How do I install the Coverage Check skill?

Run npx skillmds@latest add gabrielmoreira/coverage-check in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Coverage Check safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Coverage Check?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Coverage Check free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Coverage Check?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Coverage Check by gabrielmoreira — Agent Skill

Name: Coverage Check
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

Coverage Check

Lightweight test coverage analysis using git and file system heuristics. Identifies source files with no corresponding test file. No coverage tools required — works on any project by pattern matching. The CHECK skill for testing, analogous to validate-docs for documentation.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

Skill: Coverage Check

What This Skill Does

Performs a fast, lightweight coverage check by matching source files against test files using naming conventions. No coverage tools, no test execution, no source file reads — just file system patterns.

Answers: "Which source files have no corresponding test file?"

When to Use

At session start (via smart-start) to assess test health
Before add-tests to know where to focus
As a quick health check: "how's our test coverage?"

Do NOT use this for detailed coverage analysis — use actual coverage tools for that. This is a fast heuristic.

Execution Model

Always: the primary agent runs this skill directly.
Token budget: ~1-2k tokens. This is intentionally minimal.
Output: chat-based coverage report.

Workflow

Step 1: Detect Test Patterns

Identify how the project names test files:

# Find test files and extract naming pattern
find . -name "*.test.*" -o -name "*.spec.*" -o -name "test_*" | head -5

Common patterns:

Pattern	Convention
`src/foo.ts` → `src/foo.test.ts`	Co-located
`src/foo.ts` → `tests/foo.test.ts`	Separate directory
`src/foo.ts` → `__tests__/foo.test.ts`	Jest convention
`src/foo.py` → `tests/test_foo.py`	Python convention
`src/foo.go` → `src/foo_test.go`	Go convention

Step 2: Map Source to Tests

For each source file, check if a corresponding test file exists:

# Example for Python
for src in $(find src -name "*.py" ! -name "__init__.py" ! -path "*/test*"); do
    base=$(basename "$src" .py)
    if ! find tests -name "test_${base}.py" | grep -q .; then
        echo "UNCOVERED: $src"
    fi
done

Step 3: Generate Report

## Coverage Check

| Metric | Value |
|--------|-------|
| Source files | N |
| Test files | N |
| Coverage ratio | N% |

### Uncovered Files (no test file found)

| File | Module | Risk |
|------|--------|------|
| src/auth/login.ts | auth | High (handles user input) |
| src/utils/format.ts | utils | Low (pure utility) |

### Well-Covered Modules
- api/ (8/8 files have tests)
- models/ (5/5 files have tests)

### Recommendation
Focus `add-tests` on: auth/login.ts, data/repository.ts

Rules

No test execution: this skill never runs tests. It only checks file existence.
Heuristic, not precise: file-based matching is approximate. A test file existing doesn't mean it has good coverage. Flag this in the report.
Fast: should complete in under 5 seconds. No source file reads.
Convention-aware: detect the project's test naming convention before matching. Don't assume.
No built-in explore agent: do NOT use the built-in explore subagent type.

---name: coverage-checkdescription: Lightweight test coverage analysis using git and file system heuristics. Identifies source files with no corresponding test file. No coverage tools required — works on any project by pattern matching. The CHECK skill for testing, analogous to validate-docs for documentation.license: MIT--- # Skill: Coverage Check ## What This Skill Does Performs a fast, lightweight coverage check by matching source files against test files using naming conventions. No coverage tools, no test execution, no source file reads — just file system patterns. Answers: "Which source files have no corresponding test file?" ## When to Use - At session start (via `smart-start`) to assess test health - Before `add-tests` to know where to focus - As a quick health check: "how's our test coverage?" Do NOT use this for detailed coverage analysis — use actual coverage tools for that. This is a fast heuristic. ## Execution Model - **Always**: the primary agent runs this skill directly. - **Token budget**: ~1-2k tokens. This is intentionally minimal. - **Output**: chat-based coverage report. ## Workflow ### Step 1: Detect Test Patterns Identify how the project names test files: ```bash # Find test files and extract naming pattern find . -name "*.test.*" -o -name "*.spec.*" -o -name "test_*" | head -5 ``` Common patterns: | Pattern | Convention | |---------|-----------| | `src/foo.ts` → `src/foo.test.ts` | Co-located | | `src/foo.ts` → `tests/foo.test.ts` | Separate directory | | `src/foo.ts` → `__tests__/foo.test.ts` | Jest convention | | `src/foo.py` → `tests/test_foo.py` | Python convention | | `src/foo.go` → `src/foo_test.go` | Go convention | ### Step 2: Map Source to Tests For each source file, check if a corresponding test file exists: ```bash # Example for Python for src in $(find src -name "*.py" ! -name "__init__.py" ! -path "*/test*"); do base=$(basename "$src" .py) if ! find tests -name "test_${base}.py" | grep -q .; then echo "UNCOVERED: $src" fi done ``` ### Step 3: Generate Report ```markdown ## Coverage Check | Metric | Value | |--------|-------| | Source files | N | | Test files | N | | Coverage ratio | N% | ### Uncovered Files (no test file found) | File | Module | Risk | |------|--------|------| | src/auth/login.ts | auth | High (handles user input) | | src/utils/format.ts | utils | Low (pure utility) | ### Well-Covered Modules - api/ (8/8 files have tests) - models/ (5/5 files have tests) ### Recommendation Focus `add-tests` on: auth/login.ts, data/repository.ts ``` ## Rules 1. **No test execution**: this skill never runs tests. It only checks file existence. 2. **Heuristic, not precise**: file-based matching is approximate. A test file existing doesn't mean it has good coverage. Flag this in the report. 3. **Fast**: should complete in under 5 seconds. No source file reads. 4. **Convention-aware**: detect the project's test naming convention before matching. Don't assume. 5. **No built-in explore agent**: do NOT use the built-in `explore` subagent type.

Frequently asked questions