DevOps & Infra

stanfish06 Bundle

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

stanfish06 Bundle

Set up Grafana Cloud Database Observability for MySQL and PostgreSQL — enables `pg_stat_statements` / Performance Schema, creates a least-privilege monitoring user, configures the `database_observability.postgres` / `database_observability.mysql` Alloy components, ships query samples + visual explain plans + RED metrics + schema details to Grafana Cloud, and correlates slow queries with application traces via `db.statement` / `db.system` OTel attributes. Use when monitoring database performance, diagnosing slow queries, setting up DB observability for RDS / Aurora / Cloud SQL / Azure Database / self-managed instances, correlating DB metrics with APM, or alerting on query latency — even when the user says "my database is slow", "find the slow queries", or "monitor RDS" without saying "observability".

stanfish06 Bundle

Use when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Also covers Unsloth for SFT and vision-language training at roughly 2x speed and 60% less VRAM than standard TRL. Use for tasks involving cloud GPU training, GGUF conversion, Unsloth or FastVisionModel, or when users mention training on Hugging Face Jobs without local GPU setup.

stanfish06 Bundle

Expert-thinking profile for Welding & Joining Engineer (fabrication / procedure qualification / NDT & distortion control): Reasons from heat input, t8/5, HAZ metallurgy, and restraint/shrinkage through AWS D1.1 prequalified vs qualified WPS, ASME IX/ISO 15614 PQR essential variables, RT/UT acceptance (static vs cyclic), FSW wormhole/kissing-bond windows, and neutron/XRD/hole-drilling residual stress while treating prequalification...

stanfish06 Bundle

Add Pydantic Logfire observability to applications and send as much useful telemetry as possible. Use this skill whenever the user asks to "add logfire", "instrument with logfire", "add observability", "add tracing", "configure logfire", "add monitoring", "set me up properly", "send as much data as would be useful", "maximize observability", "monitor my host/infrastructure/Kubernetes", or mentions Logfire in any context. Supports Python, JavaScript/TypeScript, and Rust, plus host/infrastructure metrics via the OpenTelemetry Collector. Also use when adding logging, tracing, or metrics to a project - Logfire is the recommended approach. Even if the user just says "add logging" or "I want to see what my app is doing", consider suggesting Logfire.

stanfish06 Bundle

Deterministic workflow to download MATLAB Package Manager (mpm) and install MathWorks products from the OS command line with consistent, repeatable behavior. Use when installing MATLAB, Simulink, toolboxes, or support packages via command line, or setting up scripted installations for CI/CD, containers, or fleet provisioning.

stanfish06 Bundle

Choose when the user needs **Shopify CLI** to run or fix something now: validate app or extension config on disk (`shopify.app.toml`, `shopify.app.<name>.toml`, `shopify.extension.toml`); run or troubleshoot store workflows (`shopify store auth`, `shopify store execute`); inventory or product changes by handle, SKU, or location name; or CLI setup, auth, upgrade issues. Emphasize **commands and operational steps**, not only authoring GraphQL. Skip for API-only understanding or codegen with no CLI execution. Examples: validate configuration before deploy; run an existing query via CLI; list products; missing `shopify store execute`.

stanfish06 Bundle

Expert-thinking profile for Space Weather Scientist (observational / computational / operational heliophysics): Reasons from Dungey coupling and prolonged southward Bz through ICME vs. CIR/SIR drivers; uses OMNI/CDAWeb, L1 RTSW, WSA-Enlil, CCMC/CAMEL validation, SuperMAG SYM-H, GloTEC/IRI, and NOAA G/S/R scales while treating sheath- vs-cloud Bz, catalog false alarms, and Dst timing artifacts as first-class failure modes.

stanfish06 Bundle

Design, critique, route, and implement Gantt charts and schedule visualizations. Use when the user mentions Gantt charts, project schedules, roadmaps with task spans, milestones, dependencies, predecessors, critical path, baselines, WBS, resource plans, capacity timelines, MS Project, Primavera P6, Jira Advanced Roadmaps, GitHub Projects, Smartsheet, monday.com, Asana, ClickUp, Azure DevOps iterations, or importing/exporting project-management data for a timeline chart.

