Agent skill

Frontend Test Worker

by CorrectRoadH in CorrectRoadH/OpenTickly

Build and verify page-flow and E2E coverage for the tracking browser surface.

AGPL-3.0Auto-check passedTesting & QA

Install Frontend Test Worker

skills CLI
$ npx skills add CorrectRoadH/OpenTickly --skill frontend-test-worker -a claude-code

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

GitHub CLI
$ gh skill install CorrectRoadH/OpenTickly frontend-test-worker --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/CorrectRoadH/OpenTickly.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.factory/skills/frontend-test-worker .claude/skills/frontend-test-worker && 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
frontend-test-worker
GitHub stars
306
Token cost
~1.4k tokens
SKILL.md length
542 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Build and verify page-flow and E2E coverage for the tracking browser surface.

  • Works in 12 steps: Read mission.md, mission AGENTS.md,… → Identify which validation assertions the… → Write or update failing frontend tests… → …
  • Tasks that involve End-to-end testing
  • SKILL.md covers When to Use This Skill, Required Skills, Work Procedure and Example Handoff, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Frontend Test Worker is an agent skill from CorrectRoadH/OpenTickly. Build and verify page-flow and E2E coverage for the tracking browser surface.

Its SKILL.md is about 1.4k 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 End-to-end testing. It works with Playwright. The repository describes itself as: Self-hosted, Toggl-compatible time tracker. The licence is AGPL-3.0.

When your agent uses it

  • Tasks that involve End-to-end testing

Example prompts

  • “/frontend-test-worker”

Workflow steps

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

  1. Read mission.md, mission AGENTS.md, .factory/services.yaml, and .factory/library/user-testing.md.
  2. Identify which validation assertions the feature fulfills and treat those as the non-negotiable acceptance checklist.
  3. Write or update failing frontend tests first
  4. Keep E2E naming aligned with the mission rule: E2E already means real runtime, so new tests should use normal *.spec.ts.
  5. Reuse local runtime on 5173 and 8080; do not move to alternate local ports unless the orchestrator changes the boundary.
  6. When the feature is about navigation or reachability, prove it by clicking through the visible shell UI instead of only using direct goto.
  7. When the feature is about timer page-family behavior, verify calendar, list, and timesheet under the same seeded facts and stable /timer…
  8. Run the narrowest relevant frontend tests during iteration, then rerun the broader website E2E command(s) affected by the feature.
  9. Use agent-browser after the automated tests pass to confirm one real story path and capture any mismatch between runtime behavior and the…
  10. If the feature claims a code fix, verify that the commitId reported in the handoff directly contains the feature's code changes. If the…
  11. Do not treat a rerun-only pass as completion for a flaky-fix feature. If the assigned fix was stabilizing a flaky path, the handoff must…
  12. Keep the fix scoped to the assigned feature. If a flaky-fix or validator-repair change seems to require unrelated assertion rewrites or…

What it can do on your machine

Read from SKILL.md and the folder at commit 5ffd0a0. 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 (its code samples are json).

    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

Frontend Test Worker loads about 1.4k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 542 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 CorrectRoadH/OpenTickly at commit 5ffd0a0, republished under its AGPL-3.0 licence (© CorrectRoadH). 542 words, ~1,443 tokens.

Download SKILL.mdSave it as .claude/skills/frontend-test-worker/SKILL.md (or your agent's skills folder).
name
frontend-test-worker
description
Build and verify page-flow and E2E coverage for the tracking browser surface.

Frontend Test Worker

NOTE: Startup and cleanup are handled by worker-base. This skill defines the work procedure.

When to Use This Skill

Use for features that add or fix frontend page-flow tests, Playwright E2E coverage, browser fixtures, shell navigation checks, and workspace/timer view regressions.

Required Skills

  • vite-plus — use for repo-local JS/toolchain commands and website test execution.
  • agent-browser — use for manual browser verification of the changed story path on the reused local runtime.

