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

Verify

by WeZZard in WeZZard/jlens-qwen36

Build/launch/drive recipe for verifying jlens-qwen36 UI and server changes end-to-end in a real headless browser.

Apache-2.0Auto-check passedProductivity & Automation

Install Verify

skills CLI
$ npx skills add WeZZard/jlens-qwen36 --skill verify -a claude-code

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

GitHub CLI
$ gh skill install WeZZard/jlens-qwen36 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/WeZZard/jlens-qwen36.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/verify .claude/skills/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
verify
GitHub stars
402
Token cost
~684 tokens
SKILL.md length
252 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0

At a glance

Build/launch/drive recipe for verifying jlens-qwen36 UI and server changes end-to-end in a real headless browser.

  • Tasks that involve Browser automation
  • SKILL.md covers Launch the server, Drive the UI headlessly, Flows worth driving and Gotchas
  • Calls node and uv
  • Tasks that involve End-to-end testing

What it does

Verify is an agent skill from WeZZard/jlens-qwen36. Build/launch/drive recipe for verifying jlens-qwen36 UI and server changes end-to-end in a real headless browser.

Its SKILL.md is about 680 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 Productivity & Automation, covering Browser automation and End-to-end testing. The repository describes itself as: J-space / Jacobian-lens visualizer for Qwen3.6-27B (4-bit) on Apple Silicon, ported to Apple MLX. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Browser automation
  • Tasks that involve End-to-end testing

Example prompts

  • “/verify”

Requirements

  • Python 3
  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit b05ceff. 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

    Shell commands in SKILL.md call:

    • node
    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, 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

Verify loads about 684 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 252 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~684

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 WeZZard/jlens-qwen36 at commit b05ceff, republished under its Apache-2.0 licence (© WeZZard). 252 words, ~684 tokens.

Download SKILL.mdSave it as .claude/skills/verify/SKILL.md (or your agent's skills folder).
name
verify
description
Build/launch/drive recipe for verifying jlens-qwen36 UI and server changes end-to-end in a real headless browser.

Verify jlens-qwen36 changes

Launch the server

bash
JLENS_PATH=data/lens/qwen36_27b_neuronpedia_n1000.npz \
  uv run python -m uvicorn jlens_qwen.serve:app --host 127.0.0.1 --port 8765

Poll GET /api/lens until it answers and confirm "n_prompts": 1000 before interpreting any result (project rule; startup takes ~30–60 s).

Drive the UI headlessly

The repo has no Node dependency tree. The Playwright MCP server needs Google Chrome, which is not installed — use a Node driver with a cached Chromium instead, following scripts/e2e_intervention_playwright.cjs:

bash
# Find a usable playwright install (npx cache works):
for d in ~/.npm/_npx/*/node_modules; do [ -d "$d/playwright" ] && echo "$d"; done
# Pick one whose chromium exists:
NODE_PATH=<dir> node -e "console.log(require('playwright').chromium.executablePath())"

NODE_PATH=<dir> node your-driver.cjs   # chromium.launch({ headless: true })

Driver facts that hold for web/index.html (single classic script):

  • Top-level bindings (state, _wish, $, addIntervention, rerunWithInterventions, setActiveVariant, …) are reachable from page.evaluate even when declared with let/const.
  • Send a chat turn: click #chat-editor, type, press Enter; then poll !state.streaming && state.messages.at(-1).tokens.length > 0. One short turn takes ~60–90 s (27B model + per-token lens readouts).
  • Backward-search (wish) flow: click a reply token (#chat-log .tok, e.g. hasText 'Paris'), fill #wish-input, press Enter. Search requests go to /api/intervention_search_adaptive; candidate replays advance roughly one per second.
  • A real intervened A/B rerun: addIntervention({... mode: 'swap', token: ' Paris', target: ' Beijing', alpha: 1, layers: [52], scope: { type: 'at', pos: firstGeneratedPos() - 1 } ...}) then rerunWithInterventions(). The server resolves token text to ids.

Flows worth driving

  • Clean baseline chat → wish search starts (progress track, stats, pause button, recipes pill "N tested · search running").
  • Dirty baseline (applied or enabled interventions) → wish refusal modal, no search state, no /api/intervention_search_adaptive POST.
  • A/B compare: variant toggle labels (Baseline/Run A + config label), switching variants with setActiveVariant(false|true).

Gotchas

  • Check the uvicorn log for exactly the requests you expect; refusals and client-side guards send nothing.
  • state.appliedInterventions is frozen per run; only a fresh clean run, clearState(), or switching to a clean variant empties it.

