alirezarezvani/claude-skills
1.6K installs 26.3K GitHub stars
promote
Moves learned patterns from MEMORY.md into CLAUDE.md or .claude/rules/. Makes proven agent behaviors subject to permanent enforcement.
Community score
0
0 up0 down THE AGENT SKILLS DIRECTORY
Small skills.
Big possibilities.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Browse all 10815 skills.
AxelMrak/ai
0 installs 5 GitHub stars
prompt-caching
Covers caching strategies for LLM prompts and responses. Includes Anthropic prompt caching and Cache Augmented Generation (CAG).
Community score
0
0 up0 downdavila7/claude-code-templates
1.4K installs 31.5K GitHub stars
prompt-engineer
Guides prompt structure, context management, output formatting, and evaluation. Covers system prompts, few-shot examples, and reasoning-oriented prompt design.
Community score
0
0 up0 downjeffallan/claude-skills
5K installs 11.6K GitHub stars
prompt-engineer
Writes and refactors prompt templates for accuracy and token efficiency, including few-shot examples, personas, and guardrails. Builds JSON and function-calling schemas and evaluation frameworks to measure model performance.
Community score
0
0 up0 downsickn33/agentic-awesome-skills
1.6K installs 46.8K GitHub stars
prompt-engineer
Transforms user prompts using frameworks such as RTF, RISEN, RODES, Chain of Density, RACE, and CLEAR. Also incorporates Chain of Thought and other named prompting approaches.
Community score
0
0 up0 downAxelMrak/ai
0 installs 5 GitHub stars
prompt-engineering
Provides guidance on prompt engineering patterns, best practices, and optimization. Supports refining prompts, learning prompting strategies, and debugging agent behavior.
Community score
0
0 up0 downgiuseppe-trisciuoglio/developer-kit
3.4K installs 348 GitHub stars
prompt-engineering
Provides workflows for writing, debugging, and optimizing LLM prompts. Covers few-shot example selection, chain-of-thought structuring, system prompt design, and template composition.
Community score
0
0 up0 downneolabhq/context-engineering-kit
1.3K installs 1.7K GitHub stars
prompt-engineering
Guides prompts for subagents and other LLM interactions, including commands, hooks, and agent skills. Supports prompt optimization, improved model outputs, and production template design.
Community score
0
0 up0 downsickn33/agentic-awesome-skills
1.4K installs 46.8K GitHub stars
prompt-engineering
Explains prompt engineering patterns, best practices, and optimization techniques. Supports improving prompts, learning prompting strategies, and debugging agent behavior.
Community score
0
0 up0 downwshobson/agents
21.8K installs 39.9K GitHub stars
prompt-engineering-patterns
Covers advanced prompt engineering patterns, including structured prompting, few-shot prompting, and chain-of-thought techniques. Supports prompt template design, performance improvement, and debugging of prompt issues.
Community score
0
0 up0 downreplicate/skills
2.1K installs 61 GitHub stars
prompt-images
Provides prompting techniques for Replicate image generation and editing models. Applies to writing image prompts and building image generation features.
Community score
0
0 up0 downShulkwiSEC/bb-huge
0 installs 22 GitHub stars
prompt-leaking-system-prompts
Extract the hidden foundational System Prompts, internal instructions, backend APIs, and confidential contextual data powering Large Language Model (LLM) applications using targeted prompt injection manipulation and adversarial psychological engineering.
Community score
0
0 up0 downLESS SETUP. MORE POSSIBILITY.Find it. Add it.
Find it. Add it.
Make something.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
Search the actual skill.
A name only tells half the story. Search the full description and instructions to find the right fit.
Get to know it.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Give your agent a new ability.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name