AI Agent Skills Marketplace Skills are portable instruction sets that extend what AI coding agents can do. Each skill is a SKILL.md file your agent reads to learn new capabilities, from writing tests to deploying infrastructure. Compatible with Claude Code, OpenClaw, Codex CLI, Cursor, and 20+ agents. Browse the marketplace to find skills built by the community, or publish your own .
Evaluates AI coding agent platforms across five structural dimensions that determine real-world performance independently of model quality, so teams select on architectural fit rather than benchmark scores.
agent-architecture ai-agents ai-coding-agents +12
Give AI agents the ability to trace decision chains, reconstruct causal sequences, and reason over complex event timelines spanning months or years.
agent-memory causal-reasoning data-engineering +4
Enforce senior-level coding standards with a focus on verification, minimal diffs, and evidence-based bug fixing.
code-review coding-standards debugging +2
Professional prompt engineering patterns for building robust, secure, and production-ready LLM applications.
ai-agents json-schema llm-ops +3
subagent-orchestrator (Develop based on the Claude Code sourcemap) by Roy Yuen
Turn your AI agent into a coordinator that manages parallel subagents for complex coding and research tasks.
autonomous-agents devops multi-agent +2
Professional prompt engineering, audit, and evaluation system for production-grade AI agents and workflows.
ai-agents governance llm-ops +2
Standardized accessibility descriptions and verified analysis for electronic, hydraulic, and pneumatic schematics.
accessibility docx-automation electronics +2
Upgrade your AI agent with a senior-level engineering SOP focused on inspection, minimal diffs, and hard verification.
code-quality coding-assistant debugging +2
benchmarking-ai-agents-beyond-models by Loreto.io
Published AI benchmarks measure brains in jars. They test models in isolation or within a single reference harness — and then attribute all performance to the model. This skill teaches you to decompose agent performance into its two actual components: model capability and harness multiplier. The result is evaluations that predict real-world behavior instead of benchmark theater.
agent-evaluation ai-agents ai-benchmarking +10
Generate professional, formula-driven DMAIC/DFSS artifacts, Excel tools, and interactive Lean Six Sigma visualizations.
data-analysis dmaic industrial-engineering +3
High-speed intake for shaping vague prompts, triaging complex tasks, and compressing context for efficient execution.
agent-orchestration context-management productivity +2
Extract structured, evidence-backed AI persona profiles from historical chat logs, emails, and documents.
agent-tuning data-analysis nlp +2
Turn raw agent traces and tool logs into professional production-readiness audits and remediation reports.
agent-monitoring llmops python +2
Design, debug, and harden AI control loops with explicit contracts and automated verification harnesses.
ai-agents devops llm-ops +3
Transform your agent into a Senior Engineer that analyzes architecture and reuses code before writing a single line.
architecture code-design refactoring +2
A universal, multi-role AI engineering team for autonomous planning, implementation, and rigorous code review.
architecture autonomous-agents devops +2
The "Skill for building Skills": Automate creating, testing, and optimisation of custom workflows.
automation developer-tools iteration +3
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.
code-quality debugging refactoring +2
Senior-level iOS engineering agent specializing in Swift 6, SwiftUI, SwiftData, and Apple Intelligence.
apple-intelligence ios-development mobile-apps +3
Expert API architect to design, review, and audit REST, GraphQL, and event-driven API specifications.
api api-design architecture +7
prompt-spec-engineer (support Auto rewrite prompt) by Roy Yuen
Turn vague prompts into professional task specifications, optimized prompts, and verification test suites.
agent-orchestration ai-ops automation +2
Protect any Windows Java application using secure CloudFlare architecture by Bidsmarket
Protect Java desktop apps by migrating sensitive logic and API keys to a secure, Cloudflare-backed thin-client architecture.
cloudflare-workers desktop-apps java +5
Reduce Manus v5 credit consumption by 30-75% through intelligent task routing and autonomous strategy selection.
agent-orchestration cost-optimization efficiency +2
document-control-data-management by Roy Yuen
Generate structured document control packs, metadata schemas, and project registries from intake data.
data-management document-control engineering +2