awslabs

Migrate workloads from Google Cloud Platform to AWS — including AI and agentic workloads regardless of cloud provider. Triggers on: migrate from GCP, GCP to AWS, move off Google Cloud, migrate Terraform to AWS, migrate Cloud SQL to RDS, migrate GKE to EKS, migrate Cloud Run to Fargate, Google Cloud migration, migrate from OpenAI to Bedrock, move off OpenAI, switch from ChatGPT API to AWS, migrate from Gemini to Bedrock, migrate LangChain to Bedrock, migrate LangGraph to AWS, migrate agentic workloads to AWS, move AI workloads to AWS, migrate my AI app to AWS. Runs a 6-phase process: discover GCP resources from Terraform files, app code, or billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Includes AI provider migration guidance (for example, OpenAI to Amazon Bedrock) by selecting closest-fit Bedrock model families for required modality, latency/quality

Migrate workloads from Heroku to AWS. Triggers on: migrate from Heroku, Heroku to AWS, move off Heroku, migrate Heroku app, migrate Heroku Postgres to RDS, migrate Heroku Redis to ElastiCache, migrate Heroku Kafka to MSK, migrate dynos to Fargate, Heroku migration, move from Heroku to AWS, migrate Heroku Private Space, Heroku to ECS, Heroku to Fargate, leave Heroku, migrate off Heroku platform. Runs a 6-phase process: discover Heroku resources from Terraform files, Procfile/app.json, and optional billing exports, clarify migration requirements, design AWS architecture, estimate costs, generate migration artifacts, and collect optional feedback. Clarify must finish before Design, Estimate, or Generate. Uses a flat resource model (no clustering or dependency graphs) with deterministic mapping tables for core services (Dynos → Fargate, Postgres → RDS/Aurora, Redis → ElastiCache, Kafka → MSK) and a fast-path table for 13+ common add-ons. Cedar/Fir generation detection is detect-only in v1. Pipeline/Review Apps ar

Lightweight AI development lifecycle for building on AWS. A simplified take on the AI-DLC philosophy — think together, then build fast. Acts as a design partner that understands intent, proposes alternatives with trade-offs, and ships working code without the ceremony of full requirements/design/spec documents. Use when a founder says "build X on AWS", "add Y to my stack", "scaffold an API", or "write the CDK for Z".

Pre-verified fixes for Amazon Bedrock pitfalls — response key casing, IAM inference profile ARNs, model ID format, vision image normalization. Load during Bedrock-related migration work (Track 2 LLM migration or app code touching Bedrock).

Detect user-visible parameter-surface differences between source LLM provider and Bedrock. Loaded by ai-code-analyzer (Track 2) when source_provider is openai or google and same_model_family is false; consumed by ai-code-rewriter to apply the resolutions the user confirmed at the orchestration checkpoint.

Allowlist gate that blocks the rewriter from removing customer-pre-existing dependencies during dependency edits. Load before committing manifest changes. Complements ai-code-rewriter §12's lockfile regeneration; does not replace it.

Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock. End-to-end: assesses the codebase, then rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Not for standalone Bedrock cost estimates or infrastructure-only migration. Requires the migration-to-aws plugin for the Assess phase.

Validate a plan-supplied Bedrock model ID against live inference profiles in the target AWS account and correct it if stale. Load this when a plan's target_model_id needs to be used for the first time (ai-code-analyzer §10), or when a Bedrock call returns "invalid model identifier".

Reasoning skill for designing AWS GenAI and ML architectures for healthcare and life sciences workloads. Use when the user asks to choose between SageMaker and Bedrock, design a RAG system over medical literature, architect clinical NLP or medical imaging inference, plan genomics or drug discovery pipelines on AWS, address HIPAA/PHI compliance in ML systems, design MLOps for regulated clinical models, or optimize cost for HCLS ML workloads. Triggers include "AWS architecture", "SageMaker vs Bedrock", "HIPAA ML", "clinical RAG", "medical imaging inference", "genomics on AWS", "PHI training", "MLOps healthcare", "Bedrock guardrails", "HealthLake", "HCLS cloud architecture", "BAA compliance", "SageMaker endpoint", "Bedrock knowledge base", "clinical NLP on AWS", "FDA SaMD on AWS".

