seb1n/awesome-ai-agent-skills

API Design helps design production-quality RESTful APIs with resource modeling, HTTP methods, status codes, pagination, versioning, and OpenAPI docs. Use it when you need endpoint definitions, schemas, or a REST API specification.

API Integration builds reliable clients for external APIs using REST, webhooks, polling, or SDK wrappers. It handles authentication, rate limits, retries, and error handling when you need production-ready integration code.

Agent Evaluation designs reproducible tests for AI agents using task sets, rubrics, graders, baselines, and release gates. Use it when comparing prompts or models, validating a release, or investigating regressions.

Agent Observability designs privacy-aware telemetry for AI agents using traces, spans, metrics, dashboards, and alerts. Use it to debug failures, measure latency and cost, define SLOs, and audit agent behavior.

Agent Red Teaming plans, executes, documents, and retests authorized security assessments of AI agents and multi-agent workflows. Use it to test prompt injection, tool and identity boundaries, memory or cross-agent attacks, and remediation in approved environments.

Code Documentation generates docstrings, API references, and README files from source code. Use it when you need inline docs, usage guides, or project documentation for existing codebases.

Code Review performs structured reviews of files, diffs, or pull requests for bugs, security issues, performance problems, and maintainability concerns. Use it when you need actionable feedback on code changes.

Data Labeling designs and runs annotation workflows for machine learning datasets. It is used to set up labeling tools, pre-annotate data, manage quality control, and export labeled data for training.

Debugging systematically reproduces, isolates, diagnoses, fixes, and verifies software bugs from errors, stack traces, logs, or runtime behavior. Use it when you need to trace a failure to its root cause and confirm the fix with tests.

GraphQL API Design helps an agent design GraphQL schemas, queries, mutations, subscriptions, and resolver patterns from a spec or natural-language brief. Use it for cursor-based pagination, DataLoader batching, federation, and query safety patterns.

Human In The Loop designs auditable approval gates, escalation paths, and safe state transitions for AI agent workflows. Use it when an agent action needs review, dual control, or a controlled reject, retry, or recovery path.

Hyperparameter Tuning searches for better model settings using grid search, random search, Bayesian optimization, and Hyperband. Use it to tune models within a compute budget and compare results with cross-validation or validation splits.

MCP Server Building helps design, implement, and verify Model Context Protocol servers with clear tool contracts, authorization, safe transports, and interoperability tests. Use it when exposing an API or data source through MCP or preparing an MCP server for production.

ML Pipeline Creation designs reproducible machine-learning workflows with explicit data, training, evaluation, and deployment gates. Use it when turning model scripts into an orchestrated pipeline or connecting existing pipeline components safely.

Model Deployment helps package trained machine learning models into production services with APIs, containers, serverless functions, and orchestration. Use it when deploying a model or setting up health checks, validation, logging, and monitoring.

Model Training trains machine learning models end to end, from loading and preprocessing data through architecture selection, training loops, validation, and checkpointing. Use it when you need to fit a model or fine-tune one on a dataset.

Multi-Agent Orchestration designs bounded multi-agent workflows with task graphs, ownership, handoff contracts, approvals, recovery, and synthesis. Use it when a task has independent workstreams, specialized roles, parallel research or implementation, or coordination risks.

OAuth 2.0 Setup implements authorization code with PKCE, client credentials, and device code flows for API integrations. Use it when setting up secure authentication, token storage, refresh, and callback handling.

Prompt Injection Defense threat-models and hardens AI agents, RAG systems, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use it to map trust boundaries, reduce exposed authority, add tests, and document residual risk.

Refactoring improves existing code without changing its external behavior. Use it to identify code smells, apply safe refactoring patterns, and verify the result with tests.

Skill Supply Chain Audit reviews third-party skills, prompts, manifests, scripts, dependencies, and bundled assets for provenance, injection risk, permissions, execution, exfiltration, persistence, and update risk. Use it before installing or updating an untrusted skill or repository.

Testing generates, runs, and analyzes tests for a codebase across unit, integration, and end-to-end levels. Use it to cover source files, inspect failures, and review coverage gaps.

Tool Schema Design helps define model-facing tools with clear names, bounded JSON Schema parameters, explicit side effects, and safe defaults. Use it when building function-calling or MCP tools and when models choose the wrong tool or invent arguments.

Version Control manages Git repositories, branching, commits, merges, and pull requests. Use it to resolve conflicts, set up hooks, and keep history clean during team collaboration.

Webhook Setup builds webhook receivers and producer configuration with signature verification, idempotent processing, retries, and dead letter queues. Use it when setting up event-driven integrations that must handle duplicate, delayed, or failed deliveries.