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

Ralph Coverage

by jvm-skills in jvm-skills/jvm-skills

Run Ralph in coverage mode — iteratively write tests for untested classes until coverage targets are met.

Apache-2.0Auto-check passedTesting & QA

Install Ralph Coverage

skills CLI
$ npx skills add jvm-skills/jvm-skills --skill ralph-coverage -a claude-code

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

GitHub CLI
$ gh skill install jvm-skills/jvm-skills ralph-coverage --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/jvm-skills/jvm-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.junie/skills/ralph-coverage .claude/skills/ralph-coverage && 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
ralph-coverage
GitHub stars
140
Token cost
~683 tokens
SKILL.md length
341 words
Files
4 (incl. scripts)
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run Ralph in coverage mode — iteratively write tests for untested classes until coverage targets are met.

  • Works in 10 steps: Run the coverage skill to generate… → Read the generated improvement document → Read progress.txt to see which classes… → …
  • User wants to improve test coverage autonomously
  • SKILL.md covers Prerequisites, Scripts (scripts/ subfolder), Files and Process (each iteration), plus 2 more sections
  • Runs Shell scripts from its folder; calls git

What it does

Ralph Coverage is an agent skill from jvm-skills/jvm-skills. Run Ralph in coverage mode — iteratively write tests for untested classes until coverage targets are met. Use when user wants to improve test coverage autonomously.

Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `PRD.md`, `scripts/afk-ralph.sh` and `scripts/ralph-once.sh`).

It sits in Testing & QA, covering Test coverage and Test generation. The licence is Apache-2.0.

When your agent uses it

  • User wants to improve test coverage autonomously
  • Tasks that involve Test coverage
  • Tasks that involve Test generation

Example prompts

  • “/ralph-coverage”

Requirements

  • A Bash shell

Workflow steps

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

  1. Run the coverage skill to generate coverage report and improvement plan
  2. Read the generated improvement document
  3. Read progress.txt to see which classes already have tests written
  4. Pick the highest-priority untested class (lowest coverage, not already in progress.txt)
  5. Read the source class and any existing tests for it
  6. Write meaningful tests — not just line coverage, but real behavior/edge case tests
  7. Run the test filter for the new test class to verify tests pass
  8. Compile to check for syntax errors
  9. Commit: git add -A && git commit -m "test: add tests for ClassName"
  10. Update progress.txt with class name, previous coverage %, and what was tested

What it can do on your machine

Read from SKILL.md and the folder at commit c6d477f. 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

    Ships 2 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git

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

  • Network

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

Ralph Coverage loads about 683 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 341 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~683

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); the scripts in this folder are not scanned.

SKILL.md

The full file from jvm-skills/jvm-skills at commit c6d477f, republished under its Apache-2.0 licence (© jvm-skills). 341 words, ~683 tokens.

Download SKILL.mdSave it as .claude/skills/ralph-coverage/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
ralph-coverage
description
Run Ralph in coverage mode — iteratively write tests for untested classes until coverage targets are met. Use when user wants to improve test coverage autonomously.

Ralph Coverage

Autonomously improve test coverage by iterating through untested classes, writing tests, and committing. Each iteration picks one class, writes meaningful tests for it, runs them, and commits.

Prerequisites

  • A coverage skill that generates a prioritized improvement plan (e.g. coverage-kover-gradle)
  • claude CLI on PATH
  • Clean working tree (the loop commits after every iteration)

Scripts (scripts/ subfolder)

ScriptPurpose
ralph-once.shSingle iteration, foreground. Use to try the loop before committing to a long run.
afk-ralph.sh <iterations>Headless loop with retry and error handling. Stops early on <promise>COMPLETE</promise>. Depends on ralph-lib.sh from a ralph-plan skill if you use one — otherwise inline the helpers.

Both scripts cd to the project root and read PRD.md + progress.txt inside this skill's directory.

Files

  • PRD.md — coverage priorities, target thresholds, rules, and which test base classes / skip patterns to follow. Customize per project.
  • progress.txt — append-only log of completed coverage iterations. Created on first run.

Process (each iteration)

  1. Run the coverage skill to generate coverage report and improvement plan
  2. Read the generated improvement document
  3. Read progress.txt to see which classes already have tests written
  4. Pick the highest-priority untested class (lowest coverage, not already in progress.txt)
  5. Read the source class and any existing tests for it
  6. Write meaningful tests — not just line coverage, but real behavior/edge case tests
  7. Run the test filter for the new test class to verify tests pass
  8. Compile to check for syntax errors
  9. Commit: git add -A && git commit -m "test: add tests for ClassName"
  10. Update progress.txt with class name, previous coverage %, and what was tested

Rules

  • ONLY ONE CLASS PER ITERATION
  • Follow the project's existing test patterns (see PRD.md)
  • Use descriptive test names (e.g. `should do something specific`)
  • Skip generated code and framework boilerplate (see PRD.md)
  • If all priority classes are covered above the target threshold, output <promise>COMPLETE</promise>

Project Customization

Customize PRD.md in this skill's directory:

  • Test base classes and when to use each (e.g. DataBaseTest, S3Test)
  • Skip patterns (generated code, view-context data classes, etc.)
  • Coverage target threshold (e.g. 80%)
  • Commit message style
  • Project-specific exclusions

© jvm-skills, 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

SKILL.md and 3 other files (scripts) in .junie/skills/ralph-coverage of jvm-skills/jvm-skills.

  • SKILL.md
  • PRD.md
  • scripts/afk-ralph.sh
  • scripts/ralph-once.sh

Open the folder on GitHubat commit c6d477f

Compare with similar skills

Ralph Coverage 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.

