Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

test-gaps — Claude Code skill: what it does, how to install

Detects missing test coverage and suggests tests to write. Helpful right after adding a new feature or before cutting a release.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ruvnet/ruflo --skill test-gaps -a claude-code
Open on GitHub

What test-gaps does

The skill detects untested code using CLI commands or an MCP hook dispatcher. It runs @claude-flow/cli@latest hooks. The coverage-gaps command outputs a table of missing coverage, while coverage-suggest proposes tests for a specific path.

You can pass --threshold to define minimum coverage or add --critical-only for the worst gaps. The CLI tool has no --limit flag. Narrow your results by path or threshold instead.

If you have the ruflo-core MCP plugin configured, the agent dispatches the testgaps worker directly. Continuous checks are also possible by pairing /loop with the loop-worker skill.

What it helps with

  • Identify untested code paths after adding a feature
  • Generate concrete test suggestions for uncovered files
  • Check project coverage against an 80% threshold
  • Trigger continuous coverage monitoring via loop-worker

Example prompts for the agent

  • Find test coverage gaps in src/ with an 80 percent threshold
  • What tests should I write for the auth module?
  • Check for critical coverage gaps using coverage-gaps

How to install test-gaps

1Skills CLI (Vercel)

npx skills add ruvnet/ruflo --skill test-gaps -a claude-code

2Manually: put the files in place

~/.claude/skills/test-gaps/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/test-gaps/

From the same set104

The whole set →
ruflo ruvnet This skill adds multi-agent orchestration, memory, routing, and MCP tools to a project. Use it for swarm tasks and multi-step workflows. Claude Code CX Codex Cursor +1 4,000installs Swarm Orchestration ruvnet Skill for managing agent swarms with parallel execution, dynamic topology, and automatic load balancing. Use when a single agent is not enough and you need to orchestrate specialists of different types. Claude Code CX Codex Cursor +1 2,100installs github-project-management ruvnet Turns issue triage and board upkeep into gh and ruv-swarm calls: labels, subtasks, duplicate lookup. Useful when the tracker holds more tickets than order. Claude Code CX Codex Cursor +1 1,400installs github-workflow-automation ruvnet Automates GitHub Actions with AI agent coordination. Generates optimised pipelines, manages pull requests, analyzes failed runs, and deploys updates with risk assessment. Claude Code CX Codex Cursor +1 1,300installs github-code-review ruvnet Runs a swarm of specialized AI agents to inspect GitHub pull requests for security, performance, and architecture issues. Claude Code CX Codex Cursor +1 1,300installs stream-chain ruvnet Chains sequential agent steps together using streaming JSON flow and provides ready-to-run pipelines. Claude Code CX Codex Cursor +1 1,200installs flow-nexus-swarm ruvnet Deploy cloud-based AI agent swarms and define event-driven workflows with message queues. Use it to coordinate tasks, inspect runs, and scale a swarm. Claude Code CX Codex Cursor +1 1,200installs performance-analysis ruvnet Detects bottlenecks in Claude Flow swarms, profiles agent operations, and generates reports with actionable optimization recommendations. Claude Code CX Codex Cursor +1 1,200installs

Similar

ce-polish EveryInc Refines a working feature through browser feedback: you point out what needs work, the skill edits the code, hot reload shows the result. Claude Code CX Codex Cursor +1 1,100installs user-story deanpeters Turns product requirements into Mike Cohn user stories paired with Gherkin acceptance criteria. Fits backlog refinement and sprint planning. Claude Code CX Codex Cursor +1 4,100installs salesforce-flow-design official github Reviews Salesforce Flow architecture, type selection, bulk safety, and fault handling. Use it before designing, reviewing, or activating a Flow. GitHub Copilot 839installs anti-detect-browser antibrow Launch Chromium with a genuine device fingerprint through Playwright API. Each profile gets one coherent identity that persists across runs for testing, scraping, and multi-account work. Claude Code CX Codex Cursor +1 136,100installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. Claude Code CX Codex Cursor +1 673,100installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs

Questions about test-gaps

How to install test-gaps in Claude Code?

Run npx skills add ruvnet/ruflo --skill test-gaps -a claude-code in your terminal. This registers the skill for Claude Code.

What does test-gaps do?

It runs coverage analysis via @claude-flow/cli or an MCP worker trigger named testgaps. The agent then lists uncovered code and suggests specific tests to write.

Does coverage-gaps support limiting the output size?

No, the CLI tool has no --limit option. You filter output using --threshold, target directories with --path, or isolate severe issues with --critical-only.

Source text

SKILL.md · MIT
---
name: test-gaps
description: Detect missing test coverage and generate test suggestions. Use when the user asks about coverage gaps, untested code, or what tests to write next; also after adding a feature to find what still needs tests.
argument-hint: "[--path PATH] [--threshold N]"
allowed-tools: Bash(npx *) mcp__plugin_ruflo-core_ruflo__hooks_worker-dispatch Read Grep
---
Find test coverage gaps via CLI:
```bash
npx @claude-flow/cli@latest hooks coverage-gaps --format table --threshold 80   # add --critical-only for the worst gaps (there is no --limit)
npx @claude-flow/cli@latest hooks coverage-route --task 'add auth tests'
npx @claude-flow/cli@latest hooks coverage-suggest --path src/
```

Or dispatch the testgaps worker via MCP:
`mcp__plugin_ruflo-core_ruflo__hooks_worker-dispatch({ trigger: "testgaps" })`

For continuous detection, use `/loop` with the `loop-worker` skill targeting the `testgaps` worker.

© ruvnet · MIT · ruvnet/ruflo

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor