- Risk Stratification IndicesReasoning skill for clinical risk stratification index selection and interpretation. Use when the user asks about LACE scores, Charlson Comorbidity Index, Elixhauser Index, readmission risk scoring, comorbidity weighting, SDOH Z-codes, Area Deprivation Index, or population health stratification methods.awslabs/hcls-agent-skills42
- Rna Seq AnalysisBulk RNA-seq analysis pipeline covering alignment (STAR), quantification (Salmon, featureCounts), and differential expression (DESeq2). Triggers on RNA-seq, STAR, Salmon, DESeq2, differential expression, gene expression, tximport, featureCounts, transcriptomics, "bulk RNA-seq", "STAR alignment", "Salmon quantification", "gene counts", "DESeq2 results", "shrinkage estimator", "volcano plot RNA-seq".awslabs/hcls-agent-skills42
- Rwd Cohort AnalysisReal-world data cohort analysis pipeline for claims and EHR data — cohort identification with ICD-10, NDC, and CPT codes, medication adherence metrics (PDC/MPR), propensity score estimation and balance diagnostics, Kaplan-Meier survival curves, and Cox proportional hazards models. Use when the user mentions claims data, cohort identification, ICD-10 codes, NDC codes, CPT codes, medication adherence, PDC, MPR, propensity score, SMD balance, Kaplan-Meier, Cox model, Schoenfeld residuals, survival awslabs/hcls-agent-skills42
- Scrna Seq PipelineScanpy-based single-cell RNA-seq analysis pipeline covering loading (10X, h5ad), QC, normalization, HVG selection, PCA/UMAP, Leiden clustering, differential expression, and batch correction (Harmony, scVI). Use when the user mentions single-cell, scRNA-seq, Scanpy, AnnData, UMAP, clustering, 10X, h5ad, leiden, highly variable genes, Harmony, scVI, cluster cells, find marker genes, filter low-quality cells, gene expression matrix, doublet removal, normalize counts, dimensionality reduction, cell awslabs/hcls-agent-skills42
- Structure Based Drug DesignReasoning skill for structure-based drug design strategy. Use when the user asks to assess target druggability, choose a docking strategy, select a scoring function, define a binding site, interpret docking results, plan molecular dynamics or free energy perturbation (FEP), design a virtual screening cascade, or decide between fragment-based and HTS screening. Triggers include "drug design", "druggability", "docking strategy", "scoring function", "binding pocket", "molecular dynamics", "FEP", "Sawslabs/hcls-agent-skills42
- Trajectory AnalysisSingle-cell trajectory inference pipeline covering diffusion pseudotime (DPT), PAGA, RNA velocity with scVelo, and fate mapping with CellRank. Use when the user mentions pseudotime, trajectory, lineage, differentiation, RNA velocity, scVelo, CellRank, PAGA, diffusion map, fate probabilities, terminal states, spliced/unspliced, velocyto, order cells by development, cell differentiation path, cell fate, branching analysis, monocle, developmental trajectory, stem cell differentiation, progenitor toawslabs/hcls-agent-skills42
- Translational ResearchReason about translational research problems in HCLS — especially neurology and hypothesis validation. Use when the user asks to design a validation study, evaluate a target, qualify a biomarker, choose endpoints, critique a preclinical-to-clinical plan, pick a trial design (basket/umbrella/platform), plan multimodal data integration, or assess whether a hypothesis is ready to advance. Triggers include phrases like "validate target", "biomarker context of use", "bench to bedside", "T0/T1/T2/T3/Tawslabs/hcls-agent-skills42
- Variant CallingGermline and somatic short-variant calling pipeline for Illumina short-read data. Use when the user mentions BWA, BWA-MEM2, GATK, HaplotypeCaller, Mutect2, VCF, GVCF, VQSR, variant calling, germline, somatic, SNV, or indel calling from FASTQ/BAM.awslabs/hcls-agent-skills42
- Aws ArchitectureUse 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).awslabs/llm-evaluation-system26
- Port A BenchmarkPort an existing third-party benchmark or eval into this repo as an Inspect AI task, faithfully. Use this whenever the task is "add benchmark X", "port this eval", "can we run <github repo> here", or adapting any external eval harness (aiewf-eval, lm-evaluation-harness, a paper's repo, a colleague's script). Enforces the one rule that makes a port worth anything — copy the measuring instrument verbatim, adapt only the runner — plus the verification steps that prove the port is faithful rather thawslabs/llm-evaluation-system26
- Ship ItShip 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 (conventiawslabs/llm-evaluation-system26
