New: 97,000+ 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

Ft8 Test

by adecarolis in adecarolis/wfweb

Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs.

GPL-3.0Auto-check passedTesting & QA

Install Ft8 Test

skills CLI
$ npx skills add adecarolis/wfweb --skill ft8-test -a claude-code

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

GitHub CLI
$ gh skill install adecarolis/wfweb ft8-test --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/adecarolis/wfweb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ft8-test .claude/skills/ft8-test && 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
ft8-test
GitHub stars
100
Token cost
~2k tokens
SKILL.md length
984 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
GPL-3.0

At a glance

Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs.

  • Works in 3 steps: ./wfweb and… → Repo .mcp.json includes… → Load the playwright tools via…
  • The user asks to test FT8
  • SKILL.md covers Prerequisites (verify before…, Boot the bench, Per-tab UI bring-up (do for… and QSO sequence (single run — FT8), plus 2 more sections
  • Calls make

What it does

Ft8 Test is an agent skill from adecarolis/wfweb. Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs. Boots the testrig bench, drives both browsers via Playwright MCP, has each station CALL CQ on opposite slot parity, verifies each side decodes the other's CQ, screenshots both, and tears down. Use when the user asks to test FT8, run an FT8 QSO/decode, verify the ft8ts decoder, or validate the DIGI panel TX/RX path. (FT4 is a fast variant of the same panel — see the FT4 note; not run by default.)

Its SKILL.md is about 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.

When your agent uses it

  • The user asks to test FT8
  • Run an FT8 QSO/decode
  • Verify the ft8ts decoder
  • Validate the DIGI panel TX/RX path

Example prompts

  • “/ft8-test”

Workflow steps

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

  1. ./wfweb and ./tools/virtualrig/virtualrig are built. If not: qmake wfweb.pro && make -j$(nproc) and cd tools/virtualrig && qmake && make…
  2. Repo .mcp.json includes --ignore-https-errors for the playwright MCP (wfweb's cert is self-signed; without it chromium fails with…
  3. Load the playwright tools via ToolSearch: select:mcpplaywrightbrowser_navigate,mcpplaywrightbrowser_snapshot,mcpplaywrightbrowser_click,mcp…

What it can do on your machine

Read from SKILL.md and the folder at commit 3a5ae69. 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:

    • make

    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

Ft8 Test loads about 2k tokens when it runs. Until then it costs about 120 tokens; SKILL.md has 984 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~120
When it runs · the whole SKILL.md, loaded when a task matches
~2k

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 adecarolis/wfweb at commit 3a5ae69, republished under its GPL-3.0 licence (© adecarolis). 984 words, ~1,993 tokens.

Download SKILL.mdSave it as .claude/skills/ft8-test/SKILL.md (or your agent's skills folder).
name
ft8-test
description
Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs. Boots the testrig bench, drives both browsers via Playwright MCP, has each station CALL CQ on opposite slot parity, verifies each side decodes the other's CQ, screenshots both, and tears down. Use when the user asks to test FT8, run an FT8 QSO/decode, verify the ft8ts decoder, or validate the DIGI panel TX/RX path. (FT4 is a fast variant of the same panel — see the FT4 note; not run by default.)

Run an end-to-end FT8 decode round-trip between two virtual rigs: each station calls CQ on opposite slot parity, and each must decode the other's CQ. Drive both browsers via Playwright MCP, screenshot both sides, tear down. This is bench-only (virtual rigs, no hardware, no real RF).

This skill is the FT8 sibling of packet-test and reuses the same bench (scripts/testrig.sh) and Playwright lifecycle. Read the "Pitfalls" section before debugging — FT8 has one gotcha packet doesn't (RX audio must be enabled for the decoder to see anything).

Prerequisites (verify before starting; fix and stop if missing)

  1. ./wfweb and ./tools/virtualrig/virtualrig are built. If not: qmake wfweb.pro && make -j$(nproc) and cd tools/virtualrig && qmake && make -j$(nproc).
  2. Repo .mcp.json includes --ignore-https-errors for the playwright MCP (wfweb's cert is self-signed; without it chromium fails with ERR_CERT_AUTHORITY_INVALID). Verify the running MCP: 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.
  3. Load the playwright tools via ToolSearch: 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.

Boot the bench

./scripts/testrig.sh up 2

Both rigs come up on 14.074.000 USB — which is the 20 m FT8 dial frequency, so no retune is needed and audio gates (matching freq+mode) just like real FT8.

Per-tab UI bring-up (do for both A and B)

The FT8 panel is the DIGI bar, toggled from the MODE overlay (the FT8 button toggles the bar; it does NOT change rig mode — opening it forces USB + the FT8 dial freq automatically).