Reason about biomarker discovery and validation in HCLS — classifying biomarker intent, choosing feature-selection and cross-validation strategies, avoiding leakage, and planning external replication. Use when the user asks to discover, develop, or validate a biomarker; select features from high-dimensional omics or clinical data; design a validation study; choose evaluation metrics; justify sample size; combine multi-omics signals; or assess clinical utility. Triggers include "discover a biomarker", "validate biomarker", "prognostic vs predictive", "feature selection", "LASSO vs elastic net", "nested cross-validation", "data leakage", "C-index", "time-dependent AUC", "decision curve analysis", "external validation cohort", "events per variable", "optimism-corrected", "multi-omics integration", "clinical utility of a biomarker", "is this biomarker ready".

Reason about CDISC SDTM and ADaM implementation for regulatory submissions. Use when the user asks about SDTM domain mapping, ADaM dataset design, controlled terminology versioning, define.xml completeness, FDA or PMDA submission requirements, query prioritization by clinical impact, SUPPQUAL usage, or CDISC compliance review. Triggers include "SDTM mapping", "ADaM dataset", "CDISC compliance", "controlled terminology", "define.xml", "FDA submission data", "PMDA submission", "SDTM domain", "ADSL", "ADAE", "ADLB", "BDS structure", "SUPPQUAL", "RELREC", "value-level metadata", "CDISC CT", "regulatory submission data standards", "eCTD datasets", "SDTM 3.3", "ADaM 1.1", "query prioritization", "clinical data review".

Generate code to assign cell type labels to single-cell RNA-seq clusters using CellTypist, SingleR, marker-based annotation, or reference label transfer (scANVI/ingest). Triggers on requests to "annotate cell types", "label clusters", "run CellTypist", "SingleR annotation", "marker gene dotplot", "transfer labels from reference atlas", "cell identity", "automated annotation", "reference mapping", "scANVI label transfer", "canonical markers", "immune cell types", "hierarchical annotation", "majority voting CellTypist", "over-clustering annotation".

Cheminformatics pipeline for small-molecule property calculation, filtering, and similarity analysis using RDKit. Use when the user asks to compute molecular descriptors, filter compounds by Lipinski or Veber rules, detect PAINS, calculate fingerprint similarity, run matched molecular pair analysis, generate ADMET descriptors, or process SMILES. Triggers include "RDKit", "molecular descriptors", "Lipinski", "rule of five", "Veber", "PAINS", "pan-assay interference", "Morgan fingerprint", "Tanimoto", "fingerprint similarity", "matched molecular pair", "MMP", "mmpdb", "ADMET", "druglikeness", "SMILES", "cheminformatics", "compound filtering", "chemical similarity".

Pipeline skill for healthcare claims data parsing, analysis, and fraud detection. Use when the user asks to parse X12 837 or 835 claim files, manipulate ICD-10 CPT or HCPCS codes, detect billing pattern anomalies, profile providers against specialty peers, identify outlier billing behavior, validate NCCI edits programmatically, detect duplicate claims, run Benford's law analysis on charges, build claims data pipelines, or analyze E&M code distributions. Triggers include "parse X12 837", "parse 835", "claims SQL", "ICD-10 manipulation", "CPT code analysis", "provider profiling", "billing outlier", "NCCI validation code", "duplicate claim detection", "Benford's law charges", "claims ETL", "E&M distribution analysis", "claims analytics pipeline".