- Agent AdvisorUnified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC — all in one flow. Triggers on: which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda, AgentCore vs Lambda MicroVMs, deploy an AI agent on AWS, agent architecture on AWS, I have an agent idea what do I build, move my agents to AWS, migrate my agents to AWS with a plan, agent migration plan, add AgentCore services, add memory/gatewawslabs/startups22
- Agent AdvisorUnified entry point for AI-agent work on AWS: evaluate and pick a runtime, generate a full migration plan (for existing workloads), and build an executable POC — all in one flow. Triggers on: which runtime for my agent, AgentCore vs ECS vs EKS vs Lambda, AgentCore vs Lambda MicroVMs, deploy an AI agent on AWS, agent architecture on AWS, I have an agent idea what do I build, move my agents to AWS, migrate my agents to AWS with a plan, agent migration plan, add AgentCore services, add memory/gatewawslabs/startups22
- Agentcore PatternsThis skill should be used when an automated agent's output is published under its own identity and carries weight in someone else's work, such as a reviewer whose verdict lands on a pull request, and the open question is how much authority it has actually earned. Covers which conclusions such an agent may state as settled and which it must hand to a person, why a verdict that moves between runs on unchanged input cannot be allowed to decide anything, handing an uncertain item to a human rather tawslabs/startups22
- Architect For StartupsStartup-tailored AWS architecture advice that adjusts recommendations to the company's stage (pre-revenue through Series B+), team size, runway, and available credits. Use when a founder wants guidance or a recommendation rather than code changes: which services to choose, how to plan or review an architecture, how to stretch credits and control cost, or how to prepare architecture for a fundraise or technical diligence. For an interactive discovery flow that scaffolds and writes the architecturawslabs/startups22
- Azure To AwsMigrate workloads from Microsoft Azure to AWS. Triggers on: migrate from Azure, Azure to AWS, move off Azure, migrate Azure app to AWS, migrate AKS to EKS, migrate App Service to AWS, migrate App Service to Elastic Beanstalk, migrate Azure VMs to EC2, migrate Azure SQL to RDS, migrate Azure Database for PostgreSQL to RDS, migrate Azure Database for MySQL to RDS, migrate Cosmos DB to DynamoDB, migrate Azure Cache for Redis to ElastiCache, migrate Blob Storage to S3, migrate Azure Functions to Lamawslabs/startups22
- Azure To AwsMigrate workloads from Microsoft Azure to AWS. Triggers on: migrate from Azure, Azure to AWS, move off Azure, migrate Azure app to AWS, migrate AKS to EKS, migrate App Service to AWS, migrate App Service to Elastic Beanstalk, migrate Azure VMs to EC2, migrate Azure SQL to RDS, migrate Azure Database for PostgreSQL to RDS, migrate Azure Database for MySQL to RDS, migrate Cosmos DB to DynamoDB, migrate Azure Cache for Redis to ElastiCache, migrate Blob Storage to S3, migrate Azure Functions to Lamawslabs/startups22
- Contextual Offers For StartupsSurfaces a single, genuinely relevant AWS Activate partner offer as optional context AFTER another AWS Startup Advisor skill has finalized its recommendation, plan, or build — never influencing the technical advice. Consulted by architect-for-startups, start-building-for-startups, agent-advisor, gcp-to-aws, heroku-to-aws, and llm-to-bedrock: once their output is final, this skill checks whether a relevant Activate offer exists for what the founder is building or migrating and, if so, appends oneawslabs/startups22
- Gcp To AwsMigrate 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, migrate App Engine to Elastic Beanstalk, 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, migraawslabs/startups22
- Gcp To AwsMigrate 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, migrate App Engine to Elastic Beanstalk, 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, migraawslabs/startups22
- Heroku To AwsMigrate 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 Elastic Beanstalk, migrate dynos to Fargate, Heroku migration, move from Heroku to AWS, migrate Heroku Private Space, Heroku to Elastic Beanstalk, Heroku to ECS, Heroku to Fargate, leave Heroku, migrate off Heroku platform, what-if workshop, reprice Heroku migrawslabs/startups22
- Heroku To AwsMigrate 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 Elastic Beanstalk, migrate dynos to Fargate, Heroku migration, move from Heroku to AWS, migrate Heroku Private Space, Heroku to Elastic Beanstalk, Heroku to ECS, Heroku to Fargate, leave Heroku, migrate off Heroku platform, what-if workshop, reprice Heroku migrawslabs/startups22
