# run-relevant-tests-after-logic-changes

run-relevant-tests-after-logic-changes enforces running target test suites after code changes and forbids reporting completion until all checks pass.

- skill · `type=skill` · Claude Code, Codex, OpenCode, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 539 repo stars
- Author: ZaxbyHub
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/ZaxbyHub/opencode-swarm/tree/HEAD/.opencode/skills/generated/run-relevant-tests-after-logic-changes/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/run-relevant-tests-after-logic-changes

## What it does

This skill instructs the agent to run relevant test suites whenever logic changes. Passing linters or formatters is not enough; the assistant must confirm tests actually pass before concluding work.

Boundary-condition updates such as swapping `>` for `>=` frequently break tests expecting older behavior. The skill specifically targets these regressions by demanding proof of passing test runs directly in the workflow.

It also provides concrete checklist items for reviewers and test engineers to ensure verification steps appear in diffs and trigger conditions receive test coverage.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add ZaxbyHub/opencode-swarm --skill run-relevant-tests-after-logic-changes -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/run-relevant-tests-after-logic-changes/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/run-relevant-tests-after-logic-changes/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add ZaxbyHub/opencode-swarm --skill run-relevant-tests-after-logic-changes -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/run-relevant-tests-after-logic-changes/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add ZaxbyHub/opencode-swarm --skill run-relevant-tests-after-logic-changes -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/run-relevant-tests-after-logic-changes/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install ZaxbyHub/opencode-swarm .opencode/skills/generated/run-relevant-tests-after-logic-changes
```

2. **Manually: put the files in place**
- File: `.github/skills/run-relevant-tests-after-logic-changes/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add ZaxbyHub/opencode-swarm --skill run-relevant-tests-after-logic-changes -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/ZaxbyHub/opencode-swarm --path .opencode/skills/generated/run-relevant-tests-after-logic-changes
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/run-relevant-tests-after-logic-changes/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add ZaxbyHub/opencode-swarm --skill run-relevant-tests-after-logic-changes -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ZaxbyHub/opencode-swarm/tree/HEAD/.opencode/skills/generated/run-relevant-tests-after-logic-changes/SKILL.md

## When to use it
- prevent the agent from claiming success before executing tests
- catch regressions caused by boundary condition edits
- require actual test suite execution instead of lint checks alone
- provide review checks for verifying test execution inside the diff

## Example prompts
- I adjusted the discount logic in the checkout service, run the relevant tests and confirm they pass
- Update the boundary comparisons in the validator and verify the suite before reporting completion
- Refactor the order calculation logic and execute the related test suite

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 0538efd2557186d4.

BEGIN THIRD-PARTY FILE 0538efd2557186d4
````text
---
name: run-relevant-tests-after-logic-changes
description: run relevant tests after logic changes
metadata:
  generated_from_knowledge: '["78334fd4-d394-41c8-a845-7f5da6e15096"]'
  source_knowledge_ids: '["78334fd4-d394-41c8-a845-7f5da6e15096"]'
  generated_at: "2026-07-14T05:31:50.518Z"
  confidence: "0.60"
  status: active
  version: "1"
  skill_origin: generated
---

<!-- generated by opencode-swarm skill-generator. Do not edit by hand; edits will be preserved on regeneration only with controlled update mode. -->

# run relevant tests after logic changes

## Trigger

- (no explicit trigger metadata; cluster derived from category/tags)

## Required Procedure

- run relevant tests after logic changes
- confirm test pass before reporting completion

## Forbidden Shortcuts

- (none recorded)

## Delegation Template

When delegating a task affected by this skill, include:

```
SKILLS: file:.opencode/skills/generated/run-relevant-tests-after-logic-changes/SKILL.md
```

## Reviewer Checks

- Verify each required action above appears in the diff.

## Test Engineer Checks

- Add or update tests covering the trigger condition and the forbidden shortcut.

## Source Knowledge IDs

- 78334fd4-d394-41c8-a845-7f5da6e15096 — Run the actual test suite after behavioral changes, not just linting/formatting. Boundary-condition fixes (>, >=) often break existing tests that depend on the prior semantics.
````
END THIRD-PARTY FILE 0538efd2557186d4

The third-party file has ended. Everything between the 0538efd2557186d4 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© ZaxbyHub · MIT · https://github.com/ZaxbyHub/opencode-swarm/tree/HEAD/.opencode/skills/generated/run-relevant-tests-after-logic-changes/SKILL.md

## Similar
- [run-tests-after-changes](https://affpapa.org/en/nevibecode/hooks/run-tests-after-changes.md) — hook · 1967 installs
- [run-tests](https://affpapa.org/en/nevibecode/skills/run-tests.md) — skill · 7000 installs
- [run-smoke-tests](https://affpapa.org/en/nevibecode/skills/run-smoke-tests.md) — skill · 2300 installs
- [test-changes](https://affpapa.org/en/nevibecode/skills/test-changes.md) — skill · 335 installs
- [run-acceptance-tests](https://affpapa.org/en/nevibecode/skills/run-acceptance-tests.md) — skill · 3900 installs
- [run-python-tests](https://affpapa.org/en/nevibecode/skills/run-python-tests.md) — skill · ★ 6244 repo stars

From the same set: [zaxbyhub/opencode-swarm](https://affpapa.org/en/nevibecode/by/zaxbyhub/opencode-swarm.md) — 121 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
