Invisible Playwright
feder-cr/invisible_dots
Use the Dot's browser (invisibleplaywright) for any task on a website: logging in, reading pages, filling forms, clicking through a site as a person would.
Run an end-to-end JS8 message round-trip between two virtual wfweb rigs.
$ npx skills add adecarolis/wfweb --skill js8-test -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install adecarolis/wfweb js8-test --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/adecarolis/wfweb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/js8-test .claude/skills/js8-test && 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 "js8-test" agent skill from https://github.com/adecarolis/wfweb/tree/master/.claude/skills/js8-test into .claude/skills/js8-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "js8-test", 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/adecarolis/wfweb/tree/master/.claude/skills/js8-testType 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 adecarolis/wfweb --skill js8-test -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install adecarolis/wfweb js8-test --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adecarolis/wfweb.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/js8-test .agents/skills/js8-test && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "js8-test" agent skill from https://github.com/adecarolis/wfweb/tree/master/.claude/skills/js8-test into .agents/skills/js8-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "js8-test", 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 adecarolis/wfweb --skill js8-test -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install adecarolis/wfweb js8-test --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adecarolis/wfweb.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/js8-test .cursor/skills/js8-test && 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 "js8-test" agent skill from https://github.com/adecarolis/wfweb/tree/master/.claude/skills/js8-test into .cursor/skills/js8-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "js8-test", 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/adecarolis/wfweb.git --path .claude/skills/js8-test--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 adecarolis/wfweb --skill js8-test -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install adecarolis/wfweb js8-test --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adecarolis/wfweb.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/js8-test .gemini/skills/js8-test && 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 "js8-test" agent skill from https://github.com/adecarolis/wfweb/tree/master/.claude/skills/js8-test into .gemini/skills/js8-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "js8-test", 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 adecarolis/wfweb js8-testInstalls 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 adecarolis/wfweb --skill js8-test -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/adecarolis/wfweb.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/js8-test .github/skills/js8-test && 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 "js8-test" agent skill from https://github.com/adecarolis/wfweb/tree/master/.claude/skills/js8-test into .github/skills/js8-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "js8-test", 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 adecarolis/wfweb --skill js8-test -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install adecarolis/wfweb js8-test --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adecarolis/wfweb.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/js8-test .opencode/skills/js8-test && 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 "js8-test" agent skill from https://github.com/adecarolis/wfweb/tree/master/.claude/skills/js8-test into .opencode/skills/js8-test/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "js8-test", 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.
js8-testRun an end-to-end JS8 message round-trip between two virtual wfweb rigs.
Js8 Test is an agent skill from adecarolis/wfweb. Run an end-to-end JS8 message round-trip between two virtual wfweb rigs. Boots the testrig bench, drives both browsers via Playwright MCP, has each station send a directed JS8 message via the compose box while the other decodes it into its feed, verifies the copy, screenshots both, and tears down. Use when the user asks to test JS8, run a JS8 QSO, verify the JS8 codec/panel, or validate the JS8 messenger TX/RX path. (wfweb-vs-wfweb on the bench — not interop against real JS8Call.)
Its SKILL.md is about 2.2k 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 Testing & QA, covering Browser testing. It works with Model Context Protocol and Playwright. The repository describes itself as: Turn any Icom transceiver into a web-accessible station. Headless wfview fork with browser-based control, audio streaming, SSB, FreeDV, AX.25, CW, JS8 and FT8. The licence is GPL-3.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 7cd5d2f. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
makeFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Js8 Test loads about 2.2k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 1,074 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.
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.
The full file from adecarolis/wfweb at commit 7cd5d2f, republished under its GPL-3.0 licence (© adecarolis). 1,074 words, ~2,190 tokens.
.claude/skills/js8-test/SKILL.md (or your agent's skills folder).Run an end-to-end JS8 message round-trip between two virtual rigs: each station sends a directed message from the compose box, and the other must decode it into its feed. Drive both browsers via Playwright MCP, screenshot both sides, tear down. Bench-only (virtual rigs, no hardware, no real RF) — this tests wfweb's JS8 codec against itself, not interop with real JS8Call.
Sibling of packet-test / ft8-test / cw-test; reuses the same bench (scripts/testrig.sh) and Playwright lifecycle. JS8 is browser-side WASM like FT8, so it shares FT8's RX-audio gate and slot timing. Read "Pitfalls" before debugging.