© WeZZard, 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 .claude/skills/verify of WeZZard/jlens-qwen36.

Open the folder on GitHubat commit b05ceff

Compare with similar skills

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.

Verify compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Verify this skillWeZZard/jlens-qwen36402—~684Automated safety check: PassApache-2.0
Electron App Automationvercel-labs/agent-browser44k5 repos~1.7kAutomated safety check: PassApache-2.0
Snaplii AutopilotSnaplii-Inc/agent-to-merchant-payments813—~4.4kAutomated safety check: PassNone
Actionbook Browser Action Manualssmallnest/goclaw5991 repos~4.1kAutomated safety check: WarnMIT
Browser Automationmozilla/firefox-devtools-mcp474—~807Automated safety check: PassCustom licence
Patchright Skillaiskillstore/marketplace430—~1.6kAutomated safety check: PassMIT

Similar skills

  • Electron App Automation

    vercel-labs/agent-browser

    Official

    Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port.

    44k GitHub starsUsed in 5 repos~1.7k tokens
    Productivity & AutomationAuto-check passed

  • Snaplii Autopilot

    Snaplii-Inc/agent-to-merchant-payments

    End-to-end Agent-to-Merchant autopilot: buy a Snaplii gift card with cashback, then drive the browser to redeem it on the merchant/delivery site and place the order — all in one flow.

    813 GitHub stars~4.4k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

  • Actionbook Browser Action Manuals

    smallnest/goclaw

    Looks up action manuals with verified selectors for multi-step website tasks, then drives the browser with the actionbook CLI in a dedicated or an existing Chrome session.

    599 GitHub starsUsed in 1 repo~4.1k tokens
    Productivity & AutomationAuto-check: warnings

  • Browser Automation

    mozilla/firefox-devtools-mcp

    This skill should be used when the user asks about browser automation, testing web pages, extracting content, filling forms, taking screenshots, or monitoring console/network activity.

    474 GitHub stars~807 tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

  • Patchright Skill

    aiskillstore/marketplace

    Patchright-based browser automation with bot detection bypass.

    430 GitHub stars~1.6k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • playwright-cli Browser Automation

    github/gh-aw

    Official

    Drives a real browser from the command line with playwright-cli to open pages, interact, mock requests, save state and work with Playwright tests.

    5.4k GitHub starsUsed in 23 repos~2.8k tokens
    Testing & QAAuto-check passed

Categories

Questions about Verify

What does Verify do?

Build/launch/drive recipe for verifying jlens-qwen36 UI and server changes end-to-end in a real headless browser. Verify is an agent skill from WeZZard/jlens-qwen36. Build/launch/drive recipe for verifying jlens-qwen36 UI and server changes end-to-end in a real headless browser.

When should I use Verify?

Verify fits situations like: tasks that involve Browser automation; tasks that involve End-to-end testing.

How do I install Verify in Claude Code?

Run `npx skills add WeZZard/jlens-qwen36 --skill verify -a claude-code`. Or copy the skill folder (.claude/skills/verify in WeZZard/jlens-qwen36) into .claude/skills/verify in your project. Claude Code loads it when a task matches its description.

How do I install Verify in Codex?

Run `npx skills add WeZZard/jlens-qwen36 --skill verify -a codex`. Or copy the skill folder (.claude/skills/verify in WeZZard/jlens-qwen36) into .agents/skills/verify in your project. Codex loads it when a task matches its description.

Can I use 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 WeZZard/jlens-qwen36 --skill 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/verify, .gemini/skills/verify, .github/skills/verify and .opencode/skills/verify in your project.

What does Verify need to run?

Going by SKILL.md and its folder, Verify needs the command-line tools its instructions call (node and uv). Our summary lists: Python 3; Node.js.

Does Verify access the network?

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

Is 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 Verify use?

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 Verify use?

About 684 tokens (SKILL.md is roughly 2.7k 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 Verify?

Skills that share tags, products or a category with Verify: Electron App Automation (vercel-labs/agent-browser, 44k stars), Snaplii Autopilot (Snaplii-Inc/agent-to-merchant-payments, 813 stars), Actionbook Browser Action Manuals (smallnest/goclaw, 599 stars) and Browser Automation (mozilla/firefox-devtools-mcp, 474 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Verify?

WeZZard (a GitHub user) maintains it in WeZZard/jlens-qwen36, which has 402 GitHub stars. The repository was last updated on September 8, 2026.

Source: WeZZard/jlens-qwen36 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.