improving-test-suites — Claude Code skill: tests and setup
improving-test-suites is a Claude Code skill that reviews test suites and focuses them on important behavior. It activates for requests to trim, rewrite, review, or strengthen tests.
no license 119 installs ★ 3 updated 2026-10-25
npx skills add b-mendoza/agent-skills --skill improving-test-suites -a claude-codeWhat improving-test-suites does
The skill examines the specified test files and proposes a compact set of behavior checks. Subagents handle scoped review tasks and return short reports; the orchestrator turns them into an itemized change plan. Test changes require approval unless AUTO_APPROVE=true bypasses the plan-approval request.
After approved edits, it checks that each retained high-value behavior still has a named test, then runs validation. Repair is capped at three attempts. Set TARGET_TEST_FILES to identify the suite; TEST_COMMAND can provide the command used to run it.
What it helps with
- trim tests that duplicate low-value implementation details
- spot brittle checks tied to internal code structure
- review coverage for contracts, schemas, or security behavior
- verify important cases remain covered after test edits
Example prompts for the agent
- Review
tests/test_billing.pyand keep tests for important behavior. - Trim brittle tests under
tests/api/without editing application files. - Review the schema and authorization tests, then propose a change plan.
How to install improving-test-suites
1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill improving-test-suites -a claude-code2Manually: put the files in place
~/.claude/skills/improving-test-suites/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/improving-test-suites/
1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill improving-test-suites -a codex2Manually: put the files in place
.agents/skills/improving-test-suites/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill improving-test-suites -a cursor2Manually: put the files in place
.cursor/skills/improving-test-suites/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install b-mendoza/agent-skills skills/improving-test-suites2Manually: put the files in place
.github/skills/improving-test-suites/SKILL.md1Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill improving-test-suites -a gemini-cli2Platform CLI
gemini skills install https://github.com/b-mendoza/agent-skills --path skills/improving-test-suitesManually: put the files in place
.devin/skills/improving-test-suites/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add b-mendoza/agent-skills --skill improving-test-suites -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about improving-test-suites
How do I install improving-test-suites in Claude Code?
Run npx skills add b-mendoza/agent-skills --skill improving-test-suites -a claude-code. The skill file is at ~/.claude/skills/improving-test-suites/SKILL.md.
What does improving-test-suites do?
It reviews a named test suite, proposes scoped changes, and checks that important behaviors remain covered after approved edits. It then validates the result and returns a handoff status.
Can improving-test-suites approve its plan automatically?
Set AUTO_APPROVE=true to bypass the plan-approval request. Other safeguards and validation still apply.