- Knowledge Base For StartupsAWS Startups reference content — Activate FAQ, credits guide, programs, partner offers, sample architectures, and hundreds of learn articles spanning generative AI, cloud architecture, cost optimization, security, fundraising, go-to-market, and real-world startup case studies. Use when the user asks factual questions about AWS Activate (eligibility, credits, programs, providers), wants a sample architecture or solution guide, or needs an AWS-curated learn article on a specific startup topic. Forawslabs/startups22
- Llm To BedrockUse when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. 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: agent runtime selection, agentic architecture decisions, or agent migration planning — use agent-advisor for those. Not for standalone Bedrock cost estimates or infrastructure-only migration. REQUIRES thawslabs/startups22
- Llm To BedrockUse when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. 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: agent runtime selection, agentic architecture decisions, or agent migration planning — use agent-advisor for those. Not for standalone Bedrock cost estimates or infrastructure-only migration. REQUIRES thawslabs/startups22
- Multi Tenant IsolationThis skill should be used when designing or fixing tenant isolation for a multi-tenant SaaS on AWS, where a team with no dedicated security engineer must make a cross-tenant leak structurally impossible rather than a code-review responsibility. Covers choosing a silo, pool, or bridge model per layer rather than per application, enforcing isolation in IAM session policies and the database so a forgotten predicate fails closed, partitioning data across DynamoDB, Postgres, and S3, containing noisy awslabs/startups22
- Prompt Library For StartupsAWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock Preventer, Service Quota Agent, Bedrock Model Availability Agent, AWS DB Advisor). Use when the user asks for a prompt to do X on AWS, wants an installable agent for multi-account / cost monawslabs/startups22
- Self Hosted Llm Batch InferenceThis skill should be used when a startup without a dedicated ML platform team needs recurring, latency-tolerant offline inference for a self-hosted 1B to 8B generative language model on AWS while minimizing GPU spend and recovering automatically from Spot interruption. It prescribes AWS Batch backed by Amazon ECS Managed Instances Spot, with model artifacts staged in Amazon S3, deterministic input shards, vLLM offline inference on one GPU, bounded retries, and output reconciliation before succesawslabs/startups22
- Start Building For StartupsInteractive discovery + implementation workflow that gathers requirements through picker-based questions (intent, scope, constraints, preferences), scans the codebase for what it can already infer, then writes an AWS architectural scaffold and implementation directly into the project. Use when the user wants to build a new app, scaffold a project, or expand/refactor an existing one on AWS — anything that calls for a structured discovery flow followed by code changes, not a one-off lookup. Do notawslabs/startups22
- Tf Best PracticesBest-practice authoring guidance AND a read-only policy gate for AWS Terraform generated by a migration skill. Load during any phase that writes a terraform/ directory — first as the "what to emit" posture rules + security-baseline spec, then after writing as the deterministic policy verdict. Read-only: it reports whether the generated Terraform passes; it never edits .tf files, never touches .phase-status.json, and never decides phase completion. Complements (does not replace) terraform fmt/iniawslabs/startups22
- Tf Best PracticesBest-practice authoring guidance AND a read-only policy gate for AWS Terraform generated by a migration skill. Load during any phase that writes a terraform/ directory — first as the "what to emit" posture rules + security-baseline spec, then after writing as the deterministic policy verdict. Read-only: it reports whether the generated Terraform passes; it never edits .tf files, never touches .phase-status.json, and never decides phase completion. Complements (does not replace) terraform fmt/iniawslabs/startups22
- Compare NakbCompare saved NKIGym latencies with frozen NAKB baselines and export PDF comparison figures. Use for NAKB performance summaries, latency comparisons, and refreshing figures from recorded measurements in this repository.awslabs/nki-autotune20
- Develop NkigymStart or continue a persistent goal to debug and improve the NKIGym backend until all tests pass, prioritizing workload configurations with the worst NKIGym/NAKB latency ratios, modifying nkigym/src/nkigym and recording or updating best NKIGym ladders in kernel_library.awslabs/nki-autotune20
