DevOps & Infra

fabioc-aloha Skill

Azure OpenAI API patterns for rate limiting, function calling, error handling, and token optimization

fabioc-aloha Skill

Microsoft Foundry agent deployment, orchestration, and cloud-native AI service patterns

fabioc-aloha Skill

**Domain**: DevOps & Cloud Engineering

fabioc-aloha Skill

CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads

fabioc-aloha Skill

Data pipeline quality assurance — anomaly detection, schema drift, null ratio monitoring, freshness checks, and safe-write protection for reliable data engineering

fabioc-aloha Skill

Seamless notebook publishing from VS Code to Microsoft Fabric via Azure DevOps Git integration

fabioc-aloha Skill

Design well-architected Azure cloud systems — 10 design principles, 6 architecture styles, 44 design patterns, technology choices, WAF pillars

fabioc-aloha Skill

Well-Architected Framework principles and Azure best practices

fabioc-aloha Skill

Production deployment patterns for Azure Static Web Apps, Container Apps, App Service, and infrastructure

fabioc-aloha Skill

Azure Content Safety API integration, multi-layer defense pipeline, output validation, and operational safety controls

synthetic-sciences Bundle

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

synthetic-sciences Bundle

Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.

synthetic-sciences Skill

Chooses and runs compute for research work, local shell or kernel versus a detached compute_job on this machine, a saved SSH or Slurm host, or Modal GPUs, with the target discovered from what is actually configured, the run sized and priced before dispatch, outputs declared, metrics tracked, and long work handed to the job system instead of a blocking shell. Use when a task needs a GPU, will run longer than a few minutes, must survive the session, or asks which cloud or provider to use. Provider-specific setup lives in the cloud-compute library skills; load one only after compute_job targets shows that provider.

synthetic-sciences Bundle

Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. Use whenever the user mentions Nextflow, nf-core, .nf files, nextflow.config, DSL2, processes/channels/operators, samplesheets, or wants to run a community pipeline (e.g. nf-core/rnaseq, nf-core/sarek), write or test a module/subworkflow with nf-test, configure executors/containers (Docker, Singularity/Apptainer, Conda, Wave), scale a workflow to HPC/SLURM or cloud (AWS Batch, Google Batch, Azure, Kubernetes), or debug a failed/-resume run. Make sure to use this skill for any reproducible scientific/bioinformatics workflow work even if the user does not say the word "Nextflow", and for authoring nf-core-compliant pipelines, modules, configs, and linting.

synthetic-sciences Bundle

Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio/api or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization.

synthetic-sciences Bundle

Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when the user needs to validate run inputs, generate pacsomatic-compliant samplesheets, prepare reproducible Nextflow launch artifacts, run locally or submit to schedulers (LSF/Slurm/PBS/SGE), and triage execution failures. Triggers on requests to run pacsomatic, prepare launch commands/scripts, perform dry-run checks, or troubleshoot pipeline startup and scheduler submission errors.

synthetic-sciences Bundle

High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.

synthetic-sciences Bundle

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

synthetic-sciences Skill

Run approved CPU or GPU work through OpenScience compute_job on the user's configured Modal account. Use for isolated scientific scripts, dependency provisioning, durable outputs, logs, status, cancellation, and recovery. Never invoke the Modal SDK or CLI directly.

synthetic-sciences Skill

Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions.

synthetic-sciences Bundle

Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO/PPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.

synthetic-sciences Skill

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

synthetic-sciences Bundle

Read or search the user's local Zotero reference library when explicitly requested. Uses Zotero's local HTTP API; no cloud sync, library writes, or automatic indexing.

synthetic-sciences Skill

Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.

synthetic-sciences Bundle

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

synthetic-sciences Skill

Runs computations so they finish, reproduce and fit the machine that will re-execute them, detaching long jobs through compute_job instead of blocking or sleeping shells, checkpointing so reruns resume, fixing seeds and capping BLAS and OpenMP threads, streaming large tables with explicit dtypes, writing outputs atomically, logging every command with its exit code and rerunning the final pipeline from scratch under the target limits before finishing. Use for any analysis or pipeline that runs longer than a minute, reads files larger than memory, or will be re-executed on a machine with tighter CPU, memory, wall-clock or network limits than this one; a one-off shell command whose output is read immediately does not need it.

