Top Agent Skills

Runs five parallel review agents on code changes, validates findings, triages them, and applies approved fixes after confirmation.

Analyze SQLite databases using the better-sqlite3 Node.js library, including querying, inserting, and iterating over rows.

Runs KICS to scan infrastructure-as-code files for security vulnerabilities and compliance issues.

Sets up a Node.js project that uses the AWS SDK for JavaScript v3 to interact with DynamoDB, including installation and basic usage steps.

Checks evidence about an unfamiliar autonomous agent before delegation, verifies signed Agent Guild passports, and returns a bounded hire, caution, or avoid recommendation without taking consequential action.

Sets up an AWS S3 MCP server using the AWS SDK for JavaScript, with installation and documentation links.

Translate a vague request or GitHub issue into a concrete, testable spec using five structured elements (problem, scope, acceptance criteria, edge cases, success criterion) before writing any code. Prevents scope creep, PR churn, and mid-implementation pivots.

Sets up the Stripe Node.js library for building payment integrations, with links to official documentation and source.

Installs and configures Apache Airflow via pip or Docker, with guidance on constraints, requirements, and deployment options.

Scaffolds AWS CDK projects and manages the CDK CLI installation for Node.js and Python environments.

Enhances plain-language requests into structured, reviewable prompts and inspects a self-hosted MCP gateway with provider-free defaults.

Manages Discord bots by providing installation guidance and references to the discord.js library for interacting with the Discord API.

Generates custom Semgrep rules from natural language descriptions of vulnerability patterns, verifying syntax with semgrep --validate and testing against sample fixtures with semgrep --test.

Builds multi-tenant Laravel SaaS applications with stancl/tenancy v3, covering tenant identification, data isolation, bootstrappers, queues, and production patterns.

Fetches MDN Web Docs content via the Yari API and search index, including browser compatibility data, Web API references, and CSS property documentation, with offline lookups using the BCD npm package.

Write and run analytical SQL queries against Redpanda SQL (Oxla), a distributed PostgreSQL-wire-compatible columnar database, including data loading, external sources, and type handling.

Build streaming data pipelines with Redpanda Connect using declarative YAML configs, Bloblang mappings, and component discovery. Covers running, linting, and dry-running pipelines.

Manage Kafka consumer groups on Redpanda with rpk group: list, describe, seek, delete groups, and delete offsets.

Manage Redpanda topics and produce or consume records from the CLI using the `rpk topic` command group. Use when creating or deleting topics with custom partitions, replication, or configs; altering topic configs or retention; adding partitions; trimming or deleting records; or using `rpk topic produce`/`consume` with.

Operate a self-managed Redpanda broker process and node from the CLI using the `rpk redpanda` command family and `rpk iotune`: node lifecycle (start/stop), production vs. development mode, kernel autotuning, node configuration (redpanda.yaml), and per-node Admin API operations including broker.

Manage schemas, subjects, compatibility levels, modes, and contexts in the Redpanda Schema Registry via the rpk registry CLI. Register or fetch Avro, Protobuf, and JSON schemas, set compatibility levels, change registry mode, and work with schema contexts.

Manage Redpanda authentication and authorization from the CLI using the `rpk security` command group, covering SASL/SCRAM users, Kafka ACLs, RBAC roles, and Cloud secrets.

Diagnose and observe an Oxla distributed analytical database using system catalog tables, Prometheus metrics, runtime log-level changes, and troubleshooting workflows for slow queries, node health, and memory/OOM pressure. Also covers debugging Oxla's external data sources, including the Redpanda/Kafka ingestion path.

Provisions and manages Redpanda Cloud Dedicated clusters via the Control Plane API, covering network and cluster creation, polling operations, and connectivity configuration.

Provisions and manages Redpanda Cloud Serverless clusters via the public Control Plane API, including authentication, cluster lifecycle, and data-plane operations.

Streams change data capture from Oracle Database into Redpanda or Kafka using the oracledb_cdc input in Redpanda Connect, which reads redo logs via LogMiner. Covers configuration, Oracle setup, checkpointing, and enterprise features.

Streams change data capture from MongoDB into Redpanda or Kafka using Redpanda Connect's mongodb_cdc input, covering Change Streams, snapshots, document modes, and resume-token checkpointing.

Streams change data capture from Google Cloud Spanner into Redpanda or Kafka using Redpanda Connect's gcp_spanner_cdc input, with partition-aware watermarked delivery and support for Redpanda Enterprise features.

Guides setup and operation of the aws_dynamodb_cdc input in Redpanda Connect, which streams change data capture from AWS DynamoDB into Redpanda or Kafka using DynamoDB Streams. Covers enabling streams, IAM policies, checkpoint tables, snapshot modes, table discovery, and operational constraints.

Streams change data capture from PostgreSQL into Redpanda or Kafka using Redpanda Connect's postgres_cdc input, covering setup, snapshotting, and troubleshooting.

Streams change data capture from Microsoft SQL Server into Redpanda or Kafka using Redpanda Connect's microsoft_sql_server_cdc input, covering setup, configuration, and troubleshooting.

Streams change data capture events from a TigerBeetle financial transactions database into Redpanda or Kafka using the tigerbeetle_cdc input, with checkpointing, filtering, and routing guidance.

Automates end-to-end QA: starts the app, exercises screens and API endpoints, verifies functionality and design quality, runs domain analysis, and fixes issues found.

Creates and manages Architecture Decision Records using the Michael Nygard format, including new ADR creation, retrospective analysis, superseding, deprecating, and index generation.

Runs a fast quality gate that detects the project stack, performs static analysis, checks cross-layer consistency, and fixes issues between pipeline phases.

Creates a convention-compliant pull request from the current branch, inferring details from git history and code changes.

Generates production-grade Kubernetes manifests including Deployments with probes and security contexts, Services, Ingress with TLS, HPA, PDB, NetworkPolicy, ConfigMaps, and Secrets, with optional Helm charts, Kustomize overlays, Istio mesh, and ArgoCD GitOps.

Runs a comprehensive QA audit on Unity, Unreal, Godot, or web game projects, covering null references, missing assets, scene transitions, physics, input, save/load, localization, audio, and platform certification.

Generates project documentation including README files, API docs, and changelogs by analyzing codebases and config files.

Analyzes development cycle and quality metrics to identify recurring issues, then generates additive patches to skill instructions to prevent them.

Polishes UI primitives one at a time using research-backed patterns: adds loading and icon states to buttons, replaces inline skeletons with primitives, adds secondary actions to errors, ensures 48px touch targets and visible focus indicators, and applies a standard motion token ladder.

Generates Mermaid architecture diagrams from a codebase, including C4 context and container diagrams, sequence diagrams for key flows, ER diagrams from database schemas, and module dependency graphs.

Generates an operations runbook from deployment configs, CI/CD pipelines, and monitoring setup, with copy-pasteable procedures for deployment, rollback, scaling, database maintenance, incident response, and troubleshooting.

Runs a read-only pre-deploy verification gate covering git status, builds, tests, migrations, secrets, and commit conventions, then reports READY or NOT READY.

Walks a running app across routes, states, and interactions to find real bugs, then root-causes, fixes, adds regression tests, and verifies each fix before committing.

Detects the project stack and generates production-ready multi-stage Dockerfiles with compose services, .dockerignore, non-root users, health checks, layer caching, and optional dev hot-reload profiles.

Diagnoses and fixes bugs in emergency mode with a maximum of two iterations, then commits, pushes, and creates a pull request.

Generates OpenAPI 3.1 documentation from an API codebase, auto-detecting frameworks, extracting routes and schemas, and setting up interactive docs.

Turns a pile of bugs, issues, and error reports into a ranked, actionable plan with reproduction evidence. Ingests GitHub issues via gh, TODO/FIXME scans, error logs, or a pasted list; attempts to reproduce or classify every item; scores by impact, frequency, fix cost, and regression risk; clusters duplicates; and.

Runs a hypothesis-driven debugging workflow that reproduces failures, forms discriminating tests, proves root cause via toggle, and delivers a fix, regression test, and postmortem.

Runs a complete testing pipeline covering full test suites, automated and manual tests, and logs execution metadata for the /evolve pipeline.

Builds distinctive, production-grade UI by committing to one of 12 named visual directions, implementing a real typography scale, spacing system, and one signature flourish, then gating the result through a measurable anti-slop checklist and contrast/touch-target verification.

Generates hand-drawn-style Excalidraw architecture diagrams from a codebase, including C4 context and container views, sequence diagrams for key flows, ER diagrams from database schemas, and module dependency graphs.

Generates a comprehensive developer onboarding guide from a codebase, covering tech stack, setup, architecture, conventions, and troubleshooting.

Scans a codebase for broken links and references, auto-fixes what it can, and flags what needs human review.

Analyzes test coverage across unit, integration, E2E, load, visual regression, contract, and accessibility dimensions, scores health, and routes remediation to specific testing sub-skills.

Runs a deep cross-layer consistency audit across a codebase, tracing features from UI to database to find broken wiring, missing handlers, model mismatches, and security gaps, then auto-fixes critical and warning issues.

Mines git history to compute development quality, velocity, and stability metrics, compares them against stored baselines, and tracks improvement over time.

Generates modular Terraform infrastructure-as-code for AWS, GCP, or Azure, including VPC, compute, database, cache, CDN, and monitoring with per-environment sizing, remote state, and cost estimates.

Writes human-sounding, SEO-optimized blog posts for skills-hub.ai in tutorial, deep-dive, opinion, listicle, or case-study styles.