  1. browser_navigate to the rig URL.
  2. Wipe stale browser state (Playwright reuses its profile across runs): browser_evaluate () => { localStorage.clear(); sessionStorage.clear(); }, then browser_navigate to the same URL again.
  3. Click the CLICK TO START splash (browsers refuse AudioContext without a gesture).
  4. Wait for RX audio to come up. This is the FT8-specific step packet doesn't need: the decoder only runs on RX audio, and the splash enables it asynchronously ~1 s after START. Poll until window.audioEnabled === true before continuing — otherwise no audio reaches the decoder and nothing ever decodes.
  5. Open MODE, then click the FT8 button (find by text FT8 among visible buttons). Confirm window.digiBarVisible === true.
  6. Open settings (#digiSettingsBtn), set MY CALL (#digiMyCall) and GRID (#digiGrid), then close (#digiSettingsCloseBtn). Dispatch input events so the handlers fire.
    • A: W1AAA / FN20. B: W1BBB / FN21.
    • Both call AND grid are required — digiCallCq() silently aborts (and pops the settings modal) if either is missing. The callsign is the shared station call (CW/FT8/JS8/FreeDV/APRS) — that's by design.
  7. Set opposite slot parity. A keeps the default TX EVEN (digiCqParity === 0). On B, click #digiCqParityBtn once to flip it to TX ODD (digiCqParity === 1). Opposite parity is mandatory: a station can't receive while it transmits, so if both call CQ on the same parity they transmit in the same slot and never hear each other.

When refs go stale across snapshots, drive directly via browser_evaluate with stable IDs (this is the normal path, not a fallback):

  • Buttons: digiSettingsBtn, digiSettingsCloseBtn, digiCqParityBtn, digiCallCqBtn, digiEnableTxBtn, digiHaltBtn, digiTuneBtn, digiCloseBtn
  • Fields: digiMyCall, digiGrid, digiDxCall
  • Functions (global): digiCallCq(), getMyCall(), getMyGrid(), toggleDigiBar(), getDigiSlotInfo()
  • State (globals on window — classic script, NOT a namespaced object): digiDecodes (array of {msg, snr, dt, freq, time, slotIndex}), digiMode ('FT8'/'FT4'), digiCqParity, digiTxEnabled, digiTxArmed, digiTxQueued, digiTxActive, audioEnabled, digiBarVisible
Show full SKILL.md (444 more words)Show less

QSO sequence (single run — FT8)

  1. Both → CALL CQ: on each tab call window.digiCallCq() (or click #digiCallCqBtn). This arms CQ <call> <grid> and enables TX. Confirm digiTxQueued is "CQ W1AAA FN20" on A and "CQ W1BBB FN21" on B.
  2. Wait for decodes (FT8 slots are 15 s; a decode appears only after a full slot completes). Poll up to ~75 s:
    • On A: window.digiDecodes contains an entry whose msg matches CQ W1BBB FN21.
    • On B: window.digiDecodes contains an entry whose msg matches CQ W1AAA FN20.
    • In practice the first decode lands in ~10–20 s. Each entry carries a real snr/dt/freq — sanity-check the SNR is finite (a genuine decode, not an empty array).
  3. Screenshot both with browser_take_screenshot, fullPage: true. Save as .playwright-mcp/wfweb-ft8-A.png and ...-B.png. (The MCP does NOT auto-target .playwright-mcp/ — bare names land in the project root; /tmp is rejected as outside the allowed roots.)
  4. Halt TX on both: click #digiHaltBtn (sets digiTxEnabled = false). Good hygiene even on a virtual rig.

Teardown and report

  1. browser_close (both tabs), then ./scripts/testrig.sh down.
  2. Report PASS/FAIL and the two screenshot paths. PASS = each side decoded the other's CQ with a finite SNR.

Pitfalls — read before debugging

  • The decoder needs RX audio. handleAudioData() returns early when audioEnabled is false (no PCM reaches processDigiAudioChunk). CLICK TO START enables audio ~1 s later, so gate on window.audioEnabled === true before expecting decodes. This is the #1 cause of "nothing decodes".
  • Opposite parity is mandatory. Same parity on both ⇒ simultaneous TX ⇒ each is deaf during the other's transmission ⇒ zero decodes. A = TX EVEN, B = TX ODD.
  • Call + grid both required. No grid ⇒ digiCallCq() aborts and opens the settings modal; you'll see TX never arm.
  • FT8 is slot-timed. Don't expect an instant decode — poll for up to ~75 s (a few 15 s slots). getDigiSlotInfo() returns {slotIndex, slotPhase, remaining, period} if you need to reason about timing.
  • digiDecodes is a window global, not window.Something.state. Read window.digiDecodes directly. (Packet uses window.Packet.state; FT8 does not — it predates that pattern and uses top-level vars.)
  • Don't skip localStorage.clear() — prior runs leave a saved callsign/grid and could boot into a stale state. Clean-slate mirrors a fresh user.
  • Stale Playwright ref= handles re-render constantly; drive via browser_evaluate + the stable IDs above.
  • Screenshots are sandboxed to the project dir / .playwright-mcp/; /tmp is rejected.
  • FT4 variant (optional, not run by default): clicking the mode label (#digiModeLabel) toggles FT8 ↔ FT4; FT4 uses 7.5 s slots (digiPeriod() returns 7.5) so the round-trip is ~2× faster. To test FT4, toggle it on both tabs before CALL CQ and match the assert messages (same CQ <call> <grid> text). Both rigs must be in the same submode or they won't decode each other.

