85290 Skills Available

Find awesome
Agent Skills

Agent-Skills.md is a agent skills marketplace, to find the right agent skills for you.

Popular searches

tools

List all available Claude Code tools with their parameters and capabilities. Use to understand current tool availability before starting a task.

melodic-software
melodic-software
417

tool-design

Create custom tools using the @tool decorator for domain-specific agents. Use when building agent-specific tools, implementing MCP servers, or creating in-memory tools with the Agent SDK.

melodic-software
melodic-software
417

test

Run project test suite and report results in structured JSON format. Use to validate implementation before commit or review.

melodic-software
melodic-software
417

test-suite-setup

Set up test validation commands for any project type. Use when configuring test runners, setting up validation commands for a new project, or enabling closed-loop agent workflows.

melodic-software
melodic-software
417

test-e2e

Execute end-to-end test specification and report results. Use after implementation to validate user journeys before review.

melodic-software
melodic-software
417

template-meta-prompt-creation

Create Level 6 template meta-prompts that generate other prompts. Use when building prompt generators, designing high-leverage meta-prompts, or creating templates that scaffold other prompts.

melodic-software
melodic-software
417

template-engineering

Guide creation of meta-prompt templates that encode engineering workflows into reusable, scalable units. Use when creating slash commands that generate plans, designing workflow templates, or encoding team best practices into agentic prompts.

melodic-software
melodic-software
417

task-based-multiagent

Set up task-based multi-agent systems with shared task files. Use when setting up parallel agent execution, designing worktree isolation patterns, or implementing task file coordination.

melodic-software
melodic-software
417

system-prompt-engineering

Design effective system prompts for custom agents. Use when creating agent system prompts, defining agent identity and rules, or designing high-impact prompts that shape agent behavior.

melodic-software
melodic-software
417

swimlane-visualization

Design swimlane UI patterns for visualizing ADW execution. Use when building observability dashboards, monitoring agent workflows, or creating real-time status displays.

melodic-software
melodic-software
417

inverse-conway

Align architecture and team structure using inverse Conway maneuver

melodic-software
melodic-software
417

start-adw

Start an AI Developer Workflow with composable steps. Use when executing plan_build, plan_build_review, or plan_build_review_fix workflows.

melodic-software
melodic-software
417

standard-out-setup

Add console output and logging to make errors visible to agents. Standard out is a critical leverage point - without it, agents cannot see errors or understand application state. Use when agents fail silently, when debugging agentic workflows, or when setting up a new codebase for agentic coding.

melodic-software
melodic-software
417

ship

Validate state and merge branch to main for production deployment. Use as final ZTE step after all checks pass.

melodic-software
melodic-software
417

self-improve-prompt-design

Write self-improve prompts that sync expertise files with codebase reality. Use when creating maintenance workflows for agent experts, designing validation logic, or implementing the LEARN step of Act-Learn-Reuse.

melodic-software
melodic-software
417

seed-expertise

Generate initial expertise.yaml from codebase exploration. Use to bootstrap a new agent expert's mental model.

melodic-software
melodic-software
417

scout-and-build

Execute the scout-then-build pattern for a feature implementation. Use when you need to explore the codebase before implementing changes.

melodic-software
melodic-software
417

scaffold-layer

Create minimum viable agentic layer structure for a project. Use when adding agentic capabilities to a new project.

melodic-software
melodic-software
417

review-workflow-design

Design spec-based review workflows with visual proof and issue classification. Use when setting up review processes, validating against specifications, or implementing screenshot-based visual validation.

melodic-software
melodic-software
417

resolve-failed-test

Analyze a failed test, fix the underlying issue, and verify the fix. Use after /test reports failures.

melodic-software
melodic-software
417

resolve-failed-e2e-test

Analyze a failed E2E test, fix the underlying issue, and verify the fix. Use after /test-e2e reports failures.

melodic-software
melodic-software
417

reduce-delegate-framework

Apply R&D framework to optimize prompts and context. Use when optimizing context window usage, reducing prompt size, delegating to specialized agents, or applying systematic context management.

melodic-software
melodic-software
417

query-expert

Ask an agent expert a question using its expertise mental model. Use for quick domain-specific answers without code exploration.

melodic-software
melodic-software
417

pull-request

Create a GitHub pull request with full context linking back to the original issue. Use after implementation is complete and ready for review.

melodic-software
melodic-software
417

prompt-section-design

Design composable prompt sections for building agentic prompts. Use when creating reusable prompt components, designing LEGO-block prompt sections, or structuring prompts for the stakeholder trifecta.

melodic-software
melodic-software
417

prompt-level-selection

Guide selection of appropriate prompt level for a task. Use when choosing between simple prompts and complex workflows, applying the seven levels framework, or matching task complexity to prompt investment.

melodic-software
melodic-software
417

product-expert-design

Design user-facing agent experts for adaptive UX and personalization. Use when building product features that learn from user behavior, creating per-user expertise files, or implementing AI-driven personalization.

