Video & Animation

Use AB Method when a Claude Code task is too large for one pass and needs to be broken into focused tasks and missions that are completed incrementally instead of trying to solve the whole project in one conversation.

Browserable is an open-source, self-hostable browser automation library built for AI agents. This skill turns Browserable into a repeatable workflow for navigation, form filling, extraction, and browser-based task execution with local control instead of a hosted black box.

Run a repeatable evaluation suite for browser agents against static web task snapshots instead of judging them from demos or one-off tests.

Compare browser-agent reliability on a repeatable task and anti-bot suite before choosing a stack or claiming progress.

Benchmark clean and incremental Xcode builds, surface compile and configuration hotspots, and produce an approval-first optimization plan before changing project files.

Manages AWS CodePipeline stages and actions using AWS SDK for JavaScript (CodePipeline, CodeBuild, CodeDeploy APIs). Automates blue-green deployments and cross-account pipeline configurations.

Executes structured diagnostic runbooks when CloudWatch Anomaly Detection triggers alarms. Uses the AWS SDK CloudWatch client (GetMetricData, DescribeAlarms) to gather context and suggest remediations.

Orchestrates AWS data pipelines using @aws-sdk/client-s3 and @aws-sdk/client-sqs. Manages S3 object lifecycle with PutObjectCommand/GetObjectCommand, processes SQS message queues via ReceiveMessageCommand with long polling, and configures S3 event notifications to SQS for event-driven processing.

Resolves AWS SDK v3 client commands and service endpoint signatures using @aws-sdk/client-* packages. Maps IAM permission requirements to specific API calls with request/response type definitions.

Use GitHub Agentic Workflows to let an agent triage issues, inspect CI failures, or deliver scheduled repository upkeep inside GitHub Actions with explicit workflow definitions and reviewable runs. This is for bounded, repeatable repository operations, not for listing GitHub as a general coding platform.

AutoGen is Microsoft

Use ARIS to run Markdown-based agent skills for literature review, idea discovery, cross-model critique, experiment planning, and paper-writing support.

Investigates CloudWatch metric anomalies using the AWS SDK CloudWatch.getMetricData and Logs.filterLogEvents APIs. Correlates metric spikes with log patterns and deployment events from CodeDeploy.

Normalizes and enriches AWS CloudTrail JSON logs into OCSF (Open Cybersecurity Schema Framework) format. Maps eventSource/eventName pairs to MITRE ATT&CK technique IDs using the MITRE ATT&CK STIX API.

Check Python environments and requirements files for published vulnerabilities before shipping, upgrading, or approving dependency changes.

Use NotebookLM through MCP or a local REST API to run cited Q&A, generate Studio artifacts, and manage high-volume research batches.

Use GEO SEO Claude when Claude Code should run repeatable AI-search and SEO audits with citability, crawler, schema, platform, and report workflows.

Use Agent QA

Use smartcrop when an agent needs to choose a sensible crop automatically instead of center-cropping every image. The workflow scores visual saliency, returns crop coordinates for a target aspect ratio, and hands those coordinates to an image pipeline that renders the final thumbnail or social card.

Lint Nix expressions and automatically rewrite common anti-patterns before review or refactor work.

Lets agents operate Google NotebookLM/Gemini Notebook through a Python API, CLI, skill, MCP server, or REST server to create notebooks, add sources, ask cited questions, generate artifacts, and download exports.

Executes automated diagnostics using the AWS Systems Manager Automation API and SSM Documents. Collects system metrics via the CloudWatch GetMetricData API and correlates with AWS Health events.

Add controlled retries to pytest runs so agents can contain flaky tests and report final failures without rerunning whole suites by hand.

Assess a public HTTP(S) page before building browser automation, extraction, or an integration. Use this skill to collect bounded structural evidence, readiness signals, risk flags, acceptance tests, and remediation priorities without sending credentials or accessing private targets.