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 1 hour ago
48,168 skills
- principle-build-the-levermichael-denyer/pstack-claudeApply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.WritingNo warnings★ 3.7K↓ —
- i4h-workflow-dataset-mimicNVIDIA/skillsExpand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data, alter state directly, or generate new images.ProductivityNo warnings★ 3.8K↓ —
- doca-bare-metal-deploymentNVIDIA/skillsRunning a DOCA-linked binary directly on the hardware, with no container or kubelet: on host x86 with a BlueField NIC over PCIe, or bare-metal on BlueField Arm. Use this skill for launching and supervising it (direct, tmux, systemd), and when it "exits 1 right after launch", "systemd keeps restarting it", reports "no matching device on the BF", or the BlueField itself is unhealthy: "bfb-install exited 0 but DPU is dead", "ping 192.168.100.2 works but ssh fails", "host PFs aren't showing netdevs". Refuse service containers under kubelet (doca-container-deployment). Covers PCI/NUMA/CPU/IRQ binding, co-tenant isolation (cgroup-v2/netns/numactl), a seven-layer error taxonomy, platform lifecycle (BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery) and a six-state BlueField lifecycle classifier. Destructive firmware burn / mlxconfig set requires explicit confirmation via doca-hardware-safety; library APIs, env prep, and build use other skills.DevOpsNo warnings★ 3.8K↓ —
- differential-reviewtrailofbits/skillsPerforms security-focused differential review of code changes. Adapts analysis depth to codebase size, uses git blame for context, calculates blast radius by counting callers, checks test coverage of modified code, and generates a markdown report. Use when reviewing a PR, commit, or diff for security vulnerabilities, checking whether a change re-introduces a previously fixed bug, asking what else a change could break, or finding which modified code has no test covering it.EngineeringNo warnings★ 7.9K↓ —
- pr-gardeningpaperclipai/paperclipDiscover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.OtherNo warnings★ 109.2K↓ —
- tao-train-ocrnetNVIDIA/skillsOCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCRNet model. Trigger phrases include "train OCRNet", "scene text recognition", "OCR cropped text", "CTC / attention text decoder".OtherNo warnings★ 3.8K↓ —
- prisma-postgres-setupprisma/skillsObtain or reuse a Prisma Postgres database and connect an application. Use when the user needs a database and has none configured ("I need a database", "add a Postgres database", "set up a database for this app"), runs or mentions `create-db` or `npx create-db`, or asks to set up or connect Prisma Postgres, including in v0 and the Vercel Marketplace. Hands Prisma ORM configuration to prisma-orm-setup; reuses an existing connection first and honors an explicit provider, driver, alternative ORM, or database-only choice.OfficialDataNo warnings★ 77↓ —
- humanize-pptnexu-io/open-designA presentation system for agent-made PPTs — born for the talk, not just the template. It turns raw material into an AST (audience-state-transfer) outline with per-page visual-enhancement decisions (image / SVG diagram / video), hands a production brief to a downstream renderer (HTML-PPT skills or native PPTX), then runs a capped 3-round presentation checkup (演讲体检) on the rendered deck. It never renders slides itself. Use before generating PPT/HTML slides from raw material, and after rendering when the user says things like "给这份 deck 做演讲体检" or "PPT 渲染质检". If all you want is one beautiful template page with no outline and no checkup, a rendering skill alone is enough.WritingNo warnings★ 105.1K↓ —
- Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.DataNo warnings★ 107.2K↓ —Also in 4 other repos
- daskforyourhealth111-pixel/Vibe-SkillsParallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.DataNo warnings★ 3.8K↓ —Also in 1 other repo
- conversion-signal-qaaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "QA my conversion tracking before launch", "check my UTMs / pixel / event firing", "set up a tracking pre-flight", or "set the dedup rule so Meta and Google stop double-counting"; builds and fixes the measurement plumbing — conversion-event firing, UTM hygiene, cross-platform dedup rules, attribution-window alignment, and offline/iOS-ATT modeled-gap flags — as a pre-flight checklist plus a UTM/event-spec builder. Not for scoring R1/R2 — that is a scored veto in ad-account-auditor; not for account structure — use campaign-architect. 付费广告转化追踪QA/UTM规范/跨平台去重TestingNo warnings★ 3K↓ —
- miro-hello-worldjeremylongshore/tons-of-skills-marketplaceDesign and implement a bounded, read-only Miro connectivity probe that proves authorization context before writes are enabled. Use when smoke-testing a new Miro integration. Trigger with "test Miro connection".TestingNo warnings★ 2.9K↓ —