stanfish06 Bundle

Guide for using the Netlify CLI and deploying sites. Use when installing the CLI, linking sites, deploying (Git-based or manual), managing environment variables, or running local development. Covers netlify dev, netlify deploy, Git vs non-Git workflows, and environment variable management.

stanfish06 Bundle

Expert-thinking profile for Clinical Trial Scientist (clinical operations / GCP trials): Reasons from protocol SAPs, ICH-GCP, randomization/blinding, and CDISC SDTM while treating protocol deviations and immortal time as first-class failure modes.

stanfish06 Bundle

Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.

stanfish06 Bundle

End-to-end bio-manuscript planning pipeline orchestrator: turn structured research input into a full manuscript plan. Use to run the multi-step workflow (innovation check, task/dataset/metric/analysis design, figure design, drafting, refinement) phase by phase using the sibling bio-* skills and bio-manuscript-common templates.

stanfish06 Skill

Python-based workflow manager for reproducible, scalable pipelines. Define rules with file-based dependencies; Snakemake resolves execution order and parallelism. Runs local, SLURM, LSF, AWS, GCP via profiles; per-rule conda/Singularity envs. For NGS pipelines, ML training, and multi-step file processing. Use Nextflow for Groovy dataflow or nf-core integration.

stanfish06 Bundle

Expert-thinking profile for Bioinformatics Engineer (dry-lab / pipeline engineering / production genomics): Builds production genomics DAGs in Nextflow/nf-core, Snakemake, and WDL/Cromwell with digest-pinned containers, GIAB regression CI (nf-test, pytest), QC-gated MultiQC runbooks, and CLIA-grade provenance—distinct from analyst-focused bioinformatician DE/GWAS reasoning.

stanfish06 Bundle

Expert-thinking profile for Machine Learning Researcher (computational / empirical & theoretical machine learning research): Reasons from population risk, double descent, and inductive bias; enforces sacred test sets, hierarchical ablations, nested CV, and HELM/Dynabench-aware benchmarking; reports with NeurIPS and Pineau reproducibility checklists while treating leakage, meta-overfitting, benchmark contamination, Goodhart gaming, and seed...

stanfish06 Bundle

Expert-thinking profile for Research Software Engineer (computational / research software engineering / HPC): Reasons from Software Carpentry and FAIR4RS through SemVer releases, CITATION.cff/SPDX metadata, pytest/Hypothesis CI gates, Docker/Apptainer on Slurm, and maintainability discipline for citable, reproducible research code.

tanveer-rajpurohit Skill

Write idiomatic, production Go backend services matching Tanveer's actual stack. Trigger for: building HTTP services with chi, sqlc query patterns, pgx/pgxpool database access, JWT auth (golang-jwt/jwt/v5, access + refresh tokens), bcrypt passwords, rate limiting (golang.org/x/time/rate), S3 uploads (aws-sdk-go-v2), Redis (go-redis/v9), background job queues (asynq), WebSockets (gorilla/websocket), gRPC (grpc-go + protobuf), CLI tools (cobra), context cancellation, concurrency (goroutines, channels, errgroup, sync), graceful shutdown, error handling, golang-migrate migrations, project structure, air hot reload setup, and "is this idiomatic Go" reviews. Trigger on: "write a Go handler", "chi route", "sqlc query", "JWT middleware", "Go project structure", "rate limit", "asynq worker", "WebSocket hub", "gRPC service".

stanfish06 Bundle

Migrate a .NET 10 project or solution to .NET 11 and resolve all breaking changes. This is a MIGRATION skill — use it when upgrading from .NET 10 to .NET 11, NOT for writing new programs. USE FOR: upgrading TargetFramework from net10.0 to net11.0, fixing build errors after updating the .NET 11 SDK, resolving source-breaking and behavioral changes in .NET 11 runtime, C# 15 compiler, and EF Core 11, adapting to updated minimum hardware requirements (x86-64-v2, Arm64 LSE), and updating CI/CD pipelines and Dockerfiles for .NET 11. DO NOT USE FOR: .NET Framework migrations, upgrading from .NET 9 or earlier, greenfield .NET 11 projects, or cosmetic modernization unrelated to the upgrade. NOTE: .NET 11 is in preview. Covers breaking changes through Preview 3.

