Browsing:

Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.

16 available skills

hugging-face-evaluation

[ Official ]
Logo of huggingface
huggingface

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations

9.5k
0
AI

Healthcare AI Evaluation

Logo of MFD3000
MFD3000

Guide evaluation of healthcare AI systems with domain-specific safety criteria, clinical accuracy rubrics, and score interpretation. Use when building or reviewing health/medical AI evaluations.

0
0
Developer

skill-stocktake

[ Featured ]
Logo of affaan-m
affaan-m

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

108.5k
0
Developer

cpp-testing

[ Featured ]
Logo of affaan-m
affaan-m

cpp-testing is a specialized AI agent skill for automating C++ test workflows using GoogleTest and CMake.

108.5k
0
Developer

requesting-code-review

[ Featured ]
Logo of obra
obra

requesting-code-review is a skill that enables developers to request code reviews, ensuring work meets requirements through subagent-driven evaluation

113.6k
0
Productivity

sandbox-sdk

[ Official ]
Logo of cloudflare
cloudflare

sandbox-sdk is a Cloudflare Workers solution for secure code execution, providing a sandboxed environment for running untrusted code, ideal for developers needing isolated execution.

711
0
Developer

gemini

Logo of interactive-inc
interactive-inc

Get alternative perspectives via Google Gemini on complex design decisions, architecture trade-offs, stuck debugging, or approach evaluation.

0
0
Developer

Benchmark Manager

Logo of sunholo-data
sunholo-data

Benchmark Manager is a skill that manages AILANG evaluation benchmarks with features like prompt integration, debugging, and best practices.

21
0
AI

eval

Logo of Kastalien-Research
Kastalien-Research

eval is a Thoughtbox intention ledger for agents, designed to evaluate AI decisions against its decision-making metrics.

52
0
AI

analyze-experiment

Logo of niznik-dev
niznik-dev

Generate visualizations from completed experiment evaluations using inspect-viz. Use after run-experiment to create interactive HTML plots from inspect-ai evaluation logs.

0
0
Developer

mixseek-skills

Logo of drillan
drillan

MixSeek Agent Skills collection for AI coding assistants. Provides workspace management, team configuration, evaluation setup, and debugging tools for MixSeek-Core.

0
0
Developer

agent-evaluation

Logo of oimiragieo
oimiragieo

LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evi

14
0
Developer