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 19 hours ago
48,168 skills
- aeonforyourhealth111-pixel/Vibe-SkillsThis skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.PlanningNo warnings★ 3.8K↓ —Also in 1 other repo
- miro-rate-limitsjeremylongshore/tons-of-skills-marketplaceDesign and implement repository-side Miro REST traffic controls from credit weights, supplied headers, bounded queues, and reset-aware retries. Use when preventing or recovering from Miro 429 responses. Trigger with "Miro rate limit".DesignNo warnings★ 2.9K↓ —
- context-hunterforyourhealth111-pixel/Vibe-SkillsDiscover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixing bugs, or refactoring code.ProductivityNo warnings★ 3.8K↓ —
- ramp-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement a shared Ramp request budget with rolling-window throttling, bounded retries, pagination, and 504 recovery. Use when clients receive 429 or 504 responses or share one outbound IP. Trigger with "Ramp rate limit" or "Ramp 429".OtherNo warnings★ 2.9K↓ —
- memoryjeremylongshore/tons-of-skills-marketplaceUse when sharpening a perception or observation you ALREADY formed about conversation state, user behavior, drift, emotional shifts, or cross-turn patterns. Trigger phrases include "what did you notice about X", "the user keeps doing Y", "I sense something has changed", "is the user X-ing", "what does this pattern suggest", "what shifted across our turns", "am I missing something here", "why did the conversation move from X to Y", or any moment requiring verification of whether a felt signal is real or projection. The skill calls the memory MCP tool to retrieve a perception scaffold (perception failure, detection procedure, suppression vectors) that SHARPENS an observation you already have. It is NOT a substitute for observing first. Do NOT trigger for fact extraction, summarization, list-making, factual lookups, or write-heavy memory tasks (storing/retrieving structured data). Memory harness is filter/perception oriented; calling on write-heavy tasks produces scaffold paralysis.ProductivityNo warnings★ 2.9K↓ —
- skill-risk-scannerZJU-REAL/Easel内容原创度与版权风险评估：分析文案是否存在洗稿/搬运嫌疑，评估素材版权风险， 检查引用规范。基于 LLM 文本分析，不包含技术查重。 当用户说"查重"、"原创度"、"是不是抄的"、"版权风险"、"能不能用这张图"、 "音乐版权"、"原创检测"、"有没有侵权"、"素材版权"、"会不会被投诉"时触发。 和 skill-quality-gate 的区别：quality-gate 查敏感词和平台规则合规， risk-scanner 专注原创度和版权侵权风险。OtherNo warnings★ 4.2K↓ —
- groq-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect Groq debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Groq problems. Trigger with phrases like "groq debug", "groq support bundle", "collect groq logs", "groq diagnostic".EngineeringNo warnings★ 2.9K↓ —
- yt-outlinejeremylongshore/tons-of-skills-marketplaceCreate a filmable YouTube outline and demo prep checklist from approved brief and packaging artifacts. Use when planning screen actions, section timing and rehearsals. Trigger with "outline this video" or "demo prep checklist".MediaNo warnings★ 2.9K↓ —
- package-searchdavepoon/buildwithclaudeSearch for packages and assess security risk before adding as dependenciesSecurityNo warnings★ 3.7K↓ —
- exa-observabilityjeremylongshore/tons-of-skills-marketplaceInstrument Exa calls with content-free metrics, traces, cost, and asynchronous lifecycle signals that support diagnosis without logging retrieved text. Use when operating or reviewing this Exa boundary. Trigger with "Exa observability", "review Exa observability", or "fix Exa observability".DevOpsNo warnings★ 2.9K↓ —
- hermes-tweetdavepoon/buildwithclaudeUse Hermes Tweet when a Claude Code workflow needs a source-aware handoff to Hermes Agent for X/Twitter research, account context, monitoring, or approval-gated actions through the native Hermes Agent plugin.ScienceNo warnings★ 3.7K↓ —
- apify-debug-bundlejeremylongshore/tons-of-skills-marketplaceCollect Apify debug evidence for support tickets and troubleshooting. Use when an Actor run has failed, is stuck, or produced empty output and you need to gather run metadata, logs, dataset samples, and environment info before opening a support ticket. Trigger with "apify debug", "apify support bundle", "collect apify logs", "apify diagnostic", "apify run failed why".EngineeringNo warnings★ 2.9K↓ —
- doca-argpNVIDIA/skillsUse this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring `doca_argp_init` → register params → `doca_argp_start` → `doca_argp_destroy` in order; picking a parameter type from the full public enum (`DOCA_ARGP_TYPE_STRING`, `_INT`, `_BOOLEAN`, `_DEVICE`, `_DEVICE_REP`, `_DOUBLE` — six values, not three); preserving the built-in DOCA flags (`-h` `-v` `-l` `--sdk-log-level` `--log-filter` `-j`/`--json`, NOT `--json-config`); `--device` is per-program; or debugging `DOCA_ERROR_BAD_STATE` / `INVALID_VALUE` / `NOT_SUPPORTED` / `IO_FAILED` from `doca_argp_*`. Trigger on implicit phrasings: "add a custom flag to a DOCA sample", "should I use getopt here", "BAD_STATE registering a new param", "my JSON config key is rejected", or "my sample's --json is ignored". Refuse and route elsewhere for variadic-flag / subcommand / shell-completion features, DOCA Core context, or DOCA Log internals.EngineeringNo warnings★ 3.8K↓ —