./wfweb and ./tools/virtualrig/virtualrig are built. If not: qmake wfweb.pro && make -j$(nproc) and cd tools/virtualrig && qmake && make -j$(nproc)..mcp.json includes --ignore-https-errors for the playwright MCP. Verify: pgrep -af @playwright/mcp must show --ignore-https-errors. If .mcp.json was just edited, the user must restart Claude Code (a /mcp reconnect re-uses cached args). Stop and tell them.select:mcp__playwright__browser_navigate,mcp__playwright__browser_snapshot,mcp__playwright__browser_click,mcp__playwright__browser_type,mcp__playwright__browser_take_screenshot,mcp__playwright__browser_wait_for,mcp__playwright__browser_evaluate,mcp__playwright__browser_close,mcp__playwright__browser_tabs,mcp__playwright__browser_select_option../scripts/testrig.sh up 2Both rigs come up on 14.074.000. Opening the JS8 panel auto-retunes each rig to the JS8 dial frequency for the band (14.078.000 on 20 m) and forces USB — both move together, so they stay matched and audio gates.
The JS8 panel is an overlay (#js8Bar), opened from the MODE overlay's JS8 button — it's a peer of the FT8 DIGI bar (opening one closes the other).
browser_navigate to the rig URL.browser_evaluate () => { localStorage.clear(); sessionStorage.clear(); }, then browser_navigate to the same URL again. (Note: JS8 persists js8Open=1, so without the wipe a reload reopens the panel mid-init.)AudioContext).window._js8ProcessAudioChunk, which the host audio path only calls when audio is flowing. The splash enables it ~1 s asynchronously — poll until window.audioEnabled === true before continuing.window.toggleJs8Bar() (equivalently MODE → JS8). This forces USB, retunes to the JS8 dial freq, creates the decoder, and enables RX. Confirm window.js8MessengerVisible() === true and window.js8Diag().rxEnabled === true.#js8SettingsBtn), set #js8SettingMycall, then close (#js8SettingsCloseBtn). The callsign is committed to the shared station call (window.App.callsign) on close, not on input — so you must click close. Verify window.App.callsign.get() returns it.W1AAA. B: W1BBB. (Shared station call — same field feeds CW/FT8/FreeDV/APRS.)submode 0) is fine. RX decodes all submodes regardless, so the TX submode only affects the sender's frame timing.When refs go stale across snapshots, drive directly via browser_evaluate with stable IDs (the normal path, not a fallback):
js8SettingsBtn, js8SettingsCloseBtn, js8SendBtn, js8RxToggle, js8TuneBtn, js8CloseBtnjs8DxCall (the TO target — authoritative), js8Compose (message text), js8SettingMycall, js8SubmodeSel#js8Feed .textContent ← assert on this. Rows read <ts><from>→<target>│<msg><snr>dB; your own sent rows show SENT n/n.toggleJs8Bar(), js8MessengerVisible(), js8Diag() (returns {rxEnabled, txBusy, submode, decodes, audioChunks, …}), js8ClearFeed()S is not on window (unlike window.Packet.state). Use js8Diag() for status and read #js8Feed for messages.#js8DxCall to W1BBB (dispatch input), set #js8Compose to HELLO (dispatch input), click #js8SendBtn. This routes through enqueueTx, which slot-aligns the transmission. Use the compose+send path — do NOT use window.txJs8() (a raw 12-char test hook that streams un-slot-aligned audio and won't reliably decode).window.js8Diag().txBusy — it goes true on the next slot boundary, then false when done. A's own feed row shows W1AAA→W1BBB │ HELLO SENT 2/2. A short message is ~2 frames; with the wait-for-slot + TX time this takes ~25–35 s at Normal.#js8Feed.textContent until it contains both W1AAA and HELLO (allow ~30 s after A finishes). On the clean virtual channel the decode is solid (SNR ~+20 dB). Assert tolerantly — require the sender call and a recognizable chunk of the message, not byte-exact.#js8DxCall to W1AAA, #js8Compose to GE TNX, click #js8SendBtn.#js8Feed until it contains W1BBB and GE.browser_take_screenshot, fullPage: true. Save as .playwright-mcp/wfweb-js8-A.png and ...-B.png. (Bare names land in the project root; /tmp is rejected — the MCP roots are the project dir and .playwright-mcp/.)browser_close (both tabs), then ./scripts/testrig.sh down.#js8Feed).window.audioEnabled === true (enabled ~1 s after CLICK TO START). Gate on it. js8Diag().audioChunks should be climbing; if it's stuck at 0, audio isn't flowing.#js8SettingMycall does nothing until you click #js8SettingsCloseBtn — that's where App.callsign.set() runs. Verify via window.App.callsign.get().#js8SendBtn, not window.txJs8(). txJs8 requires an exact-12-char message and streams immediately without slot alignment — JS8's per-slot decoder usually won't catch it. The compose path slot-aligns via enqueueTx, which is what actually works.js8Diag().submode confirms the TX submode; a faster submode (Fast 10 s / JS8 60 4 s) speeds the run but RX decodes all modes either way.#js8DxCall → S.dxCall) is the authoritative target, not the active QSO tab. Set it before each send. Empty defaults to @ALLCALL (a broadcast, which B still decodes — fine if you prefer the simpler broadcast assert).S is not on window. Read message state from #js8Feed.textContent and status from window.js8Diag(). Don't look for window.js8.state or similar.SENT n/n; the received copy on the other tab shows an …dB SNR. Assert the receiver's feed has the sender's call — don't accidentally match the sender's own SENT row.localStorage.clear() — JS8 persists js8Open and the last callsign; a clean slate avoids reopening the panel mid-init and stale calls.ref= handles re-render constantly; drive via browser_evaluate + the stable IDs above..playwright-mcp/; /tmp is rejected.© adecarolis, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/js8-test of adecarolis/wfweb.