Ralph Coverage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ralph Coverage this skilljvm-skills/jvm-skills140—~683Automated safety check: PassApache-2.0
E2E Test ThinkerUniClipboard/UniClipboard1.9k—~1.7kAutomated safety check: PassAGPL-3.0
Designing TestsCloudAI-X/opencode-workflow275—~2.9kAutomated safety check: PassMIT
Mutation Testingproffesor-for-testing/agentic-qe495—~1.7kAutomated safety check: PassMIT
Write Testsgnomeria/usbtree691—~622Automated safety check: PassMIT
Mutation Testjmagly/aiwg220—~3.2kAutomated safety check: PassMIT

Similar skills

  • E2E Test Thinker

    UniClipboard/UniClipboard

    Analyze the current branch's diff against main and determine which changes are testable via CLI-based end-to-end tests.

    1.9k GitHub stars~1.7k tokensUpdated today
    Testing & QAAuto-check passed

  • Designing Tests

    CloudAI-X/opencode-workflow

    Guides test strategy, TDD/BDD approaches, test coverage planning, and testing best practices.

    275 GitHub stars~2.9k tokensUpdated 9 mo ago
    Testing & QAAuto-check passed

  • Mutation Testing

    proffesor-for-testing/agentic-qe

    Test quality validation through mutation testing, assessing test suite effectiveness by introducing code mutations and measuring kill rate.

    495 GitHub stars~1.7k tokensUpdated 5 days ago
    Testing & QAAuto-check passed

  • Write Tests

    gnomeria/usbtree

    Author tests that match the repo's stack and existing test style, at the cheapest level that catches the regression.

    691 GitHub stars~622 tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Mutation Test

    jmagly/aiwg

    Run mutation testing to validate test quality beyond code coverage.

    220 GitHub stars~3.2k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Write Frontend Tests

    Elite588/AUTOGPT

    Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them.

    103 GitHub stars~1.9k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

More from jvm-skills/jvm-skills

All 16 skills in this repo

  • Mutation Testing

    jvm-skills/jvm-skills

    Bootstrap pitest via the info.solidsoft.pitest Gradle plugin with Kotlin-sane defaults, run mutation tests scoped to changed classes, interpret surviving mutants from mutations.xml, triage…

    140 GitHub stars~6.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Skill Scout

    jvm-skills/jvm-skills

    Run the skill-scout loop — scan the next batch of unscanned JVM-conference rosters for speaker-created AI skills and apply results to the CSV store via the overnight Workflow.

    140 GitHub stars~727 tokensUpdated 1 mo ago
    Auto-check passed

  • Spec

    jvm-skills/jvm-skills

    Generate a feature spec with user stories directly from conversation context and codebase exploration — no interview needed.

    140 GitHub stars~832 tokensUpdated 1 mo ago
    Auto-check passed

  • UI Review

    jvm-skills/jvm-skills

    Verify UI/UX by running Playwright tests and reviewing screenshots.

    140 GitHub stars~545 tokensUpdated 1 mo ago
    Auto-check passed

  • Kotest

    jvm-skills/jvm-skills

    Write a new Kotlin test, or modernize an existing one, using Kotest matchers and idiomatic Kotlin test style — backticked names, apply/assertSoftly blocks, and existing object mothers and helpers.

    140 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Voice

    jvm-skills/jvm-skills

    Make prose sound like Thomas, not like a generic technical writer.

    140 GitHub stars~592 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Ralph Coverage

What does Ralph Coverage do?

Run Ralph in coverage mode — iteratively write tests for untested classes until coverage targets are met. Ralph Coverage is an agent skill from jvm-skills/jvm-skills. Run Ralph in coverage mode — iteratively write tests for untested classes until coverage targets are met.

When should I use Ralph Coverage?

Ralph Coverage fits situations like: user wants to improve test coverage autonomously; tasks that involve Test coverage; tasks that involve Test generation.

How do I install Ralph Coverage in Claude Code?

Run `npx skills add jvm-skills/jvm-skills --skill ralph-coverage -a claude-code`. Or copy the skill folder (.junie/skills/ralph-coverage in jvm-skills/jvm-skills) into .claude/skills/ralph-coverage in your project. Claude Code loads it when a task matches its description.

How do I install Ralph Coverage in Codex?

Run `npx skills add jvm-skills/jvm-skills --skill ralph-coverage -a codex`. Or copy the skill folder (.junie/skills/ralph-coverage in jvm-skills/jvm-skills) into .agents/skills/ralph-coverage in your project. Codex loads it when a task matches its description.

Can I use Ralph Coverage 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 jvm-skills/jvm-skills --skill ralph-coverage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ralph-coverage, .gemini/skills/ralph-coverage, .github/skills/ralph-coverage and .opencode/skills/ralph-coverage in your project.

What does Ralph Coverage need to run?

Going by SKILL.md and its folder, Ralph Coverage needs a shell for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: A Bash shell.

Does Ralph Coverage access the network?

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

Is Ralph Coverage 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Ralph Coverage use?

Ralph Coverage 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 Ralph Coverage use?

About 683 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 Ralph Coverage?

Skills that share tags, products or a category with Ralph Coverage: E2E Test Thinker (UniClipboard/UniClipboard, 1.9k stars), Designing Tests (CloudAI-X/opencode-workflow, 275 stars), Mutation Testing (proffesor-for-testing/agentic-qe, 495 stars) and Write Tests (gnomeria/usbtree, 691 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ralph Coverage?

jvm-skills (a GitHub organization) maintains it in jvm-skills/jvm-skills, which has 140 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on August 31, 2026.

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