Checking A Page
awss1i/assay
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it.
Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.
Install Web
$ npx skills add autonomous-ai/openharness --skill web -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install autonomous-ai/openharness web --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/web-studio/skills/web .claude/skills/web && rm -rf skills-srcUse ~/.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/
Install the "web" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/web into .claude/skills/web/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/webType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add autonomous-ai/openharness --skill web -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install autonomous-ai/openharness web --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/store/agents/web-studio/skills/web .agents/skills/web && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "web" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/web into .agents/skills/web/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill web -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install autonomous-ai/openharness web --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/store/agents/web-studio/skills/web .cursor/skills/web && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "web" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/web into .cursor/skills/web/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/autonomous-ai/openharness.git --path store/agents/web-studio/skills/web--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add autonomous-ai/openharness --skill web -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install autonomous-ai/openharness web --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/store/agents/web-studio/skills/web .gemini/skills/web && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "web" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/web into .gemini/skills/web/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install autonomous-ai/openharness webInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add autonomous-ai/openharness --skill web -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .github/skills && cp -r skills-src/store/agents/web-studio/skills/web .github/skills/web && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "web" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/web into .github/skills/web/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add autonomous-ai/openharness --skill web -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install autonomous-ai/openharness web --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/store/agents/web-studio/skills/web .opencode/skills/web && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "web" agent skill from https://github.com/autonomous-ai/openharness/tree/main/store/agents/web-studio/skills/web into .opencode/skills/web/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "web", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
web- GitHub stars
- 1.1k
- Token cost
- ~518 tokens
- SKILL.md length
- 261 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 99
- Repo updated
- First seen
- Licence
- MIT
At a glance
Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.
- Tasks that involve HTML artifacts
- Runs JavaScript scripts from its folder; calls node
What it does
Web is an agent skill from autonomous-ai/openharness. Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.
Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts.
It sits in Frontend & Design, covering HTML artifacts. It works with Playwright. The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.
When your agent uses it
- Tasks that involve HTML artifacts
Example prompts
- “/web”
Requirements
- Node.js
What it can do on your machine
Read from SKILL.md and the folder at commit 54a1f1b. 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
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 loads about 518 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 261 words of instructions outside code blocks.
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 autonomous-ai/openharness at commit 54a1f1b, republished under its MIT licence (© autonomous-ai). 261 words, ~518 tokens.
Download SKILL.mdSave it as
.claude/skills/web/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- web
- description
- Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.
Web Studio
index.html is the entry point. Local JS, CSS, images and ES modules work through the shared viewer;
use relative URLs. No bundler is required. Prefer local assets for a reliable first open.
Field's starter uses WebGL2 with a Canvas 2D fallback. Its geometry, palette and controls are all editable. Keep GPU resources and geometry buffers reusable; coalesce continuous updates in rAF. Pause animation when hidden and respect reduced motion. Controls must still work when paused. A new visual direction can replace the starter entirely when that serves the user's request.
Verify the experience
Keep proof.json aligned with the current page. Each action names a CSS selector, followed by
click: true, fill or select; assertions use exact text or
attribute: {"name":"aria-pressed","value":"true"}. Include a state change and its meaningful result.
node "$WEB_SKILLS/web/scripts/screenshot.mjs" "$HARNESS_WORKSPACE/index.html"
node "$WEB_SKILLS/web/scripts/perf.mjs" "$HARNESS_WORKSPACE/index.html"The proof runs the real sandboxed HTTP viewer, checks the actions and browser errors, saves
.harness/last.png and a dependency-hashed browser-proof.json, and refreshes the verdict.
Inspect the image and test a narrow viewport as well as desktop.
The performance probe drives those controls while measuring rAF delays and long tasks, rather than
measuring an idle page. Target ≥55 fps and <2% slow frames. Record the hardware/renderer and dataset;
a software WebGL renderer is not a measurement of the user's GPU. PLAYWRIGHT_CHANNEL=chrome can
measure installed Chrome. Do not label an unmeasured or failing page “60 fps.”
