agentleFS
proffesor-for-testingproffesor-for-testing/agentic-qe/.claude/skills/coverage-guard/SKILL.md

coverage-guard

Skill515 starsChanged 22 days agoMITView on GitHub

Use when you want to prevent coverage regressions during development. Activate with /coverage-guard to warn when coverage drops below threshold after code changes.

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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. Distinctive:

    When activated, checks coverage after test runs and warns if it drops below the configured threshold.

    line 9
  2. Very specific:

    After any test execution (via Bash tool), compares coverage to the threshold in config.json.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Coverage Guard Mode

When activated, checks coverage after test runs and warns if it drops below the configured threshold.

What It Does

After any test execution (via Bash tool), compares coverage to the threshold in config.json. Warns (doesn't block) if coverage decreased.

Activation

/coverage-guard

Configuration

Edit config.json in this skill directory to set thresholds:

{
  "thresholds": {
    "statements": 80,
    "branches": 70,
    "functions": 75,
    "lines": 80
  },
  "coverageCommand": "npx jest --coverage --coverageReporters=json-summary",
  "coverageFile": "coverage/coverage-summary.json"
}

Hook Configuration

{
  "hooks": {
    "PostToolUse": [
      {
        "matcher": "Bash",
        "hook": ".claude/skills/coverage-guard/scripts/check-coverage.sh",
        "condition": "command contains 'jest' OR command contains 'vitest' OR command contains 'npm test'"
      }
    ]
  }
}

Enforcement Logic

#!/bin/bash
# check-coverage.sh
COVERAGE_FILE="coverage/coverage-summary.json"
THRESHOLD=80

if [ -f "$COVERAGE_FILE" ]; then
  STATEMENTS=$(jq '.total.statements.pct' "$COVERAGE_FILE")
  BRANCHES=$(jq '.total.branches.pct' "$COVERAGE_FILE")

  if (( $(echo "$STATEMENTS < $THRESHOLD" | bc -l) )); then
    echo "WARNING: Statement coverage ($STATEMENTS%) below threshold ($THRESHOLD%)"
    echo "Coverage dropped — check which files lost coverage."
  fi

  if (( $(echo "$BRANCHES < 70" | bc -l) )); then
    echo "WARNING: Branch coverage ($BRANCHES%) below 70%"
  fi
fi

Gotchas

  • Coverage check runs AFTER the test command — if tests crash, no coverage report is generated
  • Coverage-summary.json must be configured as a reporter — default Jest config may not include it
  • Threshold comparisons use floating point — 79.999% will trigger below 80% threshold
  • Branch coverage is typically 10-15% lower than line coverage — set thresholds accordingly

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.

Reviews can't be read right now.

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.