How do I install the Run Coverage skill?

Run npx skillmds@latest add tmj-90/run-coverage 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 Run Coverage safe to use?

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

Which AI agents work with Run Coverage?

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 Run Coverage free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Run Coverage?

tmj-90 (@tmj-90) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Run Coverage by tmj-90 — Agent Skill

Name: Run Coverage
Author: tmj-90

Run Coverage

Use when a ticket or acceptance criterion sets a coverage threshold or asks to raise coverage on a unit, and you need to measure and evidence it. Invoke for "coverage must stay above N%", "report the coverage delta", or "prove the new code is covered".

tmj-90 6bff4e8 1.6 KB Updated Sep 17, 2026

File contents

Measure coverage

Run the repo's coverage tool, read the real number, and evidence the result or delta. Do not chase a number with hollow tests.

Steps

Find the coverage command from the context packet (e.g. pnpm test --coverage, pytest --cov, go test -cover ./..., mvn jacoco:report). If silent, detect the configured tool from the manifest.
Run it and capture the exact command plus the overall percentage and, where the ticket names a unit, that file's/module's coverage.
Compare against the threshold in the ticket/AC. If it falls short, add or extend tests for the genuinely uncovered branches (use the add-unit-test skill) — cover real behaviour, not lines for their own sake.
Re-run to capture the new figure. Note the before→after delta if the ticket asks for an improvement.
Evidence: the command, the percentage (and delta). Then use the record-evidence skill to record coverage_report against the AC and submit for review.

Rules

Report the true figure from a run in this session — never estimate coverage.
Don't write assertion-free tests just to lift the number.
Match the repo's coverage tooling and existing thresholds.
Run on a branch (the create-branch skill), never a protected branch.

Frequently asked questions