Search
AI & LLM Engineering · For devops and sre engineers
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 145 | Proactively harden a cloud account or organization before an incident — prioritizing IAM and identity risk over checkbox findings, closing the exposures that become attack paths (public storage… | trilwu/ | 157 | — | ~1.9k | Automated safety check: Pass | MIT | 1 mo ago |
| 146 | Interactive discovery + implementation workflow that gathers requirements through picker-based questions (intent, scope, constraints, preferences), scans the codebase for what it can already infer… | aws/ | 2.8k | — | ~6.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 147 | Govern Azure costs with budgets, alerts, tags, and policy restrictions. | microsoft/ | 255 | — | ~476 | Automated safety check: Pass | MIT | yesterday |
| 148 | Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit… | datadog-labs/ | 177 | — | ~25k | Automated safety check: Pass | MIT | 2 days ago |
| 149 | Production readiness checklist for Claude-powered applications — Use when working with prod-checklist patterns. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 150 | Secure your Anthropic integration — API key management, input validation, Use when working with security-basics patterns. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Notes | MIT | yesterday |
| 151 | Migrate an application to or from Cohere with a provider adapter, parallel embedding index, quality evaluation, canary traffic, and rollback. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 152 | Migrate Cohere API v1 or older SDK usage to v2 with contract tests, model lifecycle checks, canarying, and rollback. | jeremylongshore/ | 2.8k | — | ~1.1k | Automated safety check: Pass | MIT | yesterday |
| 153 | Triage LangChain 1.0 / LangGraph 1.0 production incidents — LLM-specific SLOs, provider outage runbook, latency spike decision tree, cost-overrun response, agent loop containment. | jeremylongshore/ | 2.8k | — | ~3.8k | Automated safety check: Pass | MIT | yesterday |
| 154 | Wire LangChain 1.0 / LangGraph 1.0 traces into an OpenTelemetry-native backend (Jaeger, Honeycomb, Grafana Tempo, Datadog) with LLM-specific SLOs, safe prompt-content policy, and subgraph-aware span… | jeremylongshore/ | 2.8k | — | ~3.6k | Automated safety check: Pass | MIT | yesterday |
| 155 | Troubleshoot and respond to Langfuse-related incidents and outages. | jeremylongshore/ | 2.8k | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 156 | Langfuse production readiness checklist and verification. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~2k | Automated safety check: Pass | MIT | yesterday |
| 157 | Distribute OpenRouter requests across multiple keys and models for high throughput. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 158 | Validate production readiness of your OpenRouter integration. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Notes | MIT | yesterday |
| 159 | Enforce organizational governance for Supabase projects: shared RLS policy library with reusable templates, table and column naming conventions, migration review process with CI checks, cost alert… | jeremylongshore/ | 2.8k | — | ~2.8k | Automated safety check: Pass | MIT | yesterday |
| 160 | 160.AI Observability Implement comprehensive observability for LLM applications including tracing (Langfuse/Helicone), cost tracking, token optimization, RAG evaluation metrics (RAGAS), hallucination detection, and… | omer-metin/ | 163 | — | ~578 | Automated safety check: Pass | Apache-2.0 | 8 mo ago |
| 161 | Audit a Claude/Agent SKILL.md (or any AI skill / system prompt) for safety before installing or merging it. | mohitagw15856/ | 1.4k | — | ~1.5k | Automated safety check: Pass | MIT | 2 days ago |
| 162 | Add capabilities to an existing Agent Kernel project. An agent skill from yaalalabs/agent-kernel. | yaalalabs/ | 192 | — | ~13k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 163 | 163.Hcp Create Agent A skill your agent uses when you need to deploy HyperShift clusters on bare metal, edge environments, or disconnected infrastructures using pre-provisioned agents | openshift-eng/ | 120 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | 4 days ago |
| 164 | Optimize agent skills for discoverability on ClawdHub/MoltHub. | aAAaqwq/ | 105 | 1 repo | ~3.7k | Automated safety check: Pass | MIT | 2 days ago |
| 165 | Optimize gpu resource optimizer operations. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~569 | Automated safety check: Pass | MIT | yesterday |
| 166 | Configure CI/CD pipelines for Anthropic Claude API integrations. | jeremylongshore/ | 2.8k | — | ~1.5k | Automated safety check: Pass | MIT | yesterday |