- Inference ValuesAuthor a values-<model>.yaml file for the inference-charts Helm chart. Use when adding a new model (vLLM, Ray-vLLM, LeaderWorkerSet, Triton, AIBrix, NIM, or Neuron) to this repository, including modelParameters conventions, framework selection, GPU sizing, and validation steps.awslabs/ai-on-eks-charts15
- Codeknit FingerprintDetects duplicate and near-duplicate code across a codebase using fuzzy hashing with codeknit. Use when finding copy-paste, refactoring candidates, merging similar implementations, auditing for DRY violations, or locating semantically equivalent code across different files or languages. Supports C, C++, C#, Go, Java, JavaScript, PHP, Python, Ruby, Rust, Scala, and TypeScript.awslabs/codeknit8
- Codeknit ParseExtracts code structure (functions, classes, methods, variables) and relationships (calls, inheritance, containment) from source files into compact .skt or JSON output using codeknit. Use when analyzing a codebase, understanding code structure, mapping dependencies, or preparing context for code review and refactoring. Supports C, C++, C#, Go, Java, JavaScript, PHP, Python, Ruby, Rust, Scala, and TypeScript.awslabs/codeknit8
- Aidlc Emit IssuesEmit AIDLC inception artifacts as GitHub issues: one EPIC per intent, one child per AIDLC unit, natively sub-issue-linked, each in the repo's mandatory plain-terms opening and five technical sections with deterministic acceptance. Delivery loop generation is a two-stage protocol: Step 7 composes loop drafts as branch artifacts (invoked in Run A after delivery-planning approval); Step 8 materializes the issues from approved drafts (invoked in Run B after loop-proposal approval). Orchestrators, evawslabs/agentic-developer-platform6
- Codex BridgeDelegate a single bounded coding or code-review task to the OpenAI Codex CLI (runs against Bedrock), then review Codex's output yourself before committing. ONLY use this skill when the triggering issue or comment EXPLICITLY names Codex — e.g. "use Codex", "ask Codex to review this", "pass this to Codex", "have Codex write X". Never invoke it autonomously, speculatively, or because a task merely looks like something Codex could do. If nobody asked for Codex, do the work yourself and do not run thawslabs/agentic-developer-platform6
- Eval JudgeLLM 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.awslabs/agent-builder-toolkit-aws-transform6
- ImplementIssue-to-code workflow that takes a GitHub issue, plans the implementation, writes contract-based tests and production code via TDD, and runs unit tests to validate. Code changes are left uncommitted for user review. Use when implementing GitHub issues. Activated by commands: /ingest, /plan, /revise, /code, /validate, /respond.awslabs/operator-for-ai-chips-on-aws6
- ImplementIssue-to-code workflow that takes a GitHub issue, plans the implementation, writes contract-based tests and production code via TDD, and runs unit tests to validate. Code changes are left uncommitted for user review. Use when implementing GitHub issues. Activated by commands: /ingest, /plan, /revise, /code, /validate, /respond.awslabs/operator-for-ai-chips-on-aws6
- Scenario RunnerSimulated 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.awslabs/agent-builder-toolkit-aws-transform6
- SkypilotUse for issue-driven GPU capacity requests: express workload requirements, let SkyPilot select and provision machines, and prepare those machines for Superplane EKS workloads through the hybrid networking and node-join path.awslabs/agentic-developer-platform6
- Stage 1 TriageLightweight fingerprinting of a malware sample — hashes, file type, entropy, strings, candidate IOCs. Use this skill whenever you start a 7-stage malware analysis pipeline, need a quick file identification before deeper analysis, or want to check a sample against known-hash databases before committing compute. This is always the first stage and must run before Stage 2 (OSINT), Stage 3 (static), or Stage 4 (dynamic).awslabs/agentic-developer-platform6
- Stage 2 OsintConsult OSINT sources and synthesize a prior hypothesis that steers downstream analysis. M1 scope is MalwareBazaar (no auth, no vault dependency) + web search + MITRE ATT&CK; VirusTotal + Shodan + urlscan are commented out in the skill until vault credentials are provisioned. Use this skill whenever you have a sample's hashes + candidate IOCs (from Stage 1 triage) and want to check reputation, find prior reporting, or decide whether deeper analysis is worth the compute. Always run after Stage 1 awslabs/agentic-developer-platform6
- Stage 5 CorrelationCross-reference dynamic findings against threat intel (MISP, VT, web reporting) + MITRE ATT&CK to derive family + TTPs + campaign linkage. Use this skill whenever you have Stage 4 dynamic observations (C2 IPs, mutexes, injection targets) and want to link them to known campaigns, confirm Stage 2's hypothesis, or produce MITRE TTP IDs with specific per-stage evidence. Runs after Stage 4, or after Stage 3 if Stage 4 was unavailable — can work with partial data. Skip on Stage 2 short-circuit.awslabs/agentic-developer-platform6
