Co-Pilot
Updated a month ago

perks

Iidrevnii
0.0k
idrevnii/perks
72
Agent Score

💡 Summary

A personal collection of agentic skills for AI coding assistants to enhance decision-making processes.

🎯 Target Audience

AI developers looking to enhance coding assistantsProduct managers seeking better decision frameworksSoftware engineers wanting structured planning toolsTech educators teaching AI integrationFreelancers needing efficient project management skills

🤖 AI Roast:Powerful, but the setup might scare off the impatient.

Security AnalysisLow Risk

Risk: Low. Review: shell/CLI command execution. Run with least privilege and audit before enabling in production.

🎯 Perks

Personal collection of agentic skills for Claude Code, Antigravity, Cursor, Codex CLI, and other AI coding assistants.

Skills

| Skill | Description | |-------|-------------| | deep-plan | Structured clarification before decisions. Ensures agent asks questions instead of making autonomous decisions when multiple valid approaches exist. |

Installation

# Using npx npx skills add idrevnii/perks # Using bunx bunx skills add idrevnii/perks # Install specific skill only npx skills add idrevnii/perks --skill "deep-plan"

Compatibility

These skills work with any AI coding assistant that supports the universal SKILL.md format:

  • 🟣 Claude Code
  • 🔵 Antigravity
  • 🟠 Cursor
  • ⚪ Codex CLI
  • 🩵 GitHub Copilot

Usage

Skills can activate automatically based on context, but explicit invocation is recommended for best results:

@deep-plan let's discuss the architecture

The agent may also auto-trigger deep-plan when:

  • You're in planning mode
  • You ask to "discuss" or "plan" something
  • Agent faces decisions without clear context

License

MIT

5-Dim Analysis
Clarity8/10
Novelty6/10
Utility7/10
Completeness7/10
Maintainability8/10
Pros & Cons

Pros

  • Enhances decision-making clarity
  • Compatible with multiple AI coding assistants
  • Encourages structured planning
  • Easy installation via npx or bunx

Cons

  • Limited to specific AI assistants
  • May require explicit invocation for best results
  • Documentation could be clearer
  • Niche use case may limit broader appeal

Related Skills

pytorch

S
toolCode Lib
92/ 100

“It's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.”

agno

S
toolCode Lib
90/ 100

“It promises to be the Kubernetes for agents, but let's see if developers have the patience to learn yet another orchestration layer.”

nuxt-skills

S
toolCo-Pilot
90/ 100

“It's essentially a well-organized cheat sheet that turns your AI assistant into a Nuxt framework parrot.”

Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.

Copyright belongs to the original author idrevnii.