Reasoning skill for healthcare claims billing rules and fraud detection logic. Use when the user asks about CMS billing rules, place of service codes, global surgery periods, modifier usage (25 59 76 77), NCCI edit logic, column 1 column 2 code pairs, mutually exclusive procedures, modifier indicators, fraud waste and abuse patterns, E&M upcoding, unbundling, phantom billing, impossible day detection, coding error versus fraud distinction, FWA investigation methodology, or claims audit logic. Triggers include "CMS billing rules", "NCCI edits", "modifier 25", "modifier 59", "global surgery period", "upcoding", "unbundling", "phantom billing", "impossible day", "FWA", "fraud waste abuse", "coding error vs fraud", "claims audit", "billing compliance", "E&M level selection".

Reason about clinical data terminology standards — MedDRA hierarchy (LLT→PT→HLT→HLGT→SOC), ICD-10 code structure and grouping, SNOMED CT concept model, LOINC panel relationships, and mapping decisions between systems. Use when the user asks to code adverse events, map diagnoses to ICD-10, choose a coding granularity level, group AEs by SOC or PT, interpret SNOMED CT relationships, select LOINC codes for lab panels, convert between terminology systems, or decide when to aggregate at HLT vs PT level. Triggers include "MedDRA coding", "ICD-10 grouping", "SNOMED CT", "LOINC panel", "adverse event coding", "terminology mapping", "SOC table", "preferred term", "code hierarchy", "clinical coding", "AE frequency table", "diagnosis grouping", "lab code selection", "cross-walk between terminologies".

Migrate, modernize, and upgrade codebases to AWS. Run analysis on repos for tech debt, security vulnerabilities, and modernization opportunities. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. Use when the user says "migrate .NET to AWS", "upgrade Java to 17/21", "modernize COBOL", "modernize mainframe", "move VMware to EC2", "convert SQL Server to Aurora", "upgrade Python version", "migrate AWS SDK", "transform this codebase", "analyze for issues", "find tech debt", "what tech debt", "security vulnerabilities", "CVEs", "what's wrong with my code", "assess my repos", "where do I start", "find what's outdated", "analyze my repos", "AWS Transform - continuous modernization", "continuous modernization" or "continuous-modernization". Don't use for infrastructure provisioning, CI/CD pipelines, or general coding tasks.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/EF Core/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, distributed SQL database, serverless PostgreSQL-compatible database, migrate to DSQL, DSQL query plan, DSQL EXPLAIN ANALYZE, DSQL ENUM, DSQL foreign key, DSQL OCC retry, DSQL multi-region, DSQL JSONB, DSQL GIN index, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Evaluate, configure, and migrate workloads to AWS Lambda Managed Instances (LMI). Triggers on: Lambda Managed Instances, LMI, capacity provider, multi-concurrency Lambda, dedicated instance Lambda, EC2-backed Lambda, cold start elimination, Graviton Lambda, instance type for Lambda, scheduled scaling for LMI, Lambda cost optimization with Reserved Instances or Savings Plans. Also trigger when users describe high-volume predictable workloads seeking cost savings, want to scale LMI capacity on a schedule, or compare Lambda vs EC2 for steady-state traffic. For standard Lambda without LMI, use the aws-lambda skill instead.

Build, run, debug, and operate applications on AWS Lambda MicroVMs — Firecracker-isolated, snapshot-resumable serverless compute environments that run inside a container with up to 8-hour lifetimes. Triggers on: Lambda MicroVMs, Firecracker isolation, snapshot-resumable compute, suspend/resume, sandboxed or untrusted code execution, AI/agent code-execution sandboxes, interactive code playgrounds and notebooks (Jupyter, REPLs), reinforcement-learning environments, multi-tenant CI executors and build runners, sessionful game or simulation servers, isolated security scanners, long-lived sessions, or port-listening servers (gRPC, WebSocket, custom TCP). For standard event-driven Lambda functions, use the aws-lambda skill instead.

Deploy to AWS Elastic Beanstalk. Triggers on: elastic beanstalk, EB, managed EC2 platform, web app with managed patching, worker on EC2, Heroku alternative, don't want to manage servers or container orchestration, migrate from Heroku, managed operational lifecycle. Covers Elastic Beanstalk on EC2 for web and worker applications.