- email-render-builderaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "build the email HTML", "make this email responsive", "fix dark-mode rendering", or "QA the email across clients"; produces the coded HTML build — a responsive table layout, dark-mode + accessibility pass, a client-render matrix, image-block fallbacks, and a plain-text parity check. Not for writing the copy — use email-creative-builder; not for scoring the email or computing EQS — use email-quality-auditor. 邮件HTML/响应式邮件/暗色模式渲染MediaNo warnings★ 3K↓ —
- aurakitdavepoon/buildwithclaudeSonnet Amplified fullstack engine. 34 modes, SEC-01~15 OWASP security, 13 runtime hooks, 75% token reduction. Install: npx @smorky85/aurakitSecurityNo warnings★ 3.7K↓ —
- metabolomics-workbench-databaseforyourhealth111-pixel/Vibe-SkillsAccess NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.DataNo warnings★ 3.8K↓ —
- transformersforyourhealth111-pixel/Vibe-SkillsThis skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.MediaNo warnings★ 3.8K↓ —
- exploitsdavepoon/buildwithclaudeAnalyze exploit intelligence for a vulnerability against the current repositorySecurityNo warnings★ 3.7K↓ —
- short-video-scripteraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "script this short video", "write a TikTok / Reels / Shorts script", "给这条抖音或视频号视频写脚本", or "fix the hook — viewers drop off in the first seconds"; produces timestamped beat-sheet scripts on the retention-gate model (0-2s hook / 2-5s confirmation / 5-15s payoff / loop-or-CTA) with per-scene script lines, on-screen text for muted viewing, asset keywords, and 9:16 format-param rows per platform norm card for TikTok, Reels, Shorts, 抖音, and 视频号 — plus 2-3 hook options from named hook families and an AI-content disclosure line by default on realistic synthetic media. Spec-only: rendering, TTS, and publishing stay with the user's own tools — no pipelines, no upload automation. Not for creator video briefs — use brief-generator; long-form video SEO belongs to content-writer. 短视频脚本/抖音分镜/开头钩子/竖屏9:16MediaNo warnings★ 3K↓ —
- performing-causal-analysisforyourhealth111-pixel/Vibe-SkillsEstimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression discontinuity, or other treatment-effect analyses, including robustness checks and counterfactual plots. For choosing a study design before analysis, use designing-experiments instead.DesignNo warnings★ 3.8K↓ —
- social-pulse-monitoraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "monitor brand mentions", "set up social listening", "did anything spike about us this week", or "watch these accounts for buying triggers"; runs always-on keyless listening — a versioned listening-query architecture (brand variants incl. misspellings and 中文 names, exclusion terms, per-source syntax for HN Algolia / Bluesky / GDELT / Tavily), a mention sweep with six-class triage (crisis / bug / lead / praise / question / spam) each routed with an SLA, a 7-day rolling baseline with spike flags (the crisis trigger input), a B2B trigger watchlist (funding / hiring / launch signals), and an explicit coverage disclosure where X/IG/TikTok/LinkedIn/小红书 numbers are proxy-labeled, never Measured. Not for launch-window telemetry (T-0→T+30 rank and review polling) — use launch-monitor. 舆情监听/品牌提及监测/基线突刺/触发信号MarketingNo warnings★ 3K↓ —
- outreach-manageraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "write influencer outreach", "follow up with a creator", "pitch a journalist, hunter, or launch partner", or "negotiate partnership terms"; produces personalized pitches, multi-touch follow-up sequences, negotiation scripts with objection handling, and a status pipeline tracker — the shared outreach mechanics engine for creator, media/analyst, launch-partner, and social-selling / advocate-recruitment targets. Not for finalizing signed agreements — use contract-helper; not for media-list tiering, embargo terms, or press-release structure — use press-media-relations. 达人邀约建联/合作谈判话术LegalNo warnings★ 3K↓ —
- budget-optimizeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "allocate my influencer budget", "optimize spend across tiers", or "compare budget scenarios"; produces a tier/platform/content allocation table, ROI and CPM/CPE projections, scenario comparisons, and mid-campaign reallocation moves. Not for building the full campaign plan — use campaign-planner. 达人预算分配/投放预算优化MarketingNo warnings★ 3K↓ —
- share-of-voice-trackeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "track our share of voice", "what share of the conversation do we own vs competitors", or "trend our SOV this quarter"; computes SOV% = brand mentions ÷ (brand + competitor panel mentions) per platform per period on a LOCKED competitor panel — a panel switch invalidates the trend (restart the series and log the