Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Libragent Quality

ASecurity

Code quality validation for LibrAgent project. Use when performing code quality checks, refactoring validation, or ensuring code meets project standards for TypeScript/React frontend and Rust backend. Runs comprehensive validation including linting, formatting, type checking, build verification, and dead code detection.

10 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsjavascripttypescriptrustgojavabashreactrefactoringgitapi

Works with

cliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add fritzprix/libr-agent --skill libragent-quality --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Libragent Quality?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Libragent Quality
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fritzprix-libragent-quality-libr-agent/badge)](https://www.skillsdirectory.com/skills/fritzprix-libragent-quality-libr-agent)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: libragent-quality
description: Code quality validation for LibrAgent project. Use when performing code quality checks, refactoring validation, or ensuring code meets project standards for TypeScript/React frontend and Rust backend. Runs comprehensive validation including linting, formatting, type checking, build verification, and dead code detection.
license: MIT
---

# LibrAgent Code Quality Validation

This skill provides comprehensive code quality validation for the LibrAgent project, which uses a dual-stack architecture with React/TypeScript frontend and Rust/Tauri backend.

## Quick Start

For complete validation before commits or PRs:

```bash
pnpm refactor:validate
```

This runs all checks in sequence and ensures code quality across the entire stack.

## Individual Validation Commands

### Frontend (TypeScript/React)

```bash
# Linting - Check code style and potential errors
pnpm lint

# Format checking
pnpm format:check

# Auto-fix formatting issues
pnpm format

# Type checking and build
pnpm build

# Dead code detection
pnpm dead-code

# Run tests
pnpm test:run
```

### Backend (Rust)

```bash
# Format checking
pnpm rust:fmt:check

# Auto-format Rust code
pnpm rust:fmt

# Lint with clippy
pnpm rust:clippy

# Type checking
pnpm rust:check

# Check with all features
pnpm rust:check:all

# Run tests
pnpm rust:test

# Complete Rust validation
pnpm rust:validate
```

## Complete Validation Pipeline

The `refactor:validate` command executes:

1. **ESLint** - JavaScript/TypeScript code quality
2. **Prettier** - Code formatting consistency
3. **Vitest** - Test suite execution
4. **Rust fmt** - Rust code formatting
5. **Rust clippy** - Rust linting
6. **Rust check** - Rust compilation check with all features
7. **Rust test** - Rust test suite
8. **Vite build** - Production build verification
9. **Unimported** - Unused code detection

## Common Validation Scenarios

### Before Committing

```bash
pnpm refactor:validate
```

Wait for all checks to pass. Fix any errors reported.

### Quick Frontend Check

```bash
pnpm lint && pnpm format && pnpm build
```

### Quick Backend Check

```bash
pnpm rust:validate
```

### Fix Formatting Issues

```bash
# Fix frontend formatting
pnpm format

# Fix Rust formatting
pnpm rust:fmt
```

## Critical Project Rules

### TypeScript Rules

1. **Never use `any`** - Use precise types, `unknown` with type guards, or generics
2. **No ESLint-disable comments** - Fix the underlying issue instead
3. **Use centralized logger** - `getLogger('ComponentName')` not `console.*`
4. **No inline import types** - Use proper import statements at top of file

### Rust Rules

1. **Use `rustfmt`** - Always format before committing
2. **Fix clippy warnings** - No warnings allowed (`-D warnings` in CI)
3. **Handle errors explicitly** - Use `Result<T, E>` types
4. **Document public APIs** - Use `///` doc comments

### Architecture Rules

1. **Feature-based organization** - Components in `src/features/`
2. **Service layer pattern** - Business logic in `src/lib/`
3. **Compound components** - Use patterns like `Chat.Header`, `Chat.Messages`
4. **Type safety** - Define interfaces in `src/models/`

## Troubleshooting

### ESLint Errors

Check `.eslintrc.js` or `eslint.config.js` for rules. Fix code to match standards.

### Prettier Conflicts

Run `pnpm format` to auto-fix formatting issues.

### Rust Clippy Warnings

Read clippy suggestions carefully - they often indicate actual bugs or improvements.

### Build Failures

1. Check TypeScript errors: `tsc --noEmit`
2. Check Rust errors: `cd src-tauri && cargo check`
3. Verify dependencies: `pnpm install`

### Dead Code Detection

Review unimported output. Remove unused exports or add to ignore list if intentional.

## Integration with CI/CD

The project uses GitHub Actions for CI. All validation commands must pass before merge:

- ESLint must pass
- Prettier formatting must be correct
- TypeScript must compile without errors
- Rust must compile without warnings
- All tests must pass
- No dead code (with approved exceptions)

## Best Practices

1. **Run validation early and often** - Don't wait until PR time
2. **Fix issues incrementally** - Easier to debug when changes are small
3. **Read error messages carefully** - They often contain the solution
4. **Keep tests passing** - Don't commit broken tests
5. **Document exceptions** - If you must disable a rule, explain why

## Reference

For detailed project guidelines, see:

- `.github/copilot-instructions.md` - Complete coding standards
- `agents.md` - Agent-specific guidelines
- `docs/architecture/` - Architecture documentation
- `CONTRIBUTING.md` - Contribution guidelines

Attribution

fritzprixfritzprix
View sourceMore from fritzprix →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →