agentleFS
sd0xdevsd0xdev/sd0x-dev-flow/skills/check-coverage/SKILL.md

check-coverage

Skill192 starsChanged 38 days agoMITView on GitHub

Comprehensive assessment of Unit / Integration / E2E three-layer test coverage, identify gaps and provide actionable recommendations.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Test sufficiency review via Codex (use /codex-test-review)

    line 15
  2. Distinctive:

    Read specified feature docs.

    line 38
  3. Distinctive:

    Search related source code based on feature documentation.

    line 45
  4. Distinctive:

    Check whether each source file has corresponding tests (unit, integration, e2e).

    line 49
  5. Distinctive:

    Read source: Identify public methods, important branches, error handling

    line 54
  6. Distinctive:

    Read tests: Identify covered cases

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Test Coverage Analysis

Trigger

  • Keywords: check coverage, test coverage, coverage analysis, coverage gaps, check-coverage

When NOT to Use

  • Test sufficiency review via Codex (use /codex-test-review)
  • Generating tests (use /codex-test-gen)
  • Running tests (use /verify)

Parent Skill Reference

See @skills/test-review/SKILL.md for Codex-based test review workflow.

Agent Dispatch

Agent({
  description: "Assess three-layer test coverage and identify gaps",
  subagent_type: "coverage-analyst",
  prompt: `Assess Unit / Integration / E2E test coverage for the feature docs at: $ARGUMENTS
Follow the steps defined in this skill.`
})

Task

Step 1: Read Feature Documentation

Read specified feature docs. Extract:

  • Feature name and objectives
  • Involved Service / Provider / Entity
  • Core flows and boundary conditions

Step 2: Identify Related Source Code

Search related source code based on feature documentation. Build source code inventory.

Step 3: Map Test Files

Check whether each source file has corresponding tests (unit, integration, e2e).

Step 4: Analyze Coverage Gaps

For each source file:

  1. Read source: Identify public methods, important branches, error handling
  2. Read tests: Identify covered cases
  3. Compare gaps: missing methods, uncovered branches, untested error scenarios

Step 5: Classify and Recommend

SeverityDescription
🔴 CriticalCore logic, data writes, amount calculations
🟠 MajorImportant branches, error handling
🟡 MinorEdge cases, utility functions
⚪ Nice-to-haveLogging, formatting

Output

# Test Coverage Analysis Report

## Feature Overview
- Feature name: <from documentation>
- Documentation path: $ARGUMENTS
- Related modules: <list>

## Current Coverage
| Module | Source Path | Test Path | Coverage Status |
|--------|------------|-----------|----------------|

## Coverage Gaps
### 🔴 Critical
### 🟠 Major
### 🟡 Minor

## Recommended New Tests
| Priority | Test Type | Test Case | Target File |
|----------|-----------|-----------|-------------|

## Coverage Summary
| Metric | Status |
|--------|--------|
| Feature coverage | X/Y (Z%) |
| Happy path | ✅/❌ |
| Error path | ✅/❌ |
| Edge cases | ✅/❌ |

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.