New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Web Verify

by Sidiora-Labs in Sidiora-Labs/centra-gideon-agent

Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence.

Apache-2.0Auto-check passedFrontend & Design

Install Web Verify

skills CLI
$ npx skills add Sidiora-Labs/centra-gideon-agent --skill web-verify -a claude-code

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

GitHub CLI
$ gh skill install Sidiora-Labs/centra-gideon-agent web-verify --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/Sidiora-Labs/centra-gideon-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/gideon/extensions/skills/bundled/web-verify .claude/skills/web-verify && 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
web-verify
GitHub stars
217
Token cost
~1.1k tokens
SKILL.md length
478 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
Apache-2.0

At a glance

Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence.

  • Works in 7 steps: Build, and check the exit code. A failed… → Confirm you are serving the bundle you… → Establish a mounted-ness floor. Before… → …
  • Frontend & Design work in your project
  • SKILL.md covers The loop, What a check never sees and Worked example
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Web Verify is an agent skill from Sidiora-Labs/centra-gideon-agent. Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence. Use before claiming a frontend change works.

Its SKILL.md is about 1.1k 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. The repository describes itself as: The companion AI agent that learns, adapts and gets the work done no matter the task. The licence is Apache-2.0.

When your agent uses it

  • Frontend & Design work in your project

Example prompts

  • “/web-verify”

Workflow steps

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

  1. Build, and check the exit code. A failed build leaves the previous bundle in
  2. Confirm you are serving the bundle you just built. Read the asset hash out of
  3. Establish a mounted-ness floor. Before asserting anything about your change,
  4. Add a positive control. Assert something you know is true. If the control
  5. Drive the actual interaction. Click, type, submit. A rendered control is not
  6. Read the console and the network panel. A silent 500 on a background fetch
  7. Capture evidence — before/after for a visual change, the console log for a

What it can do on your machine

Read from SKILL.md and the folder at commit ca531ee. 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.

    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

Web Verify loads about 1.1k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 478 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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 Sidiora-Labs/centra-gideon-agent at commit ca531ee, republished under its Apache-2.0 licence (© Sidiora-Labs). 478 words, ~1,058 tokens.

Download SKILL.mdSave it as .claude/skills/web-verify/SKILL.md (or your agent's skills folder).
name
web-verify
description
Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence. Use before claiming a frontend change works.
always
false
triggers
verify the page, does it render, render correctly, screenshot the page, check in the browser, browser check, headless browser, preview the build, smoke test…

Web verify

A frontend change is not done when the build succeeds. It is done when the page a user actually loads shows the change, with a clean console. This skill is the loop that closes that gap.

The failure this prevents is the one that keeps happening: the build output looked fine, so the change was declared working, and the browser was serving something else entirely — a stale bundle, a different process on the port, a dist directory that shadowed the real one.

The loop

  1. Build, and check the exit code. A failed build leaves the previous bundle in place. If you screenshot after a failed build you are looking at the old code and will report a change that never shipped.
  2. Confirm you are serving the bundle you just built. Read the asset hash out of the generated index.html and compare it to the chunk the browser actually loaded. If they differ, stop — everything after this is measuring the wrong artifact.
  3. Establish a mounted-ness floor. Before asserting anything about your change, assert the app mounted at all: a known-good element that must exist on every render. A blank page and a page missing your feature look identical to a selector that finds nothing.
  4. Add a positive control. Assert something you know is true. If the control fails, your harness is broken, not the app.
  5. Drive the actual interaction. Click, type, submit. A rendered control is not a working one.
  6. Read the console and the network panel. A silent 500 on a background fetch renders as an empty state, which looks like "no data yet" rather than "broken".
  7. Capture evidence — before/after for a visual change, the console log for a behavioural one.
Show full SKILL.md (188 more words)Show less

What a check never sees

State your scope honestly. A single screenshot at one viewport, on first render, in one theme, with a warm cache, sees a narrow slice:

  • Viewport — a defect can exist only at 390px or only at 1440px. Name the width you measured.
  • Theme — if the app stores its theme itself, forcing the OS-level preference does not switch it. Set the app's own key.
  • Timing — a layout that settles 400ms after mount looks fine in a screenshot taken at 2s. Sweep for transient states.
  • Cold state — an empty backend, a cleared local storage, and a first-ever visit are three different renderings.
  • Inner scrollers — a full-page capture of a layout whose content scrolls inside a child element captures only the viewport.

Worked example

A change adds a "Copy link" button to the artifact detail page.

1. Build          → npm run build --workspace web; echo "exit=$?"   → exit=0
2. Serving mine?  → grep -o 'index-[a-z0-9]*\.js' web/dist/index.html → index-9f2a1c4b.js
                    browser's loaded chunk                            → index-9f2a1c4b.js   ✅ same
3. Mounted floor  → the page's <h1> is present                       → ✅
4. Positive ctrl  → the artifact title matches the seeded fixture     → ✅ (harness sees real data)
5. Drive it       → click "Copy link"; read the clipboard             → got the artifact URL
6. Console        → 0 errors, 0 failed requests
7. Evidence       → before/after at 1440px AND 390px; noted that only
                    light theme was checked

Reported as: "Copy link works on artifact detail — verified at 1440px and 390px, light theme, clipboard receives the canonical URL, console clean. Not checked: dark theme, keyboard-only activation."