Design, build, deploy, test, and debug serverless applications with AWS Lambda. Triggers on phrases like: Lambda function, event source, serverless application, API Gateway, EventBridge, Step Functions, serverless API, event-driven architecture, Lambda trigger. For deploying non-serverless apps to AWS, use deploy-on-aws plugin instead.

Build workflows with AWS Step Functions state machines using the JSONata query language. Covers Amazon States Language (ASL) structure, state types, variables, data transformation, error handling, AWS service integration, and migrating from the JSONPath to the JSONata query language.

Generates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model", "run a benchmark", "test model performance", "how did my model perform", "compare models", or other similar requests.

Author live dashboard UI from an agent via the `emit_ui` MCP tool. Emit one of six allow-listed components (approval_card, choice_prompt, diff_summary, progress, metric, agent_card) with JSON props and it renders in any AG-UI client watching the fleet. Use when you want the operator to see a decision, a diff, or a status readout instead of scrolling terminal text. Arbitrary HTML/markup is refused.

Author and run CAO Python workflow scripts — multi-step, parameterized, fan-out orchestrations executed by `cao workflow run`. Use when the user wants a repeatable multi-step job (e.g. data analysis over many files, a review pipeline, a parameterized batch). Authoring ends at a validated script file; running it is a separate, user-approved step.

Create a new CAO (CLI Agent Orchestrator) plugin. Use this skill whenever the user wants to add a plugin that reacts to CAO lifecycle or messaging events, scaffold a plugin package, understand plugin requirements, or integrate an external system (Discord, Slack, dashboards, logging, metrics) with CAO. Also use when the user asks what plugin events are available, how plugin discovery works, or how to install a plugin into a CAO environment.

Create a new CLI agent provider for CAO (CLI Agent Orchestrator). Use this skill whenever the user wants to add support for a new CLI-based AI agent (e.g., a new coding assistant CLI), integrate a new provider, or scaffold a provider implementation. Also use when the user asks about the provider architecture, what files to modify, or how providers work in CAO.

Interact with CAO (CLI Agent Orchestrator) — launch multi-agent sessions, check status, send follow-up instructions, unblock stuck terminals, or shut down sessions. Use when working with CAO sessions in any capacity.

Enable, operate, and extend CAO's MCP Apps surface — the sandboxed host-rendered fleet UI (SEP-1865) with the ui://cao/* views, the topology widget, the submit_command mutation choke point, SEP-2133 capability advertisement, and the default-off OAuth scope layer. Use whenever the user wants to turn on the MCP Apps UI, observe/steer a CAO fleet from inside an MCP App host (Claude / Claude Desktop, ChatGPT, VS Code GitHub Copilot, Microsoft 365 Copilot, Goose, Postman, MCPJam, Archestra.AI), debug why the views don't render, build the frontend bundles, or extend the surface (new view, tool, or command kind).

Store, recall, and forget durable facts with CAO memory — user preferences, project conventions, decisions, and corrections that should persist across sessions and agents. Use proactively to check memory before asking the user, and to save anything worth remembering. Distinct from any provider-native memory.

Supervisor-side orchestration patterns for assign, handoff, and idle inbox delivery in CAO

Phase 1 Business Context Analysis guide. Use when starting a threat model, setting business context, or configuring business features like industry sector, data sensitivity, and regulatory requirements.

Phase 2 Architecture Analysis guide. Use when documenting system components, connections, data stores, or analyzing technical architecture for threat modeling.

Phase 3 Threat Actor Analysis guide. Use when identifying threat actors, setting relevance and priority, or analyzing who might attack the system.

Phase 4 Trust Boundary Analysis guide. Use when defining trust zones, crossing points, and security boundaries between system components.

Phase 5 Asset Flow Analysis guide. Use when identifying valuable assets, tracking data flows, or analyzing how sensitive data moves through the system.

Phase 6 Threat Identification guide with STRIDE methodology reference. Use when identifying threats, categorizing security issues, applying STRIDE analysis, or assessing threat severity and likelihood.

Phase 7.5 Code Validation guide. Use when validating threats against actual code, checking which security controls are implemented, or generating remediation reports.