Work Procedure

  1. Read mission.md, mission AGENTS.md, .factory/services.yaml, and .factory/library/user-testing.md.
  2. Identify which validation assertions the feature fulfills and treat those as the non-negotiable acceptance checklist.
  3. Write or update failing frontend tests first:
    • page-flow tests for page-family and state behavior
    • E2E for story-level acceptance
  4. Keep E2E naming aligned with the mission rule: E2E already means real runtime, so new tests should use normal *.spec.ts.
  5. Reuse local runtime on 5173 and 8080; do not move to alternate local ports unless the orchestrator changes the boundary.
  6. When the feature is about navigation or reachability, prove it by clicking through the visible shell UI instead of only using direct goto.
  7. When the feature is about timer page-family behavior, verify calendar, list, and timesheet under the same seeded facts and stable /timer URL. Do not stop at shared-header or container-level proof; each subview must have at least one view-local assertion for the seeded fact or running timer being verified.
  8. Run the narrowest relevant frontend tests during iteration, then rerun the broader website E2E command(s) affected by the feature.
  9. Use agent-browser after the automated tests pass to confirm one real story path and capture any mismatch between runtime behavior and the test surface. For narrow Playwright assertion-fix features that do not change browser-visible behavior beyond the covered assertions, passing real-runtime Playwright evidence is sufficient if no new manual/browser-only risk was introduced. If a pre-existing Chrome DevTools or agent-browser session conflict blocks manual verification, record that conflict in the handoff and rely on the passing real-runtime Playwright evidence instead of fabricating a manual check.
  10. If the feature claims a code fix, verify that the commitId reported in the handoff directly contains the feature's code changes. If the behavior was already fixed by an earlier commit or no scoped implementation was needed, say that explicitly instead of pointing at an unrelated commit.
  11. Do not treat a rerun-only pass as completion for a flaky-fix feature. If the assigned fix was stabilizing a flaky path, the handoff must identify the specific stabilization change that landed; otherwise return to orchestrator instead of claiming success.
  12. Keep the fix scoped to the assigned feature. If a flaky-fix or validator-repair change seems to require unrelated assertion rewrites or broader story changes, stop and return to orchestrator instead of bundling those extras into the same handoff.
  13. In the handoff, name the exact stories/assertions proven, the files added/changed, what was checked manually in the browser, and which assertions have explicit view-local proof versus shared-shell/shared-header proof.
Show full SKILL.md (49 more words)Show less

Example Handoff

json
{
  "salientSummary": "Added timer page-family browser coverage for `/timer` default calendar landing, subview switching, and shell navigation entry. Verified the same seeded running timer remains visible across calendar/list/timesheet on the reused 5173/8080 runtime.",
  "whatWasImplemented": "Created page-flow and Playwright coverage for the tracking timer mainline. The browser tests now prove direct `/timer` entry and shell navigation converge on the same timer state, `/timer` keeps a stable URL while subviews switch, and running/stopped timer facts remain consistent across calendar, list, and timesheet.",
  "whatWasLeftUndone": "",
  "verification": {
    "commandsRun": [
      {
        "command": "vp run test:e2e:website -- e2e/timer-page.spec.ts",
        "exitCode": 0,
        "observation": "Timer E2E passed against the reused local runtime."
      },
      {
        "command": "vp run check -r",
        "exitCode": 0,
        "observation": "Repo-wide JS checks passed after the frontend test updates."
      }
    ],
    "interactiveChecks": [
      {
        "action": "Used agent-browser to click the visible Timer nav item from the authenticated shell and then switched calendar/list/timesheet.",
        "observed": "The page stayed on `/timer`, Timer nav became active, and the same seeded timer facts remained visible according to each view."
      }
    ]
  },
  "tests": {
    "added": [
      {
        "file": "apps/website/e2e/timer-page.spec.ts",
        "cases": [
          {
            "name": "opens `/timer` on calendar and keeps stable URL while switching subviews",
            "verifies": "VAL-TIMER-001 and VAL-TIMER-002"
          },
          {
            "name": "shows the same running timer across calendar, list, and timesheet",
            "verifies": "VAL-TIMER-004"
          }
        ]
      }
    ]
  },
  "discoveredIssues": []
}

When to Return to Orchestrator

  • The story cannot be validated because reused 5173/8080 runtime is unavailable or unstable
  • The product docs and observed browser behavior conflict in a way that changes scope or semantics
  • The feature needs backend fixture or transport behavior that does not yet exist

© CorrectRoadH, AGPL-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 .factory/skills/frontend-test-worker of CorrectRoadH/OpenTickly.

Open the folder on GitHubat commit 5ffd0a0

Compare with similar skills

Frontend Test Worker 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.