That last sentence is the part people skip. Naming what you did not check is what makes the part you did check trustworthy.

© Sidiora-Labs, 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

Just SKILL.md in runtime/gideon/extensions/skills/bundled/web-verify of Sidiora-Labs/centra-gideon-agent.

Open the folder on GitHubat commit ca531ee

Compare with similar skills

Web Verify 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.

Web Verify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Web Verify this skillSidiora-Labs/centra-gideon-agent217—~1.1kAutomated safety check: PassApache-2.0
Web Artifacts Builderanthropics/skills180k41 repos~769Automated safety check: PassApache-2.0
React Doctormakeplane/plane61k12 repos~657Automated safety check: PassAGPL-3.0
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
Figma Design System Builderwarpdotdev/warp65k2 repos~4.4kAutomated safety check: PassAGPL-3.0
Web Interface Guidelines Reviewervercel-labs/openreview1.7k97 repos~308Automated safety check: PassNone

Similar skills

  • Web Artifacts Builder

    anthropics/skills

    Official

    Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.

    180k GitHub starsUsed in 41 repos~769 tokens
    Frontend & DesignAuto-check passed

  • React Doctor

    makeplane/plane

    Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it.

    61k GitHub starsUsed in 12 repos~657 tokens
    Frontend & DesignAuto-check passed

  • 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

  • Figma Design System Builder

    warpdotdev/warp

    Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.

    65k GitHub starsUsed in 2 repos~4.4k tokens
    Frontend & DesignAuto-check passed

  • Web Interface Guidelines Reviewer

    vercel-labs/openreview

    Official

    Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my…

    1.7k GitHub starsUsed in 97 repos~308 tokens
    Frontend & DesignAuto-check passed

  • Tailwindcss Development

    anonaddy/anonaddy

    Always invoke when the user's message includes 'tailwind' in any form.

    4.9k GitHub starsUsed in 10 repos~865 tokens
    Frontend & DesignAuto-check passed

More from Sidiora-Labs/centra-gideon-agent

All 24 skills in this repo

  • Artifacts

    Sidiora-Labs/centra-gideon-agent

    Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown).

    217 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Best Of N

    Sidiora-Labs/centra-gideon-agent

    Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away.

    217 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Document Authoring

    Sidiora-Labs/centra-gideon-agent

    Author a real document — a report, proposal, slide deck, spec, or paper — by settling audience, claim, and structure before drafting prose, then writing to that structure.

    217 GitHub stars~970 tokensUpdated today
    Auto-check passed

  • Editorial Document

    Sidiora-Labs/centra-gideon-agent

    Write long-form editorial documents as clean, semantic HTML saved as an artifact (kind=document) — reports, briefs, explainers, proposals, write-ups.

    217 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

  • Gideon API

    Sidiora-Labs/centra-gideon-agent

    The operator's manual for DRIVING Gideon's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll.

    217 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Infographic Syntax

    Sidiora-Labs/centra-gideon-agent

    Author infographics with the AntV declarative DSL — pick a template, fill a small indented data tree, and save as an artifact (kind=infographic) that renders to crisp SVG and streams as you write it.

    217 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Web Verify

What does Web Verify do?

Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence. Web Verify is an agent skill from Sidiora-Labs/centra-gideon-agent. Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence.

When should I use Web Verify?

Web Verify fits situations like: frontend & Design work in your project.

How do I install Web Verify in Claude Code?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill web-verify -a claude-code`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/web-verify in Sidiora-Labs/centra-gideon-agent) into .claude/skills/web-verify in your project. Claude Code loads it when a task matches its description.

How do I install Web Verify in Codex?

Run `npx skills add Sidiora-Labs/centra-gideon-agent --skill web-verify -a codex`. Or copy the skill folder (runtime/gideon/extensions/skills/bundled/web-verify in Sidiora-Labs/centra-gideon-agent) into .agents/skills/web-verify in your project. Codex loads it when a task matches its description.

Can I use Web Verify 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 Sidiora-Labs/centra-gideon-agent --skill web-verify -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/web-verify, .gemini/skills/web-verify, .github/skills/web-verify and .opencode/skills/web-verify in your project.

What does Web Verify need to run?

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

Does Web Verify 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 Web Verify 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 Web Verify use?

Web Verify 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 Web Verify use?

About 1.1k tokens (SKILL.md is roughly 4.2k 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 Web Verify?

Skills that share tags, products or a category with Web Verify: Web Artifacts Builder (anthropics/skills, 180k stars), React Doctor (makeplane/plane, 61k stars), Impeccable (bestofjs/bestofjs, 3.1k stars) and Figma Design System Builder (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Web Verify?

Sidiora-Labs (a GitHub organization) maintains it in Sidiora-Labs/centra-gideon-agent, which has 217 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.

Source: Sidiora-Labs/centra-gideon-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.