New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Code Graph RAG Pull Request Review

by vitali87 in vitali87/code-graph-rag

Reviews pull requests to code-graph-rag, watching for wrong or missing graph edges in language parsers, cross-language consistency and tests that really exercise a fix.

MITAuto-check passedDevelopment

Install Code Graph RAG Pull Request Review

skills CLI
$ npx skills add vitali87/code-graph-rag --skill code-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vitali87/code-graph-rag code-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vitali87/code-graph-rag.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/code-review .claude/skills/code-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-review
GitHub stars
5.2k
Token cost
~685 tokens
SKILL.md length
374 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Reviews pull requests to code-graph-rag, watching for wrong or missing graph edges in language parsers, cross-language consistency and tests that really exercise a fix.

  • Reviewing a pull request that changes a language parser in code-graph-rag
  • SKILL.md covers Highest-value checks, Repository conventions and Calibration
  • Calls uv
  • Checking whether a parser fix needs the same change in other languages

What it does

A repository-specific review guide for code-graph-rag, which parses many languages with tree-sitter into a code graph of modules, classes and functions joined by edges such as CALLS, INSTANTIATES, DEFINES and IMPORTS. It points the reviewer at those edges, because most defects reaching main are wrong or missing edges for a particular language construct rather than crashes.

Checks include whether a changed construct yields every expected edge and no extra one, whether qualified names are attached correctly for cases like generics, verbatim identifiers and named constructors, whether name resolution respects scope, and whether a fix in one language parser should also be applied to its siblings. Tests need valid source in the language and must fail without the fix, and optional grammars cannot be assumed present. The reviewer skips style that ruff enforces and says briefly when a change is correct.

When your agent uses it

  • Reviewing a pull request that changes a language parser in code-graph-rag
  • Checking whether a parser fix needs the same change in other languages
  • Judging whether a new test fixture really exercises the fix

Example prompts

  • “Review this code-graph-rag PR that adds constructor handling for Dart.”
  • “Does the fixture in this PR fail without the fix? Check the INSTANTIATES edge for C# generics.”

What it can do on your machine

Read from SKILL.md and the folder at commit 39aeb70. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Code Graph RAG Pull Request Review loads about 685 tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~685

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vitali87/code-graph-rag at commit 39aeb70, republished under its MIT licence (© vitali87). 374 words, ~685 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Review pull requests to code-graph-rag, a multi-language code graph parser. Focuses on graph-edge correctness in language parsers, cross-language consistency, and test fixtures that actually exercise the fix.

Reviewing code-graph-rag

This repository parses source in many languages with tree-sitter and ingests the result into a code graph: nodes for modules, classes and functions, edges such as CALLS, INSTANTIATES, DEFINES and IMPORTS. Most defects that reach main are wrong or missing edges for a specific language construct, not crashes. Weight the review accordingly.

Highest-value checks

Graph-edge correctness
  • Does a new or changed construct produce every edge it should, and no edge it should not? A constructor call is the recurring example: it should record INSTANTIATES on the class and CALLS on the constructor.
  • Check the qualified name the edge is attached to. Name-mangling bugs recur here: duplicate-suffixed classes, verbatim identifiers (@class in C#), named constructors, generics (Box<int>()) and marker-stripping passes have each produced an edge pointing at a name that no node has.
  • Resolution must respect scope. A local variable shadowing a type means the receiver is not a construction; flag resolution that matches on bare name without checking what is actually in scope.
Language coverage and consistency
  • A fix in one language's parser usually applies to its siblings. If the change touches dart/, ask whether csharp/, cpp/, and the rest share the shape and need the same fix — or say explicitly why they do not.
  • Grammars are optional at install time. Code and tests must not assume a grammar is present; tests for one language should skip cleanly without it.
Show full SKILL.md (142 more words)Show less
Tests
  • Every behavioral fix needs a fixture reproducing the exact construct, and the fixture must be valid source in that language — an invalid fixture can pass for the wrong reason. Verify the assertion would fail without the fix.
  • Prefer asserting on specific edges between specific qualified names over asserting on counts, which pass accidentally.

Repository conventions

  • Python 3.12, ruff (line length 88), and uv for dependencies. Any dependency change must update uv.lock; CI fails on drift via uv lock --check.
  • Comments explain why, not what. Match the density of surrounding code.

Calibration

Report correctness problems: a wrong edge, a missed construct, a fixture that does not test the fix, a resolution that ignores scope. Do not report style that ruff already enforces, and do not restate what the diff does. If the change is correct, say so briefly rather than inventing findings.