Phase 7 Mitigation Planning guide. Use when creating mitigations, linking them to threats, validating coverage, or planning security controls.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, FK replacement code generation, OCC retry patterns, ORM migration (Django/Hibernate/Rails), DDL operations, query plan explainability, SQL compatibility validation, and bulk data loading. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow, DSQL foreign key, DSQL OCC retry, DSQL multi-region, load into DSQL, load CSV into DSQL, bulk load DSQL, aurora-dsql-loader.

Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.

Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too much", "cost breakdown", "expense analysis", or "how efficient are our operations". NOT for revenue or top-line analysis.

Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also use for "give me the highlights", "what do I need to know", or "quick financial update".

Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter comparison across all quarters", or any multi-period longitudinal analysis.

Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance review, P&L analysis, or interpreting financial ratios against benchmarks.

Deep-dives into revenue growth patterns, growth rates, and growth quality. Use when the user asks specifically about revenue growth, top-line performance, sales growth, revenue acceleration or deceleration, growth trajectory, or wants to understand what is driving revenue changes. NOT for cost or margin analysis — this skill is revenue-focused only.

Format weather information with emoji, temperature ranges, and activity recommendations

Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".

Patterns for unit testing bash scripts using bats-core, including AWS CLI mocking, jq/sed/awk testing, and cross-platform portability

Build the Slurm compute node container image via CodeBuild or local Docker, generate SSH keys, and render Helm values using setup.sh

Deploy HyperPod EKS infrastructure using deploy.sh via CloudFormation or Terraform, including AZ resolution, stack outputs, and kubeconfig setup

Install cert-manager, AWS LB Controller (Pod Identity), MariaDB, Slurm operator, and Slurm cluster on HyperPod EKS using install.sh, including subnet tagging and NLB configuration for SSH access

Validate all prerequisites (CLI tools, AWS credentials, environment variables, kubectl context) before running slinky-slurm deployment scripts

Post-deployment health checks for slinky-slurm including pod status, Slurm node registration, SSH connectivity, and test job submission

Implement a GitHub issue end-to-end — branch, code, test, docs, and commit.

Increment the release version, draft release notes, and prepare a GitHub release.

Finalize dev work on an issue branch — update docs, push, and open a PR.

Create a new ArgoCD addon in this project. Use when adding a Kubernetes application deployed via ArgoCD and managed through Terraform, including the ArgoCD Application manifest, Terraform resources, and variables.

Create a new Karpenter NodePool in this project. Use when adding or configuring EC2 instance provisioning for workloads on EKS, including standard Karpenter and EKS Auto Mode nodepools, EFA networking for P-family instances, and toggle strategies.

Use when the user asks to create, update, or render an AWS architecture diagram (or a cloud/infrastructure diagram using AWS service icons) — e.g. "diagram our AWS setup", "architecture diagram with CloudFront/S3/EKS/RDS", "update docs/image.png", "make an AWS infra diagram". Produces a clean, poster-style diagram with OFFICIAL AWS icons as a self-contained SVG, rendered to PNG. Not for generic flowcharts/ER/UML (use the drawio skill for those).

Ship work in the llm-evaluation-system repo end-to-end — commit with conventional-commit messages, push to a feature branch (never directly to main), open a PR with the proper title format, and after merge either run `make release` to publish to PyPI or just clean up branches. Use this skill whenever the user says ship/commit/push/open a PR/release/publish, or after code changes are done and ready to go out. Don't invent your own git workflow — invoke this skill so the repo conventions (conventional commits, manual release, setuptools-scm tag flow, branch cleanup) are applied consistently.

LLM judge agent for grading AI agent eval transcripts. Checks deterministic assertions (transcript_contains, tool_called) and uses LLM reasoning for behavioral assertions (llm_judge). Returns structured JSON grades.

Simulated human agent for eval scenarios. Interacts with the agent under test via the ACP bridge, following the scenario goal and guidance to respond to agent questions, approve tool calls, and drive the multi-turn flow to completion.