Agent skill

Qabot Fixture

by shapeshift in shapeshift/web

Create a new qabot E2E test fixture interactively. An agent skill from shapeshift/web.

MITAuto-check: notesTesting & QA

Install Qabot Fixture

skills CLI
$ npx skills add shapeshift/web --skill qabot-fixture -a claude-code

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

GitHub CLI
$ gh skill install shapeshift/web qabot-fixture --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/shapeshift/web.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/qabot-fixture .claude/skills/qabot-fixture && 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
qabot-fixture
GitHub stars
206
Token cost
~838 tokens
SKILL.md length
340 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Create a new qabot E2E test fixture interactively. An agent skill from shapeshift/web.

  • Works in 4 steps: Gather context → Read existing fixtures for reference → Build steps interactively → …
  • User says create fixture
  • SKILL.md covers Process, Fixture YAML Format and Guidelines
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Qabot Fixture is an agent skill from shapeshift/web. Create a new qabot E2E test fixture interactively. Guides the user through defining test steps, expected outcomes, and saves the YAML fixture file. Use when user says "create fixture", "new test", "qabot fixture", or "/qabot-fixture".

Its SKILL.md is about 840 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 Test data and fixtures and End-to-end testing. It works with React. The licence is MIT.

When your agent uses it

  • User says create fixture
  • Tasks that involve Test data and fixtures
  • Tasks that involve End-to-end testing

Example prompts

  • “create fixture”
  • “new test”
  • “qabot fixture”
  • “/qabot-fixture”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Gather context
  2. Read existing fixtures for reference
  3. Build steps interactively
  4. Name, describe, and save

What it can do on your machine

Read from SKILL.md and the folder at commit 9321cf5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Edit
    • Glob
    • Grep
    • AskUserQuestion

    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 bash and yaml).

    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

Qabot Fixture loads about 838 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 340 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~838

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion

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 shapeshift/web at commit 9321cf5, republished under its MIT licence (© shapeshift). 340 words, ~838 tokens.

Download SKILL.mdSave it as .claude/skills/qabot-fixture/SKILL.md (or your agent's skills folder).
name
qabot-fixture
description
Create a new qabot E2E test fixture interactively. Guides the user through defining test steps, expected outcomes, and saves the YAML fixture file. Use when user says "create fixture", "new test", "qabot fixture", or "/qabot-fixture".
allowed-tools
Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion

qabot Fixture Builder

You are helping the user create a new E2E test fixture for qabot. Fixtures are YAML files that define test steps for agent-browser to execute.

Process

1. Gather context

Ask the user what they want to test. If they give a vague answer like "test the earn page", ask clarifying questions:

  • What specific functionality? (page loads, specific interaction, full flow)
  • What route? (e.g., /earn, /trade, /dashboard) - note: the base URL is a run-level arg, not per-fixture
  • Does it need a connected wallet? (most tests do - use depends_on: wallet-health.yaml)
2. Read existing fixtures for reference
bash
ls e2e/fixtures/*.yaml

Read them to understand the established patterns before building a new one.

3. Build steps interactively

For each step, ask the user:

  • What should the agent do? (this becomes the instruction)
  • What should be true after? (this becomes the expected)

Write instructions in natural language - agent-browser interprets them. No CSS selectors needed.

4. Name, describe, and save

Ask for:

  • A fixture name (kebab-case for the filename, human-readable for the name field)
  • A short description of what this fixture tests (one line)

Save to e2e/fixtures/<name>.yaml.

Fixture YAML Format

yaml
name: Human Readable Name
description: One-line description of what this fixture tests
route: /<route>
depends_on:
  - wallet-health.yaml          # runs BEFORE main steps (wallet unlock, onboarding dismiss)
post_depends_on:
  - evm-chains-regression.yaml  # runs AFTER main steps (optional)
steps:
  - name: Step name
    instruction: >
      Natural language instruction for agent-browser.
      Be specific about what to click, fill, or verify.
      Reference UI elements by their visible text, not selectors.
    expected: What should be true after this step completes
    screenshot: true
Composability

Fixtures can declare dependencies that run before or after the main steps:

  • depends_on - fixtures that run BEFORE the main steps. Most fixtures should include wallet-health.yaml which handles onboarding dismiss + wallet unlock.
  • post_depends_on - fixtures that run AFTER all main steps (e.g. regression suites, cleanup).
  • Dependencies are resolved recursively and deduplicated (each fixture runs at most once).
  • All fixtures run in one browser session - page state carries over.
  • Step indices are continuous across all fixtures.

Guidelines

  • Instructions should be specific enough for an AI agent to follow
  • Reference UI elements by visible text (e.g., "click the ETH selector", not "click #asset-select")
  • For inputs that use React controlled components, note that press (char by char) works but fill may not trigger onChange
  • Every step should have screenshot: true so test runs capture visual evidence
  • Keep steps atomic - one action per step where possible
  • The expected field is what the agent checks in the accessibility snapshot to determine pass/fail

© shapeshift, MIT. 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/qabot-fixture of shapeshift/web.

Open the folder on GitHubat commit 9321cf5

Compare with similar skills

Qabot Fixture 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.