ryan-brosas Bundle

Use when building or porting cognee-style knowledge-pipeline memory engines — dataset-scale task-run engines with rollback, deterministic DataPoint identity, exact-reconstruction chunkers, ontology-canonicalized graph construction, provenance-folded writes, vector-to-graph triplet ranking, hybrid RRF retrieval lanes, and additive contradiction handling. Source code and direct tests are ground truth; references carry decisive excerpts and graph retrieval.

ryan-brosas Bundle

Use when porting crewAI's Flow runtime kernel — event-driven method graph execution, HITL pause/resume, checkpoint lineage, and the pluggable-infra patterns they share.

ryan-brosas Bundle

Use when porting Django's WSGI/ASGI handler pipeline, sync/async middleware chain, URL resolver/reverse engine, or request/response primitives — capsule-v2 source maps with decisive excerpts and graph retrieval.

ryan-brosas Bundle

Use when porting multi-engine push/notification fan-out, Azure Notification Hubs registration pools, tag-based targeting/exclusion grammars, installation-relay protocols for self-hosted instances, feature-flagged per-user vault-sync fan-out, or the real-time consumer side: SignalR hub group grammars and connect lifecycles, queue-consumer poll/poison loops, internal send ingress, wire-format contract tables across rolling deploys, and pre-auth token-as-group waiting rooms. Source code and direct tests are ground truth; references carry decisive excerpts and graph retrieval.

ryan-brosas Bundle

Use when porting anthropics/skills contracts — progressive disclosure, trigger-description authoring, validation gate + packager exclusions + multiline parsing, eval-driven description optimizer + trigger matrix report + seven-file JSON schema plane, skill eval harness + judge pipeline + review viewer, MCP eval harness + response truncation/paging contract, OOXML unpack/edit/rezip internals, docx run-merge + redline + comment anchoring + tracked-changes acceptance + redlining validator, pptx corruption ladder + chart/slide validators + slide registration + thumbnail grids + clean GC, xlsx recalc gate + formula portability, office toolkit triplication + XSD baseline-diff gate + mc:Ignorable preprocess + validator CLI family routing + pptx order-repair hook + docx ID constraint/repair, PDF form-fill fork + coordinate systems + bbox gate + structure extraction + tool ladder + validation overlay, render-verify loop, black-box script discipline, soffice AF_UNIX shim, artifact scaffold+bundle, webapp-test server…

ryan-brosas Bundle

Use when porting Strapi's DB-agnostic database kernel — knex-compiling query-builder state machine, lifecycle-hooked write pipeline with compensating rollback, per-subscriber hook-state threading, bounded identifier shortening, N+1-free batch populate, connect-order topological sorting, anyToOne relinking with document-sibling exclusion, hash-gated schema sync with 3-way DDL diffing, constraint-safe alter ladders, exactly-once migration runner, dual-stream user/internal migration providers, row-number deep-sort wrapping with virtual status ranking sort, three-pass metadata loading with preset-name skip, morphOne reverse-link cascade deletes, fixed-order streaming transfer stages with skip/cancel/rollback, stream-replacing progress trackers with pre-start totals, index-difference flow state machines over WebSocket step protocols, uuid dedup-replay idempotent dispatch, and init-echo binary wire negotiation.

ryan-brosas Bundle

Use when a practices leaf or question points at a specific awesome-guidelines style capsule or learning note - archived cold library; the ingestion pipeline is retired, so load only to read a cited capsule.

ryan-brosas Bundle

Use when porting a self-hosted deploy orchestrator (Coolify, PaaS-style) — a DB-backed deployment queue with admission control, a 5k-line build-pack state machine that drives remote Docker hosts over SSH, rolling updates with health-gated cutover, and cron-dedup scheduled jobs. Source code and direct tests are ground truth; references carry decisive excerpts and graph retrieval.

ryan-brosas Bundle

Use when porting agent-loop, event-stream, provider-retry, context-compaction, branch-summarization, tool-batch-execution, auto-compaction wiring, Anthropic wire-compat/message normalization, session-storage backends, extension tool-wrapping, Vertex AI auth/ADC ladders, Azure OpenAI Responses twin deltas, Codex WebSocket resume transports, provider OAuth refresh contracts, or cross-model message-history preshaping from badlogic/pi-mono — capsule-v2 source maps with decisive excerpts and graph retrieval.

ryan-brosas Bundle

Use when porting ragflow's RAG retrieval engine — hybrid search orchestration, citation attach, ingestion task kernel, resumable GraphRAG indexing pipeline, query-side KG retrieval with Go twin.