| 167 | Execute production deployment checklist for Claude API integrations. | jeremylongshore/ | 2.8k | — | ~1.8k | Automated safety check: Pass | MIT | yesterday |
| 168 | Optimize CoreWeave GPU cloud costs with right-sizing and scheduling. | jeremylongshore/ | 2.8k | — | ~1.3k | Automated safety check: Pass | MIT | yesterday |
| 169 | Set up local development workflow for CoreWeave GPU deployments. | jeremylongshore/ | 2.8k | — | ~927 | Automated safety check: Notes | MIT | yesterday |
| 170 | 170.Cortex Recon ML reconnaissance — inventory all models, pipelines, data sources, and monitoring. | jeremylongshore/ | 2.8k | — | ~1.5k | Automated safety check: Notes | MIT | yesterday |
| 171 | Configure Langfuse CI/CD integration with GitHub Actions and automated testing. | jeremylongshore/ | 2.8k | — | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 172 | Deploy Langfuse with your application across different platforms. | jeremylongshore/ | 2.8k | — | ~1.9k | Automated safety check: Pass | MIT | yesterday |
| 173 | Retell AI reliability patterns — AI voice agent and phone call automation. | jeremylongshore/ | 2.8k | — | ~522 | Automated safety check: Pass | MIT | yesterday |
| 174 | Create tensorflow savedmodel creator operations. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~593 | Automated safety check: Pass | MIT | yesterday |
| 175 | Configure tensorflow serving setup operations. An agent skill from jeremylongshore/tons-of-skills-marketplace. | jeremylongshore/ | 2.8k | — | ~578 | Automated safety check: Pass | MIT | yesterday |
| 176 | Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server. | BagelHole/ | 1.2k | — | ~2.1k | Automated safety check: Pass | MIT | 4 mo ago |
| 177 | Guide to JSON Crack for visualizing complex JSON data structures | wentorai/ | 298 | 1 repo | ~2.1k | Automated safety check: Pass | MIT | 3 mo ago |
| 178 | 178.Lambda Labs On-demand GPU cloud instances for ML training. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 171 | 1 repo | ~3k | Automated safety check: Warn | MIT | 3 days ago |
| 179 | 179.Cost Estimation A skill your agent uses when the user wants to estimate or predict the cost, token usage, or time of a task BEFORE it runs — "how much will this feature cost to build", "estimate the tokens for this… | Habitat-Thinking/ | 114 | — | ~5.4k | Automated safety check: Pass | Unknown | 20 days ago |
| 180 | Coaches end-to-end ML system design interviews covering inference pipelines, recommendation systems, RAG, feature stores, and monitoring. | curiositech/ | 244 | — | ~3.4k | Automated safety check: Pass | MIT | 1 mo ago |
| 181 | Start or resume an APEX workflow or named step in Agent Host after manual owner selection. | jonathan-vella/ | 217 | — | ~538 | Automated safety check: Pass | MIT | yesterday |
| 182 | Use this sub-skill for MLflow Models, pyfunc, flavor APIs, signatures, input examples, dependencies, local serving/prediction, and mlflow.evaluate workflows. | VectorSpaceLab/ | 331 | — | ~675 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 183 | 183.Ultralytics A skill your agent uses for Ultralytics YOLO package workflows: CLI/Python model usage, data/config setup, train/val, prediction/results, export/deployment, tracking/solutions, model-family… | VectorSpaceLab/ | 331 | — | ~1.2k | Automated safety check: Pass | AGPL-3.0 | 1 mo ago |
| 184 | 184.Phx Watch PR Watch an Elixir/Phoenix PR with an Amp Orb keep-alive lease until required non-deployment CI is green and review threads are resolved. | oliver-kriska/ | 565 | — | ~1k | Automated safety check: Pass | MIT | 5 days ago |
| 185 | 185.Ringbot Make outbound AI phone calls. An agent skill from sundial-org/awesome-openclaw-skills. | sundial-org/ | 663 | — | ~1.2k | Automated safety check: Notes | No licence | 7 mo ago |
| 186 | 186.Restore Local DB Refresh a LOCAL MySQL database from a PRODUCTION dump, safely. | hmislk/ | 236 | — | ~4.1k | Automated safety check: Warn | GPL-3.0 | yesterday |
| 187 | Stand up a complete, ready-to-run computer-vision analytics stack on Intel hardware with one Docker Compose command — point it at your video sources and an OpenVINO/ONNX model to get live annotated… | open-edge-platform/ | 140 | — | ~4.4k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 188 | Audit, prepare, and deploy PAIDF Orchestration on a Kubernetes GPU cluster - single-GPU H100/L40S hosts, managed Kubernetes, kubeadm, and similar. | NVIDIA/ | 3.6k | — | ~3.8k | Automated safety check: Warn | Apache-2.0 | yesterday |
| 189 | Expert knowledge for Azure Files development including best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. | MicrosoftDocs/ | 776 | — | ~5.1k | Automated safety check: Pass | CC-BY-4.0 | 5 days ago |