© vitali87, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/code-review of vitali87/code-graph-rag.

Open the folder on GitHubat commit 39aeb70

Compare with similar skills

Code Graph RAG Pull Request Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Graph RAG Pull Request Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Graph RAG Pull Request Review this skillvitali87/code-graph-rag5.2k—~685Automated safety check: PassMIT
Code Review Skillawesome-skills/code-review-skill2.1k—~2.8kAutomated safety check: NotesMIT
Docling Pull Request Reviewdocling-project/docling69k—~1kAutomated safety check: PassMIT
Code Reviewerjewbetcha/opentrace1162 repos~1.1kAutomated safety check: NotesMIT
Coding Agentmastra-ai/mastra29k—~2.3kAutomated safety check: PassCustom licence
Code Review SkillRain-kl/OpenFlare288—~2.3kAutomated safety check: NotesMIT

Similar skills

  • Code Review Skill

    awesome-skills/code-review-skill

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C/.NET, Kotlin, Swift, Dart…

    2.1k GitHub stars~2.8k tokensUpdated 29 days ago
    DevelopmentAuto-check: notes

  • Docling Pull Request Review

    docling-project/docling

    Reviews or re-reviews a Docling pull request in fixed stages, with findings that can be reproduced and an explicit record of every check that was run.

    69k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed

  • Code Reviewer

    jewbetcha/opentrace

    Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go.

    116 GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check: notes

  • Coding Agent

    mastra-ai/mastra

    Authoring playbook for building agents that write, edit, review, or refactor code.

    29k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed

  • Code Review Skill

    Rain-kl/OpenFlare

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, PHP, Python, Django, Go, C/.NET, Kotlin, Swift, NestJS, C/C++, and more.

    288 GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check: notes

  • Create PR

    beyonders-studio/initiative

    Open a pull request for the current changes, then watch it to green — poll CI and the Greptile review together, addressing review findings as soon as they post instead of waiting for the full…

    171 GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed

Works with

Categories

Questions about Code Graph RAG Pull Request Review

What does Code Graph RAG Pull Request Review do?

Reviews pull requests to code-graph-rag, watching for wrong or missing graph edges in language parsers, cross-language consistency and tests that really exercise a fix. A repository-specific review guide for code-graph-rag, which parses many languages with tree-sitter into a code graph of modules, classes and functions joined by edges such as CALLS, INSTANTIATES, DEFINES and IMPORTS. It points the reviewer at those edges, because most defects reaching main are wrong or missing edges for a particular language construct rather than crashes.

When should I use Code Graph RAG Pull Request Review?

Code Graph RAG Pull Request Review fits situations like: reviewing a pull request that changes a language parser in code-graph-rag; checking whether a parser fix needs the same change in other languages; judging whether a new test fixture really exercises the fix.

How do I install Code Graph RAG Pull Request Review in Claude Code?

Run `npx skills add vitali87/code-graph-rag --skill code-review -a claude-code`. Or copy the skill folder (.github/skills/code-review in vitali87/code-graph-rag) into .claude/skills/code-review in your project. Claude Code loads it when a task matches its description.

How do I install Code Graph RAG Pull Request Review in Codex?

Run `npx skills add vitali87/code-graph-rag --skill code-review -a codex`. Or copy the skill folder (.github/skills/code-review in vitali87/code-graph-rag) into .agents/skills/code-review in your project. Codex loads it when a task matches its description.

Can I use Code Graph RAG Pull Request Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vitali87/code-graph-rag --skill code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Code Graph RAG Pull Request Review need to run?

Going by SKILL.md and its folder, Code Graph RAG Pull Request Review needs the command-line tools its instructions call (uv).

Does Code Graph RAG Pull Request Review access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Code Graph RAG Pull Request Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Graph RAG Pull Request Review use?

Code Graph RAG Pull Request Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Graph RAG Pull Request Review use?

About 685 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Graph RAG Pull Request Review?

Skills that share tags, products or a category with Code Graph RAG Pull Request Review: Code Review Skill (awesome-skills/code-review-skill, 2.1k stars), Docling Pull Request Review (docling-project/docling, 69k stars), Code Reviewer (jewbetcha/opentrace, 116 stars) and Coding Agent (mastra-ai/mastra, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Graph RAG Pull Request Review?

vitali87 (a GitHub user) maintains it in vitali87/code-graph-rag, which has 5,239 GitHub stars. The repository was last updated on October 8, 2026.

Source: vitali87/code-graph-rag on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.