkthrough and it cannot be produced, block closeout with the exact missing tool, access, or artifact. Do not waive it silently.

When the caller requires a diff check and no relevant UI or rendered-output change exists, record:

Walkthrough: N/A — no UI or rendered-output change in this packet.

For a caller that requires a diff baseline, read [baseline.md](references/baseline.md) before the first mutation. It owns capture, comparison, and honest reconstruction.

Read The Minimum Evidence

Read only what explains the completed result:

  • the latest request and acceptance criteria;
  • the baseline, diff receipt, and final diff;
  • final screenshots or rendered proof already captured;
  • the final route, role, data fixture, viewport, theme, or source artifact.

Reuse valid final-state screenshots. Do not rerun an expensive flow only to capture the same state.

Show the inspected saved record, receipt, message, packet or final artifact, not just a control that promises it. Reuse the verifier's recorded artifact inspection when its source, identity, state and hash still match; open only missing or stale evidence. When a preview and a downloadable/readable artifact both exist, their material claims must agree. Report a contradiction as a failure without repeating an already-proved operation just for presentation.

Pick The Shortest Story

Use one to four frames. Each frame should explain one point:

1. where the user acts; 2. what changed or became possible; 3. what consequence appears; 4. what proves the result.

Prefer the shortest sequence a non-developer can understand in under one minute. Do not turn every field or test into a callout.

For QA, product-owner, or end-to-end walkthroughs, keep one subject, one user goal, one decision scope, and one time context across the whole sequence. If a frame changes any of them, label it as a separate example instead of implying causality. A screen captured after an action is not proof that the action caused that state unless the identity and time boundary match.

Capture The Real Artifact

For UI or rendered-output changes:

  • capture the real final affected surface in its verified state;
  • preserve the correct role, data, viewport, theme, and open or selected state;
  • use the repo-required browser or capture tool;
  • reuse existing final proof when it shows the required state.

For an explicit walkthrough of non-UI work, render the real final source, diff, report, document, CLI result, or provider read-back. Never invent a product screen to make backend or workflow work look visual.

Prefer light mode when both themes are equally truthful. Keep the verified theme when the change concerns dark mode or switching would misrepresent the result.

Save originals and annotated copies under a repo-approved ignored directory. Default to:

tmp/walkthrough/<slug>/

Use paired names:

01-<step>-original.png
01-<step>-annotated.png

Annotation

When annotation is required, read [annotation.md](references/annotation.md). Retain the original and use the permitted deterministic annotation tool. This skill never authorizes changing product evidence.

Protect Sensitive Data

  • Do not send credentials, tokens, private URLs, customer data, personal data,

health data, or other repo-restricted content to an image tool.

  • Use deterministic sanitized fixtures or crop and redact before annotation.
  • Do not present a mockup, recreated HTML, or synthetic screen as completed

product work.

  • Do not claim the annotation itself proves runtime behavior.

Write Plain Technical Prose

Annotation labels, captions and the final handoff follow `unslop`. They also:

  • Cover objective, owner, chosen fix, invariant, alternatives, blast radius,

verification, and remaining risk when they apply.

  • Never make the reader inspect the diff to understand why the result is

correct and safe.

Final Handoff

In a project with plan pages, put the annotated images on the plan page, which is published with them, and keep the reply to the page link. Otherwise show every annotated image inline with an absolute local path. Give each image one short caption stating what to notice. Name the related test, browser, external, or source proof.

When a PR or tracker needs images, follow the owning repo's upload policy and replace local paths with hosted URLs there.

Close only when:

  • the caller's applicability rule was classified correctly;
  • the baseline and receipt exist when the caller uses a diff gate;
  • the frames cover the user action and consequence;
  • QA and product-owner flows keep one subject, goal, decision scope, and time

context, or label each discontinuity as a separate example;

  • the final frame shows the saved artifact itself, not only its navigation

control;

  • preview and final artifact claims agree, or the walkthrough reports their

contradiction as a blocker;

  • originals and annotated copies are saved;
  • every annotation matches its original;
  • annotated images appear on the plan page, or inline when the project has none;
  • the owning proof is named.
Read more
@udecode
Ships withdotai

Shared skills that the pstack plugin does not cover: test audits (test-audit, adapted from openclaw's), screenshot walkthroughs and video transcripts, and pstack setup, sync and skill-drift audits (sync-pstack).

Stars on GitHub

Momentum

stars in total
1.2k
Star history of udecode/dotai on GitHub, a chart by star-history.com

Other skills on dotai.

chips

chips

Run the project's suggested-task ledger, the chips. /chips alone brings this session's open tasks up to date: it applies what the…

@udecode@udecodeInstall Skill
cleanup

cleanup

Free disk in a project by removing the git worktrees and Next.js cache folders nothing uses, keeping every worktree a session or…

@udecode@udecodeInstall Skill
passwords

passwords

Set up unattended 1Password access on a Mac or sign in to websites and apps without repeated human approvals. Use for new-device…

@udecode@udecodeInstall Skill
plan-page

plan-page

Write, check, repair and publish a plan page: a project's plans and subject files under its plans directory, rendered by…

@udecode@udecodeInstall Skill
pstack-pulse

pstack-pulse

Show every Claude Code and Codex session on the iPhone lock screen through ActivitySmith and in the Mac menubar, with each plan…

@udecode@udecodeInstall Skill
rca

rca

Turn Remote Control on for every non-archived Claude Code session in the Claude desktop app.

@udecode@udecodeInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills11d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc12d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react1d252k
@facebook@facebookInstall Skill

Questions about walkthrough.

Which coding agents can use walkthrough?
walkthrough installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.