Frontend Test Worker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Frontend Test Worker this skillCorrectRoadH/OpenTickly306—~1.4kAutomated safety check: PassAGPL-3.0
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
playwright-cli Browser Automationgithub/gh-aw5.4k24 repos~2.8kAutomated safety check: PassMIT
Write and Verify Playwright Testsappsmithorg/appsmith41k—~2.9kAutomated safety check: NotesApache-2.0
Cucumber and Playwright E2E Testslanggenius/dify158k—~682Automated safety check: PassCustom licence
E2E Testinglangflow-ai/langflow156k—~3.3kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • 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 24 repos~2.8k tokens
    Testing & QAAuto-check passed
  • Writes a Playwright end-to-end test from a prompt, runs it against a live Appsmith deployment and retries with fixes up to three times until it passes.

    41k GitHub stars~2.9k tokensUpdated yesterday
    Testing & QAAuto-check: notes
  • Guides changes and reviews of the Cucumber and Playwright end-to-end suite under `e2e/`: feature files, step definitions, support code, tags, locators and assertions.

    158k GitHub stars~682 tokensUpdated today
    Testing & QAAuto-check passed
  • E2E Testing

    langflow-ai/langflow

    Write and review Playwright E2E tests for Langflow. An agent skill from langflow-ai/langflow.

    156k GitHub stars~3.3k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • E2E

    callstack/react-native-pager-view

    Agentic end-to-end tests with e2e, the e2e runner. An agent skill from callstack/react-native-pager-view.

    3.4k GitHub starsUsed in 1 repo~2.1k tokens
    Testing & QAAuto-check passed

More from CorrectRoadH/OpenTickly

All 10 skills in this repo
  • Backend Test Worker

    CorrectRoadH/OpenTickly

    Build and verify real-Postgres Go tests and thin transport smoke for tracking behavior.

    306 GitHub stars~1.3k tokensUpdated 6 days ago
    Auto-check passed
  • Fullstack Regression Worker

    CorrectRoadH/OpenTickly

    Build cross-layer regression coverage that ties browser-visible behavior to backend truth.

    306 GitHub stars~1.1k tokensUpdated 6 days ago
    Auto-check passed
  • Test Platform Worker

    CorrectRoadH/OpenTickly

    Harden shared test infrastructure, runtime readiness, schema setup, and parallel lane behavior.

    306 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed
  • Tracking Backend Worker

    CorrectRoadH/OpenTickly

    Update backend timer/time-entry contracts, regressions, and source docs for the timer refactor mission.

    306 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed
  • Tracking Doc Worker

    CorrectRoadH/OpenTickly

    Audit and finalize inline source-document status blocks for the timer refactor mission.

    306 GitHub stars~819 tokensUpdated 6 days ago
    Auto-check passed
  • Tracking Frontend Worker

    CorrectRoadH/OpenTickly

    Refactor and verify website timer/time-entry surfaces on the reused local runtime.

    306 GitHub stars~1.2k tokensUpdated 6 days ago
    Auto-check passed

Works with

Categories

Questions about Frontend Test Worker

What does Frontend Test Worker do?

Build and verify page-flow and E2E coverage for the tracking browser surface. Frontend Test Worker is an agent skill from CorrectRoadH/OpenTickly. Build and verify page-flow and E2E coverage for the tracking browser surface.

When should I use Frontend Test Worker?

Frontend Test Worker fits situations like: tasks that involve End-to-end testing.

How do I install Frontend Test Worker in Claude Code?

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

How do I install Frontend Test Worker in Codex?

Run `npx skills add CorrectRoadH/OpenTickly --skill frontend-test-worker -a codex`. Or copy the skill folder (.factory/skills/frontend-test-worker in CorrectRoadH/OpenTickly) into .agents/skills/frontend-test-worker in your project. Codex loads it when a task matches its description.

Can I use Frontend Test Worker 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 CorrectRoadH/OpenTickly --skill frontend-test-worker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frontend-test-worker, .gemini/skills/frontend-test-worker, .github/skills/frontend-test-worker and .opencode/skills/frontend-test-worker in your project.

What does Frontend Test Worker need to run?

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

Does Frontend Test Worker 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 Frontend Test Worker 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 Frontend Test Worker use?

Frontend Test Worker is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Frontend Test Worker use?

About 1.4k tokens (SKILL.md is roughly 5.8k 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 Frontend Test Worker?

Skills that share tags, products or a category with Frontend Test Worker: Web Application Testing (anthropics/skills, 180k stars), playwright-cli Browser Automation (github/gh-aw, 5.4k stars), Write and Verify Playwright Tests (appsmithorg/appsmith, 41k stars) and Cucumber and Playwright E2E Tests (langgenius/dify, 158k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Frontend Test Worker?

CorrectRoadH (a GitHub user) maintains it in CorrectRoadH/OpenTickly, which has 306 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 2, 2026.

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