Loading...
Loading...
Found 1,660 Skills
Guides end-to-end lifecycle governance for mission-critical, high-assurance, or zero-failure- tolerance systems—concept through retirement: phases, gates, evidence, traceability, obsolescence, tech refresh, configuration baselines, NDA-safe regulated/classified patterns, assurance/DevSecOps/ ATO interfaces, decommissioning and data disposition. Use for extreme lifecycle, system lifecycle, mission-critical lifecycle, lifecycle gates, sustainment, tech refresh, obsolescence management, decommissioning, configuration baseline, lifecycle evidence, end-to-end lifecycle, or retire a system—not TPM-only (technical-program-manager), HRO-only (zero-tolerance-for-failure), tiering-only (mission-critical), classified pipeline-only (classified-software-devsecops-engineer), formal proofs (software-assurance-formal-methods-specialist), compliance-only (compliance-engineer), CI-only (build-validator), infra portfolio-only (vp-of-infrastructure).
Guides Site Reliability Engineering—SLI/SLO and error budgets, reliability dashboards and burn-rate alerting, production readiness reviews, capacity planning for availability, toil reduction, dependency and failure-mode analysis, release reliability (canaries, rollback criteria), and service-owner incident mitigation tied to customer impact. Use when defining or operating SLOs, measuring error budget burn, improving service reliability, running PRRs before launch, planning scalable resilient capacity, or leading technical mitigation during outages—not for CI/CD pipeline implementation (devops), incident program and paging policy design (incident-management-engineer), cloud access and patch tickets (cloud-system-administrator), load-test profiling (performance-engineer), rollout cutover strategy (deployment-strategist), or greenfield cloud build-out (cloud-engineer).
Guides cleaning and standardizing tabular datasets before analysis, modeling, or reporting—profiling, quality rules, missing values, duplicates, outliers, type coercion, encoding fixes, record linkage, deduplication, high-level PII handling (not legal advice), actuarial/insurance field scrubbing, reproducible scrub pipelines, validation checks, and sign-off. Distinct from warehouse ETL or statistical modeling. Use when the user asks for "data scrubbing", "clean this dataset", "scrub the data", "data cleaning", "dedupe records", "handle missing values", "outlier treatment", "standardize columns", "data quality rules", "profile this table", or "prepare data for modeling". Not warehouse pipelines (data-warehouse-engineer), ML modeling (data-scientist, actuary), privacy programs (compliance-engineer), FinOps only (finops-analyst), or assumption governance (assumption-setting).
Guides secure software delivery and DevSecOps for cleared/classified or high-side programs—disconnected or air-gapped CI/CD, artifact promotion across classification boundaries (conceptual), SBOM/signing/ provenance, SAST/DAST/secrets/IaC/container gates, supply-chain controls, STIG/CIS deploy baselines, IaC for classified landing zones, cleared developer workstations, build/deploy audit logging, and ATO/RMF pipeline evidence (not SSP ownership). Use for classified DevSecOps, cleared pipeline, high-side CI/CD, air-gapped build, cross-domain release, classified software delivery, STIG pipeline, ATO evidence CI, SBOM classified, secure software factory—not portfolio cyber governance (classified-cyber-security-senior-manager), ISSO/SSP (information-systems-security-officer-classified-specialist), commercial-only DevSecOps (devsecops), general DevOps (devops), build-only validation (build-validator), pentest (penetration-tester), or enterprise GRC-only (compliance-specialist).
Create alerts, notifications, and automated actions on Fabric data and events via Fabric REST API and `az rest` CLI. Use when the user wants to: (1) create, update, or delete an alert or notification flow, (2) send a Teams message, send an email, or run a Fabric item when something happens, (3) connect alert logic to Eventhouse, Eventstream, Real-time Hub, or Digital Twin Builder / Ontology data, (4) adjust thresholds, filters, event triggers, or actions, (5) troubleshoot or change an existing Activator/Reflex definition. Triggers: "create an alert", "notify me when", "let me know when", "take action when", "send me an email when", "send a teams message when", "run a pipeline when", "update an alert", "delete an alert", "activator rule"
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.
Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework integration.
Set up end-to-end Change Data Capture (CDC) pipelines on Confluent Cloud using Debezium source connectors, Flink for transformation, and Tableflow for data lake integration. Supports JSON_SR, Avro, and Protobuf formats. Handles schemaless topics (plain JSON without SR) and multi-event topics. This skill handles the complete workflow from database to Iceberg/Delta tables. Use this skill when users want to capture database changes and materialize them into Iceberg or Delta Lake tables via Confluent Cloud Tableflow. Trigger phrases include "CDC to Tableflow", "database to Iceberg", "database to Delta Lake", "stream database changes to data lake", "set up Tableflow pipeline", "schemaless topic to Tableflow", or "multi-event topic to Iceberg". Do NOT trigger for general CDC, Debezium, or database replication requests that do not involve Tableflow or Iceberg/Delta Lake as the destination.
Build Docker images for Python services following team conventions. Use this skill when writing Dockerfiles, authoring CI image build pipelines, or adding a new service — covers mitodl image naming, git short-ref tags, relocatable uv venvs, and shared library handling.
Thin orchestrator for the end-to-end video localization pipeline. Routes to the four focused sub-skills — /wjs-transcribing-audio, /wjs-translating-subtitles, /wjs-dubbing-video, /wjs-burning-subtitles. Use when the user asks for full localization in one go ("帮我把这个西班牙语视频做成中文字幕+配音", "translate and dub this video", "做完整的本地化"). For any individual step (just transcribe, just translate, just dub, just burn), invoke the sub-skill directly — it's faster and the boundary is cleaner.
Claude Code skills for analytics and data engineers working with dbt, Snowflake, and data pipelines
Track multiple live deals with milestones, deadlines, action items, and status updates. Maintains a deal pipeline view and surfaces upcoming deadlines and overdue items. Use when managing a book of business, tracking process milestones, or preparing for weekly deal reviews. Triggers on "deal tracker", "deal status", "where are we on", "process update", "deal pipeline", or "weekly deal review".