Qabot Fixture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qabot Fixture this skillshapeshift/web206—~838Automated safety check: NotesMIT
Java SDK E2E Test with Replay Snapshotgithub/copilot-sdk11k—~1.8kAutomated safety check: PassMIT
source-mssql E2E Test Harnessairbytehq/airbyte22k—~4.4kAutomated safety check: PassCustom licence
Airbyte source-mysql E2E Testsairbytehq/airbyte22k—~2.6kAutomated safety check: PassCustom licence
Senior QAnicepkg/auto-company1953 repos~1.1kAutomated safety check: NotesNone
Airbyte Postgres Source E2E Testsairbytehq/airbyte22k—~2.5kAutomated safety check: PassCustom licence

Similar skills

  • Official

    Creates a Java SDK end-to-end test for the Copilot SDK that runs against a recorded YAML snapshot through a replay proxy, so CI needs no real authentication.

    11k GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed
  • Official

    Stands up a throwaway local SQL Server 2022 backend, applies SQL fixtures and runs Airbyte spec, check, discover and read against source-mssql images.

    22k GitHub stars~4.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Official

    Stands up a throwaway local MySQL 8.0 backend, applies SQL fixtures and sweeps the Airbyte spec, check, discover and read commands against a source-mysql image.

    22k GitHub stars~2.6k tokensUpdated today
    Testing & QAAuto-check passed
  • Senior QA

    nicepkg/auto-company

    Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.

    195 GitHub starsUsed in 3 repos~1.1k tokens
    Testing & QAAuto-check: notes
  • Official

    Starts a local PostgreSQL 16 container, loads SQL fixtures and runs the Airbyte spec, check, discover and read commands against a chosen source-postgres image.

    22k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed
  • Add Full Slice

    fullstackhero/dotnet-starter-kit

    Build a capability end-to-end — backend vertical slice (Contracts→handler→validator→endpoint) AND the React page wired to it.

    6.8k GitHub stars~783 tokensUpdated yesterday
    Testing & QAAuto-check passed

More from shapeshift/web

  • React Best Practices

    shapeshift/web

    Comprehensive React and Next.js performance optimization guide with 40+ rules for eliminating waterfalls, optimizing bundles, and improving rendering.

    206 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Benchmark Translate

    shapeshift/web

    Run a quality benchmark of the /translate skill by selecting stratified test keys, capturing ground truth, translating, judging with sub-agents, and compiling a regression report.

    206 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Translate

    shapeshift/web

    Translate new/changed English UI strings into all supported languages using a translate-review-refine pipeline.

    206 GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Chain Integration

    shapeshift/web

    Integrate a new blockchain as a second-class citizen in ShapeShift Web.

    206 GitHub stars~20k tokensUpdated today
    Auto-check: notes
  • Qabot

    shapeshift/web

    Run QA tests using agent-browser and post results to the qabot dashboard.

    206 GitHub stars~8.2k tokensUpdated today
    Auto-check: notes
  • Swapper Integration

    shapeshift/web

    Integrate new DEX aggregators, swappers, or bridge protocols (like Bebop, Portals, Jupiter, 0x, 1inch, etc.) into ShapeShift Web.

    206 GitHub stars~11k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about Qabot Fixture

What does Qabot Fixture do?

Create a new qabot E2E test fixture interactively. An agent skill from shapeshift/web. Qabot Fixture is an agent skill from shapeshift/web. Create a new qabot E2E test fixture interactively.

When should I use Qabot Fixture?

Qabot Fixture fits situations like: user says create fixture; tasks that involve Test data and fixtures; tasks that involve End-to-end testing.

How do I install Qabot Fixture in Claude Code?

Run `npx skills add shapeshift/web --skill qabot-fixture -a claude-code`. Or copy the skill folder (.claude/skills/qabot-fixture in shapeshift/web) into .claude/skills/qabot-fixture in your project. Claude Code loads it when a task matches its description.

How do I install Qabot Fixture in Codex?

Run `npx skills add shapeshift/web --skill qabot-fixture -a codex`. Or copy the skill folder (.claude/skills/qabot-fixture in shapeshift/web) into .agents/skills/qabot-fixture in your project. Codex loads it when a task matches its description.

Can I use Qabot Fixture 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 shapeshift/web --skill qabot-fixture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qabot-fixture, .gemini/skills/qabot-fixture, .github/skills/qabot-fixture and .opencode/skills/qabot-fixture in your project.

What does Qabot Fixture need to run?

SKILL.md names no scripts, command-line tools or credentials: Qabot Fixture is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion.

Does Qabot Fixture 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 Qabot Fixture safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Qabot Fixture use?

Qabot Fixture 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 Qabot Fixture use?

About 838 tokens (SKILL.md is roughly 3.4k 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 Qabot Fixture?

Skills that share tags, products or a category with Qabot Fixture: Java SDK E2E Test with Replay Snapshot (github/copilot-sdk, 11k stars), source-mssql E2E Test Harness (airbytehq/airbyte, 22k stars), Airbyte source-mysql E2E Tests (airbytehq/airbyte, 22k stars) and Senior QA (nicepkg/auto-company, 195 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qabot Fixture?

shapeshift (a GitHub organization) maintains it in shapeshift/web, which has 206 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 9, 2026.

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