Agent Skills

Code Mode for MCP Servers

code-mode-skill

Add a sandboxed code mode tool to an MCP server so LLMs run small processing scripts against large API responses and only the script output enters the model con

ISC-Bench

ISC-Bench

Benchmark and pipeline for evaluating model safety (Internal Safety Collapse) using the TVD framework; builds prompts, runs models, extracts harmful content, an

Claw Bench

claw-bench

Benchmarking skill that guides an agent through a structured suite of capability tests and reporting steps for leaderboard submission.

AIML Spambot Benchmark (ISC)

ISC-Bench

Benchmark template for evaluating spam-detection models using anchored spam campaign examples (contains harmful anchoring content).

Darwin Skill 2.0

alchaincyf

Autonomous skill optimizer that uses a 9-dimension rubric to evaluate and improve SKILL.md files through an iterative, validation-gated loop.

Gemini Performance Benchmark Tool

domain-driven-design-skills

Compare Gemini File API vs Inline document approaches to optimize performance, caching, and document upload strategies.