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.
45,100 skills from 2,196 repositories · updated 6 hours ago
9,668 skills
- incident-managementBagelHole/DevOps-Security-Agent-SkillsImplement incident management processes and escalation procedures. Configure on-call schedules and post-incident reviews. Use when managing production incidents.OtherNo warnings★ 1.2K↓ —
- choose-metricharness/harness-skillsRecommend primary/guardrail metrics for an experiment or rollout, judged against a good-metric checklist. Checks existing metrics and event health, surfaces auto-created guardrails. Doesn't create or attach metrics — see create-metric / instrument-metric / manage-experiments. Trigger phrases: choose/pick a metric, primary metric, guardrail metric, what to monitor.OtherNo warnings★ 125↓ —
- analyze-costsharness/harness-skillsAnalyze cloud costs, find optimization opportunities, and track anomalies using Harness CCM via MCP. Use when user says "cloud costs", "analyze costs", "cost optimization", "reduce spending", "cost report", or asks about cloud bills.OtherNo warnings★ 125↓ —
- object-storageBagelHole/DevOps-Security-Agent-SkillsConfigure object storage with S3, GCS, and MinIO. Implement lifecycle policies and access controls. Use when managing object storage.OtherNo warnings★ 1.2K↓ —
- gradient-methodsparcadei/Continuous-Claude-v3Problem-solving strategies for gradient methods in optimizationOtherNo warnings★ 3.9K↓ —Also in 1 other repo
- runbook-creationBagelHole/DevOps-Security-Agent-SkillsCreate operational runbooks and standard operating procedures. Document troubleshooting guides and recovery procedures. Use when documenting operational knowledge.OtherNo warnings★ 1.2K↓ —
- create-triggerharness/harness-skillsGenerate Harness Trigger YAML for automated pipeline execution and create via MCP. Use when user says "create trigger", "webhook trigger", "cron trigger", "scheduled build", "artifact trigger", or wants pipelines to run automatically.OtherNo warnings★ 125↓ —
- skill-creatorfeiskyer/claude-code-settingsCreate, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.OtherNo warnings★ 1.7K↓ —
- ssl-tls-managementBagelHole/DevOps-Security-Agent-SkillsManage SSL/TLS certificates with Let's Encrypt and internal PKI. Configure secure HTTPS, certificate renewal, and cipher suites. Use when implementing secure communications.OtherNo warnings★ 1.2K↓ —
- alerting-oncallBagelHole/DevOps-Security-Agent-SkillsSet up alerting rules, configure on-call rotations, and manage incident response workflows. Integrate with PagerDuty, Opsgenie, or Grafana OnCall for alert routing and escalation. Use when implementing alerting strategies and on-call management for production systems.OtherNo warnings★ 1.2K↓ —
- ai-pipeline-orchestrationBagelHole/DevOps-Security-Agent-SkillsOrchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster. Build reliable, observable, and retriable workflows for production AI systems.OtherNo warnings★ 1.2K↓ —
- claude-md-improverEncod3d-Sec/TORCHOFFLINE FALLBACK for the claude-md-management plugin - prefer that plugin when it is installed. Audit and improve CLAUDE.md files - scan for CLAUDE.md files, evaluate quality against templates, output a report, then make targeted updates. Invoke explicitly (/claude-md-improver) when the plugin is unavailable.OtherNo warnings★ 335↓ —
- ai-sre-incident-responseBagelHole/DevOps-Security-Agent-SkillsBuild AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.OtherNo warnings★ 1.2K↓ —
- ai-red-teamingBagelHole/DevOps-Security-Agent-SkillsRun structured AI red team exercises for jailbreak resistance, data exfiltration risk, harmful output controls, and agent tool abuse resilience.OtherNo warnings★ 1.2K↓ —
- pm-agilekonglong87/superPMUse when: 项目启动时需要建立敏捷开发流程、设计团队协作机制、规划迭代节奏 Do NOT use when: 团队已有成熟敏捷流程、仅需单一项目管理工具而非流程设计OtherNo warnings★ 84↓ —
- example-vueBintzGavin/heliosPatterns for using Helios with Vue. Use when building compositions in a Vue environment.OtherNo warnings★ 123↓ —
- trend-to-microbetFAIRY123456789/human-edge-agent-skillsTurn a fast-moving AI, product, creator, career, or technology trend into a small evidence-producing bet instead of a vague FOMO reaction. Use when the user says something is suddenly hot, wonders whether to chase a new model, platform, agent, Skill, or plugin, or wants a 48-hour to 7-day experiment with a clear upside, effort cap, proof metric, and stop rule.OtherNo warnings★ 104↓ —
- kgThomasMoreAI/legal-skills-openFür KG und Personengesellschaften: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: Großkanzlei Corporate/M&A.OtherNo warnings★ 95↓ —
- agent-ready-dns-aidfabricioctelles/skillsSub-skill: Implement DNS-AID records so agents discover endpoints through DNS. Use SVCB/HTTPS records under _agents namespace with alpn and connection parameters.OtherNo warnings★ 121↓ —
- hunt-cacheEncod3d-Sec/TORCHWeb cache poisoning + cache deception hunting - unkeyed input poisoning, cache-key analysis, path-confusion deception, header/parameter cloaking. Wiki-first, FIND schema output.OtherNo warnings★ 335↓ —
- ardot-style-guidebalabalabalading/huuuuuuho-skills从头设计或为 Ardot 项目应用视觉主题时使用此技能。 涵盖 `search_style_guide` → `build_style_guide` 工作流程，用于发现和应用完整的设计系统（颜色、排版、间距、布局模式）。 触发条件："设计落地页"、"创建仪表板"、"应用深色主题"、 "设置设计系统"、"选择调色板"、"为应用选择字体"、 "样式指南"、"视觉风格"、"外观和感觉"。OtherNo warnings★ 118↓ —
- zhangyi-kickoffaph199686/zhangyi-studio张翼立项立意：从零点子、单一玩法或已有方案进入设计，先给可反应的概念草案，再推导病灶与支柱、比较方案并形成裁决。Use when the user wants to make a game but has no clear idea, has only one mechanic or theme, wants to choose a game direction, define core gameplay, analyze references, or evaluate an early concept. 用户想做游戏却没想好、只想好一个怎么玩的点、已有部分约束、选方向或评估早期创意时使用。OtherNo warnings★ 119↓ —
- visualizationrobium-ai/robiumChoose between RViz2, Foxglove, Lichtblick, and Rerun to inspect robot behavior.OtherNo warnings★ 100↓ —
- parallel-ops0xDarkMatter/claude-modsRouter for parallel or recurring agent work across six skills. Covers: parallel agents, fan out work, delegate to workers, run overnight, scheduled loop, land branches, mixed-model fleet, orchestrate workers, background agents at scale. Triggers on: which skill for parallel work, fan out agents, spawn workers, run this overnight, schedule a loop, land my branches, clean up after a wave, heterogeneous fleet, delegate to cheaper model, autonomous loop.OtherNo warnings★ 76↓ —
agent-ready-scan-site
fabricioctelles/skills
OtherUpdated 13 hours ago
From the author
Sub-skill: Scan any URL for agent readiness. Checks 22 standards across 5 categories, returns readiness level (0-5), status of all checks, and fix instructions.
Install
npx skills add fabricioctelles/skills --skill agent-ready-scan-site -a claude-code
Installs to .claude/skills/agent-ready-scan-site/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 83
Security100
Provenance65
Maintenance100
Licence100
Adoption36
Files (1)
- SKILL.md