© 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

Files

Just SKILL.md in .claude/skills/ft8-test of adecarolis/wfweb.

Open the folder on GitHubat commit 3a5ae69

Compare with similar skills

Ft8 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.

Ft8 Test compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ft8 Test this skilladecarolis/wfweb100—~2kAutomated safety check: PassGPL-3.0
Playwright E2E Testsonyx-dot-app/onyx32k1 repos~2.8kAutomated safety check: NotesCustom licence
Shogun Screenshotyohey-w/multi-agent-shogun1.4k—~901Automated safety check: NotesMIT
Playwright Debugvoicetreelab/voicetree922—~1.2kAutomated safety check: PassCustom licence
Hands On Testktnyt/cclsp675—~1.7kAutomated safety check: PassMIT
E2E VerificationChorus-AIDLC/Chorus1.2k—~1.5kAutomated safety check: NotesAGPL-3.0

Similar skills

  • Playwright E2E Tests

    onyx-dot-app/onyx

    Write and maintain Playwright end-to-end tests for the Onyx application.

    32k GitHub starsUsed in 1 repo~2.8k tokens
    Testing & QAAuto-check: notes

  • Shogun Screenshot

    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。

    1.4k GitHub stars~901 tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes

  • Playwright Debug

    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…

    922 GitHub stars~1.2k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed

  • Hands On Test

    ktnyt/cclsp

    Performs manual hands-on testing of a web application using playwright-cli.

    675 GitHub stars~1.7k tokensUpdated 7 mo ago
    Testing & QAAuto-check passed

  • E2E Verification

    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…

    1.2k GitHub stars~1.5k tokensUpdated today
    Testing & QAAuto-check: notes

  • UI Regression Recorder

    xuxh21/ui-regression-recorder-skill

    A skill your agent uses when the user says to initialize the current project for UI regression, record an operation, convert Playwright codegen recordings into stable tests, extract shared helpers…

    112 GitHub stars~4.4k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed

More from adecarolis/wfweb

  • Cw Test

    adecarolis/wfweb

    Run an end-to-end CW (morse) decode round-trip between two virtual wfweb rigs.

    100 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed

  • Freedv Test

    adecarolis/wfweb

    Run an end-to-end FreeDV RADE EOO-callsign round-trip between two virtual wfweb rigs.

    100 GitHub stars~2.8k tokensUpdated 3 days ago
    Auto-check passed

  • Js8 Test

    adecarolis/wfweb

    Run an end-to-end JS8 message round-trip between two virtual wfweb rigs.

    100 GitHub stars~2.2k tokensUpdated 3 days ago
    Auto-check passed

  • Packet Test

    adecarolis/wfweb

    Run an end-to-end AX.25 packet QSO test between two virtual wfweb rigs at 300 bd and 1200 bd.

    100 GitHub stars~1.7k tokensUpdated 3 days ago
    Auto-check passed

Works with

Categories

Questions about Ft8 Test

What does Ft8 Test do?

Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs. Ft8 Test is an agent skill from adecarolis/wfweb. Run an end-to-end FT8 decode round-trip between two virtual wfweb rigs.

When should I use Ft8 Test?

Ft8 Test fits situations like: the user asks to test FT8; run an FT8 QSO/decode; verify the ft8ts decoder; validate the DIGI panel TX/RX path.

How do I install Ft8 Test in Claude Code?

Run `npx skills add adecarolis/wfweb --skill ft8-test -a claude-code`. Or copy the skill folder (.claude/skills/ft8-test in adecarolis/wfweb) into .claude/skills/ft8-test in your project. Claude Code loads it when a task matches its description.

How do I install Ft8 Test in Codex?

Run `npx skills add adecarolis/wfweb --skill ft8-test -a codex`. Or copy the skill folder (.claude/skills/ft8-test in adecarolis/wfweb) into .agents/skills/ft8-test in your project. Codex loads it when a task matches its description.

Can I use Ft8 Test 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 adecarolis/wfweb --skill ft8-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/ft8-test, .gemini/skills/ft8-test, .github/skills/ft8-test and .opencode/skills/ft8-test in your project.

What does Ft8 Test need to run?

Going by SKILL.md and its folder, Ft8 Test needs the command-line tools its instructions call (make).

Does Ft8 Test 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 Ft8 Test 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 Ft8 Test use?

Ft8 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.

How many tokens does Ft8 Test use?

About 2k tokens (SKILL.md is roughly 8k 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 Ft8 Test?

Skills that share tags, products or a category with Ft8 Test: Playwright E2E Tests (onyx-dot-app/onyx, 32k stars), Shogun Screenshot (yohey-w/multi-agent-shogun, 1.4k stars), Playwright Debug (voicetreelab/voicetree, 922 stars) and Hands On Test (ktnyt/cclsp, 675 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ft8 Test?

adecarolis (a GitHub user) maintains it in adecarolis/wfweb, which has 100 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 5, 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.