Hermes Skill Leaderboard

Plan engineering work and coordinate parallel agents.

Audit repository quality and track technical debt.

Map codebases into navigable knowledge graphs.

Plan, review, test, and ship software with specialist agents.

Reduce agent verbosity and context consumption.

Audit UX and refine frontend design.

Explore codebases and knowledge through interactive graphs.

Research recent trends across social and web sources.

Make agent responses concise, structured, and action-first.

Analyze scientific data and conduct research workflows.

Find and assemble reusable agent workflows.

Turn books and documents into reusable agent skills.

Investigate threats, test defenses, and assess security compliance.

Run engineering, product, marketing, and business workflows.

Preserve task plans and findings across agent sessions.

Create illustrated content and publish it across social platforms.

Distill personal knowledge and working styles into agent profiles.

Design, simulate, and prepare physical products for fabrication.

Coordinate research, experiments, and paper writing.

Train, evaluate, and research machine learning models.

Learn and maintain reusable skills from agent sessions.

Turn system descriptions into editable draw.io architecture diagrams.

Create motion design briefs and brandkits.

Remove generic patterns from interfaces, prose, and code.

Create animated HTML presentations with presenter controls.

Turn written material into illustrated PowerPoint presentations.

Optimize prompts and code through evaluation-driven search.

Structure agent contracts, payments, and dispute resolution.

Generate and edit images and extract visual prompts.

Create office documents, analyze data, and produce multimedia.

Plan and write LinkedIn content in your voice.

Hunt vulnerabilities and document security assessment findings.

Detect AI writing patterns and rewrite in your voice.

Preserve shared agent knowledge in an Obsidian vault.

Research markets and structure trading plans and risk reviews.

Audit search visibility and plan marketing campaigns.

Build AI, robotics, and accelerated computing workflows with NVIDIA tools.

Observe agent work and propose skill improvements.

Keep agent work focused and prevent unnecessary complexity.

Build a linked knowledge base from agent work and sources.

Convert images and PDFs into editable PowerPoint slides.

Plan and execute marketing across content, search, and advertising.

Apply business, design, and coding frameworks to projects.

Navigate French accounting, taxation, and administrative paperwork.

Produce videos from scripts, generated media, and footage.

Build web scrapers and automation with Apify.

Search, compare, and book hotels and flights.

Organize agent workflows through structured folders and files.

Find reusable workflows for development and business tasks.

Improve agent workflows through context engineering and evaluation.