Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
48,168 skills from 2,325 repositories · updated 12 hours ago
10,173 skills
- fehlerkatalogThomasMoreAI/legal-skills-openFür Versr Fehlerkatalog: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- kanzleikalenderThomasMoreAI/legal-skills-openFür Kanzleikalender und interne Abstimmung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.OtherNo warnings★ 97↓ —
- data-matchingcxcscmu/SkillLearnBenchMatching observation data to simulation output with exact datetime and depth binningOtherNo warnings★ 91↓ —
- data-visualization-expertroedyrustam/vibes-plugData visualization dashboards using D3.js, Recharts, and Tremor / Visualisasi data, grafik, dan dashboard dengan D3.js dan Recharts.OtherNo warnings★ 117↓ —
- cmdb-patternsserac-labs/seracCreate ServiceNow CIs and cmdb_rel_ci relationships, walk upstream/downstream impact, detect orphan/stale CIs, and align discovered CIs with the proper sys_class_name hierarchy.OtherNo warnings★ 77↓ —
- mlflowKalarisLabs/research-agent-skillsTracks machine learning experiments and manages model lifecycles with MLflow, covering mlflow.log_param, log_metric and log_artifact, autologging for scikit-learn, PyTorch Lightning, XGBoost and HuggingFace Transformers, the Model Registry with versions and stage transitions, run searching, and local or cloud model serving. Use when logging parameters, metrics and artifacts for training runs, comparing runs across experiments, registering and promoting model versions from Staging to Production, serving a logged model for inference, or reproducing an experiment from an MLflow project. Not for hyperparameter-sweep dashboards or general data versioning; use a dedicated tool for those.OtherNo warnings★ 81↓ —
- skypilot-multi-cloud-orchestrationKalarisLabs/research-agent-skillsMulti-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.OtherNo warnings★ 81↓ —
- change-managementBagelHole/DevOps-Security-Agent-SkillsImplement change management processes. Configure CAB reviews, change windows, and rollback procedures. Use when managing production changes.OtherNo warnings★ 1.2K↓ —
- simpo-trainingKalarisLabs/research-agent-skillsSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.OtherNo warnings★ 81↓ —
- otel-telemetry-emissionsollygarden/opentelemetry-agent-skillsVersion-pinned inventory of the telemetry (spans, metrics, logs, attributes) emitted by OpenTelemetry collector components and SDK instrumentation packages. Use when working with a covered component — what it emits at a given version, or how emission changed across versions — and when upgrading a component or SDK version, to see the telemetry after the change.OtherNo warnings★ 119↓ —
- bmod-toolsmithalvin-reyes/better-agentic-ideRequired bmod metadata. Never invoke this skill.OtherNo warnings★ 85↓ —Also in 1 other repo
- sharpenjoetawil7/first-passRewrites the prompt typed after the command before any work starts, then works from the rewrite. Splits a mixed-up message into a numbered list of asks, turns words like "be 100% sure", "cover all cases" or "don't break anything" into the checks they stand for, keeps every name, path, number and quote exactly, and stops to ask only where it would have to guess. Runs only when the user types it.OtherNo warnings★ 128↓ —
- cp-skill-ingestzby/commonplaceUse when asked to ingest one URL or local snapshot into a tracked .ingest.md source analysis, or to execute a bounded re-ingest request. Retaining quotes in an existing ingest is cp-skill-ground's job, not this skill's.OtherNo warnings★ 92↓ —
- visual-intelligencershankras/claude-code-apple-skillsIntegrate your app with iOS Visual Intelligence for camera-based search and object recognition. Use when adding visual search capabilities.OtherNo warnings★ 843↓ —
- foundation-modelsrshankras/claude-code-apple-skillsOn-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.OtherNo warnings★ 843↓ —
- ctf-web26zl/cybersec-toolkitUse when solving a CTF web challenge — SQLi, XSS, SSRF, SSTI, IDOR, auth bypass, file upload, deserialization, prototype pollution, race conditions, JWT attacks. Provides a decision tree and tool stack from this installer's web module. Triggers on "ctf web", "web challenge", "sqli", "xss", "ssti", "ssrf", "jwt".OtherNo warnings★ 87↓ —
- payment-gateway-expertroedyrustam/vibes-plugPayment gateways integration (Stripe, Midtrans) and secure webhooks / Integrasi payment gateway (Stripe, Midtrans) dan webhook aman.OtherNo warnings★ 117↓ —
- preview-data-generatorrshankras/claude-code-apple-skillsGenerate sample data and a multi-variantOtherNo warnings★ 843↓ —
- difficult-conversationsitseffi/agentic-osPrepare for challenging conversations using Prepare-Listen-Empathize-Clarify-Solve framework.OtherNo warnings★ 117↓ —
- announcement-bannerrshankras/claude-code-apple-skillsGenerates an in-app announcement banner system with remote configuration, scheduling, deep link actions, and dismiss tracking. Use when user wants in-app banners, promotional notices, maintenance alerts, or contextual announcements.OtherNo warnings★ 843↓ —
- hidden-agendasitseffi/agentic-osIdentify potential hidden agendas of stakeholders. Use before high-stakes meetings with complex motivations.OtherNo warnings★ 117↓ —
- ost-target-selectionitseffi/agentic-osSelect one target opportunity from an OST using evidence-based weighted scoring and tie-breakers.OtherNo warnings★ 117↓ —
- source-verificationHezaoHezao/poirot验证信源可信度的研究过程知识，指导 agent 在涉及事实声明时交叉核验信源OtherNo warnings★ 258↓ —
- app-icon-generatorrshankras/claude-code-apple-skillsGenerates an app icon for macOS or iOS — a fast CoreGraphics placeholder and/or flat layered source art to finish in Icon Composer (the Liquid Glass / iOS 26+ standard). Produces appearance variants (light/dark/tinted) and installs into the asset catalog. Use when the user wants to create, generate, iterate, or update an app icon.OtherNo warnings★ 843↓ —