Skip to content
Agentmart
Submit a tool

grill-me

Harsh, unfiltered code review - bugs, security holes, anti-patterns, bad names, design flaws.

Skill by lunitrixx

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lunitrixx-grill-me

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Harsh, unfiltered code review - bugs, security holes, anti-patterns, bad names, design flaws. Use for a code review, feedback, "roast this", "tear this apart", "grill".

Use cases: design, security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/grill-me

What's inside

Skill name
grill-me
Description
Harsh, unfiltered code review - bugs, security holes, anti-patterns, bad names, design flaws. Use for a code review, feedback, "roast this", "tear this apart", "grill".
License
MIT
Instructions
24 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Grill me

Senior engineer, no sugarcoating: find every flaw, say why it matters and how to fix it.

1. Read the whole file and its callers/imports before commenting.
2. Get a second pass from the `reviewer` agent via the `subagent` tool, with the file path.
3. Report by severity.

Check: off-by-one, inverted conditions, null access; unhandled promises, swallowed errors; injection, hardcoded secrets, missing validation; god objects, circular deps, wrong abstractions; lying names, `data`/`tmp`/`result`/`handle`; untested error paths; N+1 queries, blocking the event loop, leaks.

Severity: **Critical** (crash, data loss, security, wrong behavior), **Serious** (edge-case bug, race, leak), **Questionable** (anti-pattern, dead code, misleading name, over-engineering), **Nitpick** (formatting, naming).

```markdown
## Grill Report - `file.ts`
<one blunt sentence on overall quality>
### Critical
- **Line X:** problem -> `broken` -> `fixed`
### Serious / Questionable / Nitpicks
- ...
```

One finding per bullet, exact line or function, always broken AND fixed code. If the code is good, say so briefly and still name one improvement.

From lunitrixx/pi-agent-kit, MIT.

More from lunitrixx/pi-agent-kit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 16, 2026 (12 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/lunitrixx/pi-agent-kit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from lunitrixx

Cite this page

grill-me skill. Agent Mart. https://agentmart.dev/skills/lunitrixx-grill-me (last updated 2026-10-24)