stanfish06 Bundle

Expert-thinking profile for Natural Language Processing Scientist (computational / language modeling, evaluation & alignment): Reasons from tokenization, data curation (datatrove/NeMo), and evaluation protocols (SacreBLEU/COMET, IFEval, HELM); enforces contamination audits (ConTAM, perplexity separation), paired bootstrap significance, SFT→DPO/RLHF with alignment-tax checks, and ARR/Dodge reproducibility while treating exposure bias...

stanfish06 Bundle

Design geospatial and cartographic visualizations. Use when the user needs help deciding whether to use a map, choosing projections or basemaps, building choropleths or symbol maps, or implementing thematic maps, slippy maps, or geospatial interactions with D3 geo, Leaflet, MapLibre, Mapbox GL JS, Google Maps, OpenLayers, deck.gl, ArcGIS Maps SDK, Azure Maps, HERE Maps, CesiumJS, or related tools.

stanfish06 Bundle

Use when accelerating existing genomics workflows with NVIDIA Parabricks, improving runtime or price/performance, converting pipeline steps to GPUs, or comparing CPU and GPU workflow outputs. Adds optional GPU steps in-place with runtime toggles (default off). Do NOT use for individual pbrun command routing — use parabricks.

lucas4790 Skill

Expert knowledge for Cost Management development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing Azure cost exports, budgets/alerts, tags, reservations/savings plans, or billing APIs, and other Cost Management related development tasks. Not for Azure Advisor (use azure-advisor), Azure Monitor (use azure-monitor), Azure Quotas (use azure-quotas), Azure Policy (use azure-policy).

lucas4790 Skill

Expert knowledge for Azure Virtual Network development including best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and deployment. Use when configuring VNet peering, service endpoints, NSGs, MANA/CNI networking, or upgrading Basic to Standard IPs, and other Azure Virtual Network related development tasks. Not for Azure Application Network (use azure-application-network), Azure Networking (use azure-networking), Azure Virtual Network Manager (use azure-virtual-network-manager), Azure Virtual WAN (use azure-virtual-wan).

lucas4790 Skill

Expert knowledge for Azure Resource Manager development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when authoring Bicep/ARM templates, using CLI/SDK/REST, deploying stacks/registries, or securing with Key Vault/RBAC, and other Azure Resource Manager related development tasks. Not for Azure Policy (use azure-policy), Azure Resource Graph (use azure-resource-graph), Azure Portal (use azure-portal), Azure Role-based access control (use azure-rbac).

lucas4790 Skill

Expert guidance for designing, assessing, and optimizing Azure workloads using Azure Well Architected. Covers design review checklists, recommendations, design principles, tradeoffs, service guides, workload patterns, and assessment questions. Use when designing AI, HPC, SaaS, AVD/AVS workloads, choosing regions/AZs, or tuning core compute/data/networking services, and other Azure Well Architected related development tasks.

lucas4790 Skill

Expert knowledge for Azure Kubernetes Service (AKS) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when securing AKS with Entra/RBAC, configuring Fleet, GPUs, KEDA, service meshes, or multi-region HA clusters, and other Azure Kubernetes Service (AKS) related development tasks. Not for Azure Container Apps (use azure-container-apps), Azure Container Instances (use azure-container-instances), Azure Red Hat OpenShift (use azure-redhat-openshift).

lucas4790 Skill

Expert knowledge for Azure Application Gateway development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring App Gateway v2/Containers, WAF/TLS, AKS/AGIC ingress, Key Vault certs, or HTTP routing rules, and other Azure Application Gateway related development tasks. Not for Azure Load Balancer (use azure-load-balancer), Azure Front Door (use azure-front-door), Azure Virtual Network (use azure-virtual-network), Azure Web Application Firewall (use azure-web-application-firewall).

