Agent skill

Walkthrough

by udecode in udecode/kitcn

Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts.

Apache-2.0Auto-check passed

Install Walkthrough

skills CLI
$ npx skills add udecode/kitcn --skill walkthrough -a claude-code

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

GitHub CLI
$ gh skill install udecode/kitcn walkthrough --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/udecode/kitcn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/walkthrough .claude/skills/walkthrough && 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
walkthrough
GitHub stars
450
Token cost
~1.6k tokens
SKILL.md length
821 words
Files
4 (incl. scripts)
Skills in repo
33
Repo updated
First seen
Licence
Apache-2.0

At a glance

Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts.

  • Works in 4 steps: where the user acts; → what changed or became possible; → what consequence appears; → …
  • A user asks for demo screenshots
  • SKILL.md covers Honor The Caller Contract, Record A Diff Baseline, Read The Minimum Evidence and Pick The Shortest Story, plus 5 more sections
  • Runs JavaScript scripts from its folder; calls node and git

What it does

Walkthrough is an agent skill from udecode/kitcn. Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts. Use when a user asks for demo screenshots or a caller requires visual evidence after UI or rendered-output changes.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts (for example `agents/openai.yaml`).

The repository describes itself as: Convex + Better Auth + tRPC + Drizzle + TanStack Query + shadcn. The licence is Apache-2.0.

When your agent uses it

  • A user asks for demo screenshots
  • A caller requires visual evidence after UI
  • Rendered-output changes

Example prompts

  • “/walkthrough”

Requirements

  • Node.js

Workflow steps

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

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

What it can do on your machine

Read from SKILL.md and the folder at commit c6010f5. 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

    Ships 2 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Walkthrough loads about 1.6k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 821 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from udecode/kitcn at commit c6010f5, republished under its Apache-2.0 licence (© udecode). 821 words, ~1,559 tokens.

Download SKILL.mdSave it as .claude/skills/walkthrough/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
walkthrough
description
Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts. Use when a user asks for demo screenshots or a caller requires visual evidence after UI or rendered-output changes.

Walkthrough

Explain a completed change with a few annotated visuals. Run this after final verification. A walkthrough explains proof; it does not replace proof.

Honor The Caller Contract

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

For UI-gated workflows, treat app pages, websites, components, styles, visual content, and generated or rendered output as UI changes. If the packet changed one of those surfaces, run the walkthrough in the final handoff.

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:

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

Record A Diff Baseline

For a diff-gated workflow, capture the baseline before the first file mutation, including plan creation:

bash
node .agents/skills/walkthrough/scripts/diff-baseline.mjs capture \
  --output tmp/walkthrough/<slug>/baseline.json

At closeout, compare the final checkout with that baseline:

bash
node .agents/skills/walkthrough/scripts/diff-baseline.mjs compare \
  --baseline tmp/walkthrough/<slug>/baseline.json \
  --output tmp/walkthrough/<slug>/diff-receipt.json

Use producedFileDiff for the file-diff gate. Use changedPaths and the final diff to decide whether UI or rendered output changed. The receipt detects committed clean-tree changes, tracked working changes, executable-bit changes, symlink changes, and untracked files without git status.

Keep receipts local. Do not publish file hashes. If an older packet has no baseline, reconstruct it from the recorded starting commit or base ref and the packet's changed-file ledger. Mark the receipt as reconstructed. New packets must capture the baseline before mutation. The helper excludes its own baseline and receipt paths from the comparison, but the output directory should still be ignored by the repo.

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.

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.

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:

txt
tmp/walkthrough/<slug>/

Use paired names:

txt
01-<step>-original.png
01-<step>-annotated.png
Show full SKILL.md (332 more words)Show less

Annotate Without Rewriting

Inspect each source image first. Use imagegen, or the repo-approved image editor, to add only:

  • numbered callouts in free margins or calm empty areas;
  • short plain-English labels;
  • thin arrows that land on the exact control, value, or consequence;
  • a compact title when the frame needs context.

Keep labels to one sentence. Use product language, not implementation terms.

Never add, remove, rewrite, beautify, or simulate product content. Compare the annotated result with the original. If product text, values, layout, or state changed, discard it and regenerate. The original is proof. The annotation is explanation.

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

Apply these rules to annotation labels, captions, and the final handoff:

  • Lead with the outcome. Give the reason before implementation details.
  • Prefer common words and one project term per concept.
  • Use active voice and short, single-topic paragraphs.
  • 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

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;
  • originals and annotated copies are saved;
  • every annotation matches its original;
  • annotated images appear inline in the final response;
  • the owning proof is named.

© udecode, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in .agents/skills/walkthrough of udecode/kitcn.

  • SKILL.md
  • agents/openai.yaml
  • scripts/diff-baseline.mjs
  • scripts/diff-baseline.test.mjs

Open the folder on GitHubat commit c6010f5

Compare with similar skills

Walkthrough 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.

Walkthrough compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Walkthrough this skilludecode/kitcn450—~1.6kAutomated safety check: PassApache-2.0
Shortsickn33/agentic-awesome-skills47k1 repos~281Automated safety check: PassMIT
Wireframe Annotatednexu-io/open-design100k—~960Automated safety check: PassApache-2.0
Walkthroughudecode/dotai1.2k—~1.5kAutomated safety check: PassNone
Arize Annotationgithub/awesome-copilot40k1 repos~2.7kAutomated safety check: NotesMIT
Image Annotationsgithub/awesome-copilot40k—~6kAutomated safety check: PassMIT

Similar skills

  • Short

    sickn33/agentic-awesome-skills

    Rewrite the previous response more briefly while preserving the substance.

    47k GitHub starsUsed in 1 repo~281 tokens
    Auto-check passed
  • Wireframe Annotated

    nexu-io/open-design

    An annotated / redline lo-fi wireframe — a desktop landing/marketing page drawn as flat greyboxes inside a browser chrome frame, overlaid with numbered annotation pins (①②③④⑤) in a single accent…

    100k GitHub stars~960 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Walkthrough

    udecode/dotai

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

    1.2k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Arize Annotation

    github/awesome-copilot

    Official

    Creates and manages annotation configs (categorical, continuous, freeform label schemas) and annotation queues (human review workflows) on Arize.

    40k GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check: notes
  • Image Annotations

    github/awesome-copilot

    Official

    Annotate screenshots, diagrams, and images with callout rectangles, arrows, labels, and color-coded highlights using PIL.

    40k GitHub stars~6k tokensUpdated today
    DevelopmentAuto-check passed
  • Short Io Automation

    ComposioHQ/awesome-claude-skills

    Automate Short IO tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~734 tokens
    Productivity & AutomationAuto-check passed

More from udecode/kitcn

All 33 skills in this repo
  • Avoid Feature Creep

    udecode/kitcn

    Prevent feature creep when building software, apps, and AI-powered products.

    450 GitHub stars~2.7k tokensUpdated 6 days ago
    Auto-check passed
  • Changeset Resolve

    udecode/kitcn

    Repair an unreleased .changeset/.md file so it matches the real branch delta against main.

    450 GitHub stars~922 tokensUpdated 6 days ago
    Auto-check passed
  • Audit newer Convex npm releases against kitcn. An agent skill from udecode/kitcn.

    450 GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed
  • Jotai X

    udecode/kitcn

    A skill your agent uses when working with Jotai X stores (createAtomStore), accessing state in components or callbacks, persisting state to cookies or localStorage

    450 GitHub stars~3.7k tokensUpdated 6 days ago
    Auto-check passed
  • Linear Backlog

    udecode/kitcn

    Run a scoped Linear backlog autonomously as a sequence of maximal safe parallel batches by composing orchestrator, autogoal, and task.

    450 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check passed
  • Nextjs

    udecode/kitcn

    Next.js routing with typed routes, PageProps, LayoutProps helpers, and nuqs for URL state.

    450 GitHub stars~1.4k tokensUpdated 6 days ago
    Auto-check passed

Questions about Walkthrough

What does Walkthrough do?

Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts. Walkthrough is an agent skill from udecode/kitcn. Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts.

When should I use Walkthrough?

Walkthrough fits situations like: A user asks for demo screenshots; A caller requires visual evidence after UI; rendered-output changes.

How do I install Walkthrough in Claude Code?

Run `npx skills add udecode/kitcn --skill walkthrough -a claude-code`. Or copy the skill folder (.agents/skills/walkthrough in udecode/kitcn) into .claude/skills/walkthrough in your project. Claude Code loads it when a task matches its description.

How do I install Walkthrough in Codex?

Run `npx skills add udecode/kitcn --skill walkthrough -a codex`. Or copy the skill folder (.agents/skills/walkthrough in udecode/kitcn) into .agents/skills/walkthrough in your project. Codex loads it when a task matches its description.

Can I use Walkthrough 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 udecode/kitcn --skill walkthrough -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/walkthrough, .gemini/skills/walkthrough, .github/skills/walkthrough and .opencode/skills/walkthrough in your project.

What does Walkthrough need to run?

Going by SKILL.md and its folder, Walkthrough needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node and git). Our summary lists: Node.js.

Does Walkthrough access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Walkthrough 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Walkthrough use?

Walkthrough is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Walkthrough use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Walkthrough?

Skills that share tags, products or a category with Walkthrough: Short (sickn33/agentic-awesome-skills, 47k stars), Wireframe Annotated (nexu-io/open-design, 100k stars), Walkthrough (udecode/dotai, 1.2k stars) and Arize Annotation (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Walkthrough?

udecode (a GitHub organization) maintains it in udecode/kitcn, which has 450 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 1, 2026.

Source: udecode/kitcn on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.