Skip to main content

LLM Gate

Skill Verified Active
Part of:Pro Workflow

LLM-powered quality verification using prompt hooks. Validates commit messages, code patterns, and conventions using AI before allowing operations. Use to set up intelligent guardrails.

Purpose

To implement AI-driven quality gates that validate operations, enforce conventions, and prevent errors before they occur, enhancing workflow reliability.

Features

  • LLM-powered quality verification with prompt hooks
  • Validation of commit messages, code patterns, and conventions
  • Setup of intelligent guardrails for operations
  • Support for 'prompt' and 'agent' hook types
  • Example configurations for conventional commits, destructive commands, and secret leaks

Use Cases

  • Implementing commit message validation
  • Enforcing complex code conventions
  • Creating smart guardrails for critical operations
  • Preventing accidental secret leaks in file writes

Non-Goals

  • Performing code refactoring or automatic code fixes
  • Replacing traditional linters or static analysis tools entirely
  • Handling general purpose code generation tasks

Workflow

  1. Identify operations to gate
  2. Write a focused prompt hook
  3. Select appropriate LLM model and timeout
  4. Add hook to hooks.json
  5. Test hook before deployment

Practices

  • Prompt engineering
  • AI safety
  • Code quality
  • Workflow automation

Prerequisites

  • Claude Code environment
  • A suitable LLM model (Haiku, Sonnet)

Installation

First, add the marketplace

/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow

Quality Score

Verified
98 /100
Analyzed about 22 hours ago

Trust Signals

Last commit3 days ago
Stars2.1k
LicenseMIT
Status
View Source

Similar Extensions

Safe Mode

100

Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.

Skill
rohitg00

TradeMemory Protocol

100

Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or reviewing evolution logs. Triggers on "evolve", "discover patterns", "backtest", "evolution", "strategy generation", "candidate strategy".

Skill
mnemox-ai

Oh My Claudecode

100

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

Skill
Yeachan-Heo

Wrap Up Ritual

100

End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.

Skill
rohitg00

Trader Regime

100

Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy

Skill
ruvnet

Trading Memory

100

Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on "record trade", "remember trade", "recall", "similar trades", "performance", "behavioral", "disposition", "affective state", "confidence".

Skill
mnemox-ai

© 2025 SkillRepo · Find the right skill, skip the noise.