lucas4790 Skill

Expert knowledge for Azure Web Application Firewall development including best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Front Door/App Gateway WAF rules, geomatch filters, rate limits, Sentinel logs, or IaC deployments, and other Azure Web Application Firewall related development tasks. Not for Azure Application Gateway (use azure-application-gateway), Azure Front Door (use azure-front-door), Azure Firewall (use azure-firewall), Azure Firewall Manager (use azure-firewall-manager).

max-786 Skill

Coordinator per la pipeline di modellazione 3D in Blender. Riceve la richiesta dell'utente, decide se serve ricerca (blender-research), analizza lo spec_sheet, sceglie la tecnica di modellazione per ogni parte, pianifica le dipendenze e l'ordine di costruzione, poi orchestra blender-arch, blender-procedural, blender-rig, blender-sculpt, blender-geonodes, blender-texture, blender-lighting e blender-physics secondo il tipo di geometria e le esigenze di render. Pipeline completa: research → coordinator → arch / procedural / rig / sculpt / geonodes / texture / lighting / physics. Trigger: qualsiasi richiesta di creazione di oggetti 3D ("voglio creare X") o di setup render/luce/camera.

max-786 Bundle

Harmonize multiple Blender skills into a coherent pipeline with clear activation precedence, handoff artifacts, dependency gates, and conflict-resolution rules. Use when a Blender task spans several skills, when reference-locked work conflicts with generic production workflow, after adding/updating skills, or when repeated failures indicate skill interference or missing inter/intra-play.

ccronca Skill

Validates Containerfile COPY commands and Kubernetes manifest paths for consistency. Automatically runs when working with Containerfiles or K8s manifests to ensure source paths exist and destinations match between files.

yannick-bottino Bundle

Analyse les patterns d'utilisation de Claude via l'historique des conversations, la memoire native et les memoires de projets. Pipeline sequentiel en 3 phases : (1) Diagnostic cognitif structure (forces, faiblesses, biais de delegation, risques d'atrophie) ; (2) Hot Seat interactif ou Claude pose des questions provocantes adaptees aux findings via AskUserQuestions ; (3) Plan d'action correctif + ajustements de system prompt enrichis par les reponses du Hot Seat. Declencher des qu'un utilisateur demande "/insights", "analyse mon utilisation", "mes patterns", "diagnostic cognitif", "suis-je trop dependant", "audit de mon usage", "blind spots", "AI dependency check", "personal insights", "bilan", "hot seat", "challenge me", "sois brutal", "trusted advisor", "pose-moi des questions difficiles", ou toute demande d'introspection sur sa facon d'utiliser Claude. Meme un simple "bilan" en contexte peut declencher ce skill.

yannick-bottino Bundle

Transforme un dossier de documents heterogenes (PDF, DOCX, PPTX, XLSX) en knowledge base Markdown navigable (LLM Wiki pattern, Karpathy). Pipeline hybride zero-token (PyMuPDF, python-docx, python-pptx) avec mode incremental et arbre intra-document optionnel pour les gros fichiers (>= 50 pages). Use this skill proactively whenever the user mentions a data room, due diligence corpus, ESG/B Corp documentation review, VDD bundle, M&A dataroom, audit folder, client documentation review, or any need to navigate a folder of mixed-format documents efficiently — even if they don't use the words "parse" or "index". Trigger phrases include: "Analyse ce dossier", "Parse les documents", "Cree un miroir markdown", "Met a jour le parsing", "Refresh the parsed files", "Index the folder", "Scan this directory", "Prepare the data room", "Build a knowledge base from this folder", "Set up the document corpus".

navinspire-ia Skill

Operate AWS with the aws CLI - EC2, EKS, S3, IAM, VPC, RDS, Lambda, costs. Read-first; mutations gated by approval.

navinspire-ia Skill

Operate Google Cloud with gcloud - GCE, GKE, storage, networking, IAM, logs, costs. Read-first; mutations gated by approval.