Helpers need Playwright plus Chromium, installed in the shared isolated-web-viewer package or addressed by
PLAYWRIGHT_MODULE (absolute path to playwright/index.mjs). Missing tooling is a failed proof,
not permission to report success. The preview itself needs only Node 20+.
© autonomous-ai, MIT. 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 2 other files (scripts) in store/agents/web-studio/skills/web of autonomous-ai/openharness.
- SKILL.md
- scripts/perf.mjs
- scripts/screenshot.mjs
Open the folder on GitHubat commit 54a1f1b
Compare with similar skills
Web 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Web this skillautonomous-ai/openharness | 1.1k | — | ~518 | Automated safety check: Pass | MIT | |
| Checking A Pageawss1i/assay | 102 | — | ~712 | Automated safety check: Pass | MIT | |
| Self-Contained HTML PagesSourceWeft/SourceWeft | 158 | — | ~817 | Automated safety check: Pass | Custom licence | |
| Design Lintaiskillstore/marketplace | 430 | — | ~1.4k | Automated safety check: Notes | None | |
| LobeHub Interactive Prototypelobehub/lobehub | 83k | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Paperclip Pagepaperclipai/paperclip | 98k | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
Self-Contained HTML Pages
SourceWeft/SourceWeft
Builds and revises polished offline HTML reports, landing pages, infographics and interactive visualizations as a single file, with viewport QA before delivery.
Design Lint
aiskillstore/marketplace
결정론적(no-LLM) 디자인 안티패턴 린터. An agent skill from aiskillstore/marketplace.
LobeHub Interactive Prototype
lobehub/lobehub
Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.
Paperclip Page
paperclipai/paperclip
Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host.
Openkb Deck Neon
VectifyAI/OpenKB
A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow /…
More from autonomous-ai/openharness
All 99 skills in this repoG-code Slicer Tool
autonomous-ai/openharness
Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.
Home Assistant Automation Builder
autonomous-ai/openharness
Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.
Score Music Composer
autonomous-ai/openharness
Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.
OrcaSlicer 3MF and G-code Workflow
autonomous-ai/openharness
Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.
Sheets and Docs Report Builder
autonomous-ai/openharness
Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.
Bambu Labs
autonomous-ai/openharness
Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.
Related
Works with
Categories
Questions about Web
What does Web do?
Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview. Web is an agent skill from autonomous-ai/openharness. Build and verify interactive HTML experiences in Web Studio's live, sandboxed preview.
When should I use Web?
Web fits situations like: tasks that involve HTML artifacts.
How do I install Web in Claude Code?
Run `npx skills add autonomous-ai/openharness --skill web -a claude-code`. Or copy the skill folder (store/agents/web-studio/skills/web in autonomous-ai/openharness) into .claude/skills/web in your project. Claude Code loads it when a task matches its description.
How do I install Web in Codex?
Run `npx skills add autonomous-ai/openharness --skill web -a codex`. Or copy the skill folder (store/agents/web-studio/skills/web in autonomous-ai/openharness) into .agents/skills/web in your project. Codex loads it when a task matches its description.
Can I use Web 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 autonomous-ai/openharness --skill web -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, .gemini/skills/web, .github/skills/web and .opencode/skills/web in your project.
What does Web need to run?
Going by SKILL.md and its folder, Web needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js.
Does Web 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 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 Web use?
Web is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Web use?
About 518 tokens (SKILL.md is roughly 2.1k 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?
Skills that share tags, products or a category with Web: Checking A Page (awss1i/assay, 102 stars), Self-Contained HTML Pages (SourceWeft/SourceWeft, 158 stars), Design Lint (aiskillstore/marketplace, 430 stars) and LobeHub Interactive Prototype (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Web?
autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,137 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 7, 2026.
Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.