- Stage 6 VerdictSynthesize severity (malicious/suspicious/benign), confidence (high/medium/low), STIX 2.1 IOC bundle, CSV feed, and concrete recommended actions (host isolation, token revocation, perimeter blocks, fleet-wide hunt queries) from all prior stage envelopes. Use this skill whenever earlier stages have produced findings (or on a Stage 2 short-circuit to benign) and you need a machine-readable verdict that IR teams can ingest into Splunk/Elastic/Sentinel or block at the perimeter. Always runs — even sawslabs/agentic-developer-platform6
- Stage 7 ReportProduce the final deliverables — executive summary (for leadership), structured technical report (for IR), STIX 2.1 + CSV IOC feeds (for SIEM/firewall), copy-pasteable Splunk/Elastic/Sentinel hunt queries — upload them all to S3 with presigned URLs, and post a single consolidated comment linking everything. Use this skill whenever the pipeline has reached a verdict (Stage 6 done) and the issue needs a handoff-ready set of artifacts for IR follow-up. Always the last stage; runs on benign short-ciawslabs/agentic-developer-platform6
- SuperplaneUse to inspect Superplane workspaces, provider readiness, workload operations and costs through the maintained ADP CLI. For GPU machine selection and the issue-driven SkyPilot-to-EKS workflow, use the sibling skypilot skill.awslabs/agentic-developer-platform6
- Url AnalysisInvestigate URLs using Common Crawl, live AgentCore browsing and sourced intelligence; produce an actionable analyst assessment.awslabs/agentic-developer-platform6
- Url AnalysisInvestigate submitted URLs with Task-authorized Common Crawl and isolated browser tools, and report evidence and coverage limitations.awslabs/agentic-developer-platform6
- FlinkComprehensive guidance for developing, optimizing, and operating Apache Flink applications on Amazon Managed Service for Apache Flink. Use when working with Apache Flink, Managed Service for Apache Flink, streaming, stream-processing, real-time data, Kafka, or Kinesis.awslabs/managed-service-for-apache-flink-agent-steering-files3
- Bedrock Readiness CliAssess whether an AWS account's Amazon Bedrock deployment is operationally ready for production, by running the bedrock-readiness CLI directly. Use when a builder asks about Bedrock/AgentCore production readiness, quota headroom, guardrails, security posture, data governance, or wants an architecture diagram reviewed before infrastructure exists. No MCP server required; runs in the agent's own shell environment.awslabs/support-solutions-aws2
- Bedrock Readiness McpAssess whether an AWS account's Amazon Bedrock deployment is operationally ready for production, by calling the bedrock-readiness MCP server. Use when a builder asks about Bedrock/AgentCore production readiness, quota headroom, guardrails, security posture, data governance, or wants an architecture diagram reviewed before infrastructure exists. Requires the bedrock-readiness MCP server to be configured and reachable.awslabs/support-solutions-aws2
- Update Debug PricingDebug discrepancies in resolved model pricing data; Refresh local integration test snapshots or price API data dumps; audit model pricing additions/removals and existing-price changes; diagnose unresolved model IDs; implement source-grounded price mapper or classifier fixes.awslabs/model-info-amazon-bedrock1
- Ai AdrKeep a project's architecture decision log — stand it up on first run, then write records and move them through propose, accept, and decline. Invoke ONLY via the /ai-adr slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.awslabs/sample-ai-skills
- Ai Agent ContextWrite agent context documentation (CLAUDE.md + README.md) for a source code directory. Invoke ONLY via the /ai-agent-context slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.awslabs/sample-ai-skills
- Ai ArchiveRetire one finished work folder by moving it into the working root's .archive/ directory and transferring its manifest row. Invoke ONLY via the /ai-archive slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.awslabs/sample-ai-skills
- Ai CreateCreate a new working folder with a README.md identity document for a feature or a document. Invoke ONLY via the /ai-create slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.awslabs/sample-ai-skills
- Ai Human DocxExport one markdown file to Microsoft Word (.docx), optionally styled by a .dotx template. Invoke ONLY via the /ai-human-docx slash command. Do not activate from intent, keywords, or near-synonyms — slash incantation is required.awslabs/sample-ai-skills