Amey-Thakur/AI-SKILLS

Plug-and-play skills and prompts for every AI coding agent

This repository also configures its own agents. See what AI-SKILLS tells them →

7Stars on the repository
200Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

ab-test-plan

01

Amey-Thakur/AI-SKILLS

Command Claude Code

Design an experiment with the hypothesis, sample size, and decision rule fixed before it runs.

not rated 7 4d ago A 18 tokens original MIT

ad-copy

02

Amey-Thakur/AI-SKILLS

Command Claude Code

Write advertising copy that leads with the benefit, speaks to one audience, and drives one clear action.

not rated 7 4d ago A 20 tokens original MIT

add-code-comments

03

Amey-Thakur/AI-SKILLS

Command Claude Code

Add docstrings and comments that explain why, matching the code's existing style, without noise.

not rated 7 4d ago A 19 tokens original MIT

adjust-tone

04

Amey-Thakur/AI-SKILLS

Command Claude Code

Rewrite text in a different tone (more formal, friendlier, more direct) while keeping the meaning.

not rated 7 4d ago A 21 tokens original MIT

agent-build-feature

05

Amey-Thakur/AI-SKILLS

Command Claude Code

A strict brief that makes a coding agent implement a feature end to end, matching the codebase and verifying it works.

not rated 7 4d ago A 24 tokens original MIT

agent-complete-task

06

Amey-Thakur/AI-SKILLS

Command Claude Code

A strict, goal-focused brief that makes a coding agent (Claude Code, Cursor, Antigravity) finish a task correctly and verify it.

not rated 7 4d ago A 29 tokens original MIT

agent-eval-design

07

Amey-Thakur/AI-SKILLS

Command Claude Code

Design an evaluation for an AI agent or LLM feature: what to test, how to grade it, and how to catch regressions.

not rated 7 4d ago A 28 tokens original MIT

Amey-Thakur/AI-SKILLS

Command Claude Code

A focused brief that makes a coding agent map an unfamiliar codebase so you (or it) can work in it confidently.

not rated 7 4d ago A 25 tokens original MIT

agent-fix-bug

09

Amey-Thakur/AI-SKILLS

Command Claude Code

A strict brief that makes a coding agent find the root cause of a bug, fix it minimally, and prove it is fixed.

not rated 7 4d ago A 26 tokens original MIT

agent-refactor-code

10

Amey-Thakur/AI-SKILLS

Command Claude Code

A strict brief that makes a coding agent refactor code without changing behavior, verifying nothing broke.

not rated 7 4d ago A 19 tokens original MIT

agent-system-prompt

11

Amey-Thakur/AI-SKILLS

Command Claude Code

Write a system prompt for an AI agent that defines its role, tools, boundaries, and output clearly enough to act reliably.

not rated 7 4d ago A 25 tokens original MIT

Amey-Thakur/AI-SKILLS

Command Claude Code

Decompose a complex task into clear subtasks an AI agent (or agents) can execute and verify step by step.

not rated 7 4d ago A 24 tokens original MIT

Amey-Thakur/AI-SKILLS

Command Claude Code

Write a tool/function definition for an AI agent with a description that steers use and parameters it fills correctly.

not rated 7 4d ago A 22 tokens original MIT

Amey-Thakur/AI-SKILLS

Command Claude Code

Design a multi-agent workflow with the right pattern, explicit handoffs, and human gates on consequential actions.

not rated 7 4d ago A 21 tokens original MIT

analyze-performance

16

Amey-Thakur/AI-SKILLS

Command Claude Code

Diagnose a performance problem from measurements rather than intuition, and propose the fix with the largest expected return.

not rated 7 4d ago A 21 tokens original MIT

api-design

17

Amey-Thakur/AI-SKILLS

Command Claude Code

Design a clean REST or GraphQL API from requirements, with sensible resources, methods, status codes, and error shapes.

not rated 7 4d ago A 24 tokens original MIT

api-docs-from-code

18

Amey-Thakur/AI-SKILLS

Command Claude Code

Generate accurate reference documentation for an API from its code, marking every inference.

not rated 7 4d ago A 15 tokens original MIT

api-migration-guide

19

Amey-Thakur/AI-SKILLS

Command Claude Code

Write a guide that gets consumers from an old API version to a new one with every breaking change addressed.

not rated 7 4d ago A 21 tokens original MIT

apology-email

20

Amey-Thakur/AI-SKILLS

Command Claude Code

Write a sincere, professional apology email that owns the mistake, addresses the impact, and offers a fix.

not rated 7 4d ago A 21 tokens original MIT

Amey-Thakur/AI-SKILLS

Command Claude Code

Write an ADR that captures a technical decision, its context, and its consequences so future teams know why.

not rated 7 4d ago A 21 tokens original MIT

Amey-Thakur/AI-SKILLS

Command Claude Code

Assess technical debt by what it costs now, and produce a paydown plan tied to upcoming work.

not rated 7 4d ago A 20 tokens original MIT

audit-accessibility

23

Amey-Thakur/AI-SKILLS

Command Claude Code

Audit a product against real assistive technology use, prioritised by who is blocked.

not rated 7 4d ago A 17 tokens original MIT

autoresearch

24

Amey-Thakur/AI-SKILLS

Command Claude Code

Run a full autonomous research investigation and return a verified, cited report: plan, search broadly, check primary sources, verify adversarially, and synthesize. Run like an /autoresearch command for a deep, trustworthy answer.

not rated 7 4d ago A 46 tokens original MIT

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: