Tariux/AI-Skills-Not-Awesome

A curated collection of operational system prompts and behavioral patterns for AI assistants, LLM agents, and prompt engineers. Each `.skill.md` file can be injected as a primary system instruction to enforce specific reasoning, execution, or formatting behaviors.

49Stars on the repository
14Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied

Absolute Mode

01

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Enforces decisive execution without confirmation requests; suppresses redundant explanations and prioritizes direct action.

not rated 49 +1 yesterday A 21 tokens

Project Analyzer

02

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Produces a concise, structured analysis report of a codebase: dependencies, workflow, and context.

not rated 49 +1 yesterday A 22 tokens

Package Audit

03

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Produces a rigorous, forward-looking technical audit with severity ratings and improvement directions.

not rated 49 +1 yesterday A 18 tokens

Combo Developer

04

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Automatically routes requests to the correct skill (Planner, Debugger, Advisor, etc.) based on first message content.

not rated 49 +1 yesterday A 26 tokens

Debugging

05

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Systematic root-cause isolation and minimal fix proposal for software bugs.

not rated 49 +1 yesterday A 17 tokens

Documentation

06

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Generates or fills gaps in project documentation (README, AGENTS.md, /docs, inline comments).

not rated 49 +1 yesterday A 23 tokens

No-Slop

08

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Writing engine that audits and rewrites prose for AI-resistance, fidelity, and mechanical tell removal.

not rated 49 +1 yesterday A 24 tokens

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Systems-level performance engineer: identifies hotspots, provides optimized code with resource justifications.

not rated 49 +1 yesterday A 20 tokens

Planner

11

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Breaks down complex tasks into ordered, verifiable sub-tasks with dependencies, milestones, and risks.

not rated 49 +1 yesterday A 23 tokens

Code Simplifier

12

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Rewrites code to its simplest possible form while preserving exact external behavior (KISS, YAGNI).

not rated 49 +1 yesterday A 25 tokens

Test Engineer

13

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Creates or completes a medium-coverage test suite: unit, component, and critical e2e flows.

not rated 49 +1 yesterday A 24 tokens

Tariux/AI-Skills-Not-Awesome

Skill Claude CodeCodex

Builds compact, high-signal, copy-paste-ready project context for handing software tasks to a separate web chatbot or AI agent with limited context. Use when a developer needs a reusable global project brief, or a task-focused brief that preserves global constraints, identifies relevant files, and asks only for…

not rated 49 +1 yesterday B 72 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: