agentleFS
lgtm-hqlgtm-hq/ai-skills/skills/greptile/SKILL.md

greptile

Skill1 starsChanged 11 days agoMITView on GitHub

Run Greptile CLI for pre-push AI branch review. Use when asked for Greptile review, raycast/extensions pre-PR checks, or as part of the default pre-push review set with coderabbit and lintro-review. Max 2 runs per change set.

  • Installs packages

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run Greptile (greptile) for automated branch review before push.

    line 11
  2. Distinctive:

    Do not duplicate full analyze rubrics here.

    line 25
  3. Distinctive:

    Default pre-push flow when CI runs the review tools:

    line 29
  4. Very specific:

    Run greptile, coderabbit, and lintro-review in parallel (‖) when possible.

    line 37
  5. Distinctive:

    Run from the repository root on the feature branch

    line 66
  6. Distinctive:

    When asked to run Greptile or as part of pre-push review:

    line 70
  7. Distinctive:

    Ensure changes are committed and lint/tests pass

    line 72
  8. Very specific:

    Run greptile review -b main --agent (can run parallel with CodeRabbit)

    line 73
  9. Distinctive:

    After fixes to Greptile-sensitive areas, optional verification pass

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Greptile CLI Review

Run Greptile (greptile) for automated branch review before push. Pair with coderabbit and lintro-review for the default pre-push review set — the tools catch different issues and mirror CI. When Greptile (or CodeRabbit) is rate-limited, do not wait for the reset: the lintro-review pass is the review of record for that push.

Relationship to analyze-* skills

The analyze-code, analyze-project, and analyze-tests skills are for manual or agent-driven pre-review checks—they run concrete commands (lintro, ripgrep, coverage, etc.) and produce structured findings before you open a PR.

This skill uses Greptile CLI for external AI branch review. Follow the lint and test skills (or the commit skill, which includes them) before invoking Greptile. Do not duplicate full analyze rubrics here.

Relationship to coderabbit and lintro-review

Default pre-push flow when CI runs the review tools:

commit → [greptile ‖ coderabbit ‖ lintro-review] → pr

Each step names the skill to follow.

Run greptile, coderabbit, and lintro-review in parallel (‖) when possible. Greptile is typically faster (~1 min). Do not re-run on unchanged code.

Prerequisites

greptile login
greptile whoami

Install: npm i -g greptile or see Greptile CLI.

Commands

  • greptile review -b main --agent — Review current branch vs main (default for agents)
  • greptile review --diff — Findings inline with relevant code
  • greptile review --json — Machine-readable output (use instead of --agent for parsing)
  • greptile review --resume — Continue the latest unfinished review
  • greptile review show [ID] — Reopen a past review

--agent is an alias for --text (plain text, not JSON). Use --json when a tool needs structured output.

Rules

  • Max 2 Greptile runs per change set (workflow discipline)
  • Commit before running — Greptile reviews branch commits vs base; uncommitted changes are ignored
  • Default to -b main unless the repo uses a different default branch
  • Run from the repository root on the feature branch

Usage

When asked to run Greptile or as part of pre-push review:

  1. Ensure changes are committed and lint/tests pass
  2. Run greptile review -b main --agent (can run parallel with CodeRabbit)
  3. Analyze findings; address critical/major issues
  4. After fixes to Greptile-sensitive areas, optional verification pass
  5. Track run count (max 2 per change set)

For Raycast extension PRs, run static greps from pr-raycast before the CLI review.

Differences from CodeRabbit

CodeRabbitGreptile
Scopeall / committed / uncommittedBranch commits vs base only
Agent output--agent → JSON stream--agent → plain text; --json for machine-readable
Base branch--base main-b main

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.