Open the folder on GitHubat commit 7cd5d2f
Js8 Test 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 |
|---|---|---|---|---|---|---|
| Js8 Test this skilladecarolis/wfweb | 106 | — | ~2.2k | Automated safety check: Pass | GPL-3.0 | |
| Invisible Playwrightfeder-cr/invisible_dots | 32k | — | ~989 | Automated safety check: Pass | MIT | |
| Playwright E2E Testsonyx-dot-app/onyx | 32k | 1 repos | ~2.8k | Automated safety check: Notes | Custom licence | |
| Shogun Screenshotyohey-w/multi-agent-shogun | 1.4k | — | ~901 | Automated safety check: Notes | MIT | |
| Playwright Debugvoicetreelab/voicetree | 923 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Hands On Testktnyt/cclsp | 675 | — | ~1.7k | Automated safety check: Pass | MIT |
feder-cr/invisible_dots
Use the Dot's browser (invisibleplaywright) for any task on a website: logging in, reading pages, filling forms, clicking through a site as a person would.
onyx-dot-app/onyx
Write and maintain Playwright end-to-end tests for the Onyx application.
yohey-w/multi-agent-shogun
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。
voicetreelab/voicetree
This skill should be used when the user asks to "debug the electron app", "connect playwright to VoiceTree", "take screenshots of the running app", "interact with the live UI", "inspect the running…
ktnyt/cclsp
Performs manual hands-on testing of a web application using playwright-cli.
Chorus-AIDLC/Chorus
A skill your agent uses when manually verifying a Chorus frontend change in a real browser — finding local login credentials, driving the running dev server with the Playwright MCP, logging in…
adecarolis/wfweb
Run an end-to-end CW (morse) decode round-trip between two virtual wfweb rigs.
adecarolis/wfweb
Run an end-to-end FreeDV RADE EOO-callsign round-trip between two virtual wfweb rigs.
adecarolis/wfweb
Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs.
adecarolis/wfweb
Run an end-to-end AX.25 packet QSO test between two virtual wfweb rigs at 300 bd and 1200 bd.
Works with
Categories
Run an end-to-end JS8 message round-trip between two virtual wfweb rigs. Js8 Test is an agent skill from adecarolis/wfweb. Run an end-to-end JS8 message round-trip between two virtual wfweb rigs.
Js8 Test fits situations like: the user asks to test JS8; verify the JS8 codec/panel; validate the JS8 messenger TX/RX path.
Run `npx skills add adecarolis/wfweb --skill js8-test -a claude-code`. Or copy the skill folder (.claude/skills/js8-test in adecarolis/wfweb) into .claude/skills/js8-test in your project. Claude Code loads it when a task matches its description.
Run `npx skills add adecarolis/wfweb --skill js8-test -a codex`. Or copy the skill folder (.claude/skills/js8-test in adecarolis/wfweb) into .agents/skills/js8-test in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adecarolis/wfweb --skill js8-test -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/js8-test, .gemini/skills/js8-test, .github/skills/js8-test and .opencode/skills/js8-test in your project.
Going by SKILL.md and its folder, Js8 Test needs the command-line tools its instructions call (make).
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.
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.
Js8 Test is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Js8 Test: Invisible Playwright (feder-cr/invisible_dots, 32k stars), Playwright E2E Tests (onyx-dot-app/onyx, 32k stars), Shogun Screenshot (yohey-w/multi-agent-shogun, 1.4k stars) and Playwright Debug (voicetreelab/voicetree, 923 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
adecarolis (a GitHub user) maintains it in adecarolis/wfweb, which has 106 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 7, 2026.
Source: adecarolis/wfweb on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.