KS
Killer-Skills

review-rust-all — how to use review-rust-all how to use review-rust-all, review-rust-all setup guide, review-rust-all alternative, review-rust-all vs Feather-Flow, review-rust-all install, SQL orchestration tool for Rust, Rust code review best practices

v1.0.0
GitHub

About this Skill

Perfect for Code Review Agents needing comprehensive Rust code analysis and SQL validation. review-rust-all is a SQL orchestration tool that validates Rust code changes using make ci and sub-skills review-rust*

Features

Orchestrates review-rust* skills against changed files
Validates code using make ci command
Integrates with Feather-Flow schema validation framework
Supports static analysis as a first-class citizen
Works with Rust code and SQL validation

# Core Topics

datastx datastx
[1]
[0]
Updated: 2/27/2026

Quality Score

Top 5%
54
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add datastx/Feather-Flow/review-rust-all

Agent Capability Analysis

The review-rust-all MCP Server by datastx is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use review-rust-all, review-rust-all setup guide, review-rust-all alternative.

Ideal Agent Persona

Perfect for Code Review Agents needing comprehensive Rust code analysis and SQL validation.

Core Value

Empowers agents to orchestrate SQL validation and static analysis for Rust code using the Feather-Flow schema validation framework, leveraging sub-skills for in-depth review and validation with 'make ci', ensuring high-quality code changes.

Capabilities Granted for review-rust-all MCP Server

Validating Rust code changes against Feather-Flow schema
Performing static analysis on Rust codebases
Automating code reviews with 'make ci' validation

! Prerequisites & Limits

  • Requires Feather-Flow schema validation framework
  • Limited to Rust code review
  • Dependent on sub-skills for review criteria
Project
SKILL.md
3.0 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Comprehensive Rust Code Review

Orchestrates all three review-rust* skills against changed files, then validates with make ci. This skill contains no review criteria of its own — all opinions live in the sub-skills.

Context: Feather-Flow is a schema validation framework with static analysis as a first-class citizen. See HOW_FEATHERFLOW_WORKS.md for the full architecture. All code changes should be reviewed in the context of this goal — mandatory schemas, compile-time validation, AST-based dependency extraction, and no CTEs.

Project Layout

Cargo workspace with crates under crates/:

CratePathRole
ff-clicrates/ff-cli/Binary (CLI commands, integration tests)
ff-corecrates/ff-core/Library (shared types, config, DAG)
ff-analysiscrates/ff-analysis/Library (DataFusion static analysis)
ff-sqlcrates/ff-sql/Library (SQL parsing, lineage)
ff-jinjacrates/ff-jinja/Library (Jinja template rendering)
ff-dbcrates/ff-db/Library (database trait + DuckDB)
ff-testcrates/ff-test/Library (schema test generation)

Procedure

Step 1: Identify changed files

Find modified .rs files:

bash
1# If on a feature branch: 2git diff --name-only main -- '*.rs' 3 4# If on main with uncommitted changes: 5git diff --name-only -- '*.rs' 6git diff --cached --name-only -- '*.rs' 7 8# For the last commit: 9git diff --name-only HEAD~1 -- '*.rs'

Separate into two groups:

  • Production code: files under crates/*/src/
  • Test code: files under crates/*/tests/ or ending in _test.rs

Read every changed file in full before reviewing.

Step 2: Apply review-rust-code

Read the full skill file and apply all of its rules against every changed .rs file:

Read .claude/skills/review-rust-code/SKILL.md

Step 3: Apply review-rust-async-patterns

Check if any changed files contain async code:

bash
1grep -rl 'async\|\.await\|tokio::\|spawn' <changed-files>

Skip this step entirely if none do.

Otherwise, read the full skill file and apply all of its rules against each async file:

Read .claude/skills/review-rust-async-patterns/SKILL.md

Step 4: Apply review-rust-memory

Read the full skill file and apply all of its rules against every changed .rs file:

Read .claude/skills/review-rust-memory/SKILL.md

Step 5: Report findings

Combine all findings from steps 2-4 into a single report grouped by crate, then by file. Use the severity definitions from the sub-skills. Example format:

## ff-analysis

### crates/ff-analysis/src/datafusion_bridge/provider.rs

- **Error**: [description]
- **Warning**: [description]

## ff-cli

### crates/ff-cli/src/commands/common.rs

- **Info**: [description]

Step 6: Verify

Run make ci to confirm format, clippy, tests, and docs all pass.

Usage

/review-rust-all

Or target specific files:

/review-rust-all crates/ff-cli/src/commands/compile.rs crates/ff-analysis/src/datafusion_bridge/propagation.rs

Related Skills

Looking for an alternative to review-rust-all or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication