# Try

> Manually test the latest change with one realistic positive case and one adversarial negative case, capturing evidence before any further fix. Use when the user asks for a quick confidence check or wants to test a recent implementation.

- Skill: `megabadcoder/try` (Agent Skill)
- Install (CLI): `npx skillmds@latest add megabadcoder/try`
- Raw SKILL.md: https://api.skillmd.com/api/skills/megabadcoder/try/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: MegaBadCoder (https://skillmd.com/u/megabadcoder)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/megabadcoder/try

---


# Fast manual test

Use this as Codex's equivalent of `/up:try`.

1. Identify the latest relevant change from the conversation and `git status`.
2. Design exactly two fast probes: one realistic happy path and one likely misuse or edge case that should fail or be rejected.
3. Run both and capture their actual output. Do not fix unexpected failures before reporting them.
4. Report exactly:

```
Pos: [PASS/FAIL] — <what happened>
Neg: [PASS/FAIL] — <what happened>
```