- style-transferZJU-REAL/Easel文案风格迁移：把一段文案从一种风格改写成另一种风格（严肃→搞笑、书面→口语、文艺→直白、正式→社交媒体感）， 支持风格参考（给一段目标风格的示例文本）。 使用时机：用户说"改成搞笑风格"、"换个风格"、"风格迁移"、"改成口语化"、"改成文艺风"、 "像 XX 那样写"、"风格改写"、"换个腔调"。 和 text-polisher 的区别：polisher 提升质量不改风格，style-transfer 改变风格不做质量评估。OtherNo warnings★ 4.2K↓ —
- skill-zhihu-answerZJU-REAL/Easel知乎问答回答发布：在知乎问题下发布原创回答——搜热门问题、检查可答性、写内容、 Playwright 发布（绕 header 遮挡 + JS 遍历发布按钮）。当用户说"回答知乎问题""在知乎问答下回答" "发知乎回答""知乎答题""帮我回答这个知乎问题""批量回答知乎"时使用。与 skill-zhihu-publisher 区别：那个发**专栏文章**（zhuanlan），本 SKILL 专发**问答区的回答**；回答内容写作用制作层 SKILL （novel-writer / copywriting）。TestingNo warnings★ 4.2K↓ —
- html-wireframeplannotator/effective-htmlDirect-invocation specialist for low-fidelity, self-contained HTML wireframes that test information hierarchy, content, navigation, task flow, and responsive structure before visual design. Use when the user explicitly invokes html-wireframe or the broad html skill routes a wireframe request here. Do not activate independently from a general request. Do not use for polished mockups or production-like interaction; use html-prototype for those.TestingNo warnings★ 3.8K↓ —
- cohere-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement Cohere endpoint-aware throttling, bounded retry, and queue backpressure from current limits and observed responses. Use when handling 429s or planning throughput. Trigger with "Cohere rate limit", "Cohere throttling", or "Cohere 429".PlanningNo warnings★ 2.9K↓ —
- reasoningjeremylongshore/tons-of-skills-marketplaceUse BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare these approaches". Also fires on cross-domain analysis, strategy questions, architecture decisions, or anything requiring multiple factors to be weighed before responding. The skill calls the reasoning MCP tool to retrieve a cognitive scaffold (named failure pattern, executable procedure, suppression vectors, falsification test) the model absorbs internally before generating its response. Catches causal shortcuts, premature conclusions, generic templates, and surface pattern matching that produce confidently-wrong answers. Do NOT trigger for simple factual lookups, syntax questions, file reads, code execution, or restating the user's input.TestingNo warnings★ 2.9K↓ —
- create-verification-skillbacknotprop/pstackGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.DesignNo warnings★ 3.3K↓ —
- apify-sdk-patternsjeremylongshore/tons-of-skills-marketplaceProduction-ready patterns for Apify SDK and apify-client in TypeScript. Use when building Actors with Crawlee, managing datasets/KV stores, or implementing robust client wrappers with retry and validation. Trigger with "apify SDK patterns", "apify best practices", "apify client wrapper", "crawlee patterns", "idiomatic apify".BrowserNo warnings★ 2.9K↓ —
- figure-it-outbacknotprop/pstackDesign an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.DesignNo warnings★ 3.3K↓ —
- no-commentsmichael-denyer/pstack-claudeSpawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.OtherNo warnings★ 3.7K↓ —
- sharp-edgestrailofbits/skillsIdentifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by default' and 'pit of success' principles. Triggers: footgun, misuse-resistant, secure defaults, API usability, dangerous configuration.SecurityNo warnings★ 7.9K↓ —
- chrome-mcp-troubleshootingtrailofbits/skillsDiagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.BrowserNo warnings★ 7.9K↓ —
doca-perftest
NVIDIA/skills
NewTestingUpdated 2 days ago
From the author
Use this skill when the user is running DOCA Perftest (doca_perftest), the RDMA benchmark that measures bandwidth, message rate and latency for RDMA verbs, point-to-point or across a cluster, with an optional DOCA Verbs backend (-r dv) or GPUNetIO engine (--engine gpunetio). Trigger even when the user does not say "DOCA Perftest" — implicit phrasings include "how do I benchmark RDMA write bandwidth with DOCA", "run ib_write_bw but across 8 nodes", "perftest says the device is busy", "my latency numbers differ between client and server", "launch the server over SSH", or "run an all-to-all RDMA test from a JSON scenario". Refuse and route elsewhere for DOCA install (doca-setup), DOCA Bench (doca-bench), and application-level throughput.
Install
npx skills add NVIDIA/skills --skill doca-perftest -a claude-code
Installs to .claude/skills/doca-perftest/ · 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 90
Security100
Provenance83
Maintenance100
Licence100
Adoption57
Files (8)
- BENCHMARK.md
- CAPABILITIES.md
- SKILL.md
- SKILLCARD.yaml
- TASKS.md
- evals/evals.json
- skill-card.md
- skill.oms.sig