melodic-software
melodic-software
417

quality-attributes-taxonomy

The "-ilities" framework for non-functional requirements. Use when defining NFRs, evaluating architecture trade-offs, or ensuring quality attributes are addressed in system design. Covers scalability, reliability, availability, performance, security, maintainability, and more.

melodic-software
melodic-software
417

platform-design

Design Internal Developer Platforms, self-service capabilities, and golden paths

melodic-software
melodic-software
417

optimize-llm

Get LLM optimization recommendations for serving latency, inference costs, and throughput improvements

melodic-software
melodic-software
417

observability-patterns

Use when implementing observability strategy, correlating signals, or designing monitoring systems. Covers the three pillars (logs, metrics, traces) and their integration.

melodic-software
melodic-software
417

multi-region-deployment

Use when designing globally distributed systems, multi-region architectures, or disaster recovery strategies. Covers region selection, active-active vs active-passive, data replication, and failover patterns.

melodic-software
melodic-software
417

mtls-service-mesh

Use when implementing service-to-service security, mTLS, or service mesh patterns. Covers mutual TLS, Istio, Linkerd, certificate management, and service mesh security configurations.

melodic-software
melodic-software
417

mock-interview

Run an interactive system design mock interview - simulates a real interview with problem statement, follow-ups, and structured feedback

melodic-software
melodic-software
417

ml-system-design

End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems. Covers the complete lifecycle from data ingestion to model deployment and monitoring.

melodic-software
melodic-software
417

ml-pipeline

Design an ML system for a problem

melodic-software
melodic-software
417

ml-inference-optimization

ML inference latency optimization, model compression, distillation, caching strategies, and edge deployment patterns. Use when optimizing inference performance, reducing model size, or deploying ML at the edge.

melodic-software
melodic-software
417

llm-serving-patterns

LLM inference infrastructure, serving frameworks (vLLM, TGI, TensorRT-LLM), quantization techniques, batching strategies, and streaming response patterns. Use when designing LLM serving infrastructure, optimizing inference latency, or scaling LLM deployments.

melodic-software
melodic-software
417

latency-optimization

Use when optimizing end-to-end latency, reducing response times, or improving performance for latency-sensitive applications. Covers latency budgets, geographic routing, protocol optimization, and latency measurement techniques.

melodic-software
melodic-software
417

latency-budget

Calculate and allocate latency budgets for a system - breaks down end-to-end latency into component budgets with optimization recommendations

melodic-software
melodic-software
417

internal-developer-platform

Use when designing Internal Developer Platforms (IDPs), building platform teams, or improving developer experience. Covers platform engineering principles, Backstage, portal design, and platform team structures.

melodic-software
melodic-software
417

instrumentation-planning

Plan instrumentation strategy before implementation, covering what to instrument, naming conventions, cardinality management, and instrumentation budget

melodic-software
melodic-software
417

incident-response

Use when designing incident management processes, creating runbooks, or establishing on-call practices. Covers incident lifecycle, communication, and postmortems.

melodic-software
melodic-software
417

improve-expertise

Run self-improve on an expert's mental model to sync with codebase. Use periodically to keep expertise files accurate.

melodic-software
melodic-software
417

idempotency-patterns

Use when designing idempotent APIs, handling retries safely, or preventing duplicate operations. Covers idempotency keys, at-most-once semantics, and duplicate prevention.

melodic-software
melodic-software
417

golden-paths

Use when designing standardized development workflows, paved roads, or opinionated defaults. Covers golden path patterns, template design, developer workflow optimization, and guardrails.

melodic-software
melodic-software
417

gameday-planning

Use when planning GameDay exercises, designing failure scenarios, or conducting chaos drills. Covers GameDay preparation, execution, and follow-up.

melodic-software
melodic-software
417

explain

Explain a systems design concept

melodic-software
melodic-software
417

etl-elt-patterns

Use when designing data pipelines, choosing between ETL and ELT approaches, or implementing data transformation patterns. Covers modern data pipeline architecture.

melodic-software
melodic-software
417

estimation-techniques

Back-of-envelope calculations for system design. Use when estimating QPS, storage, bandwidth, or latency for capacity planning. Includes latency numbers every programmer should know and common estimation patterns.

melodic-software
melodic-software
417

Page 834 of 1706 · 85290 results

Adoption

Agent Skills are supported by leading AI development tools.

FAQ

Frequently asked questions about Agent Skills.

01

What are Agent Skills?

Agent Skills are reusable, production-ready capability packs for AI agents. Each skill lives in its own folder and is described by a SKILL.md file with metadata and instructions.

02

What does this agent-skills.md site do?

Agent Skills is a curated directory that indexes skill repositories and lets you browse, preview, and download skills in a consistent format.

03

Where are skills stored in a repo?

By default, the site scans the skills/ folder. You can also submit a URL that points directly to a specific skills folder.

04

What is required inside SKILL.md?

SKILL.md must include YAML frontmatter with at least name and description. The body contains the actual guidance and steps for the agent.

05

How can I submit a repo?

Click Submit in the header and paste a GitHub URL that points to a skills folder. We’ll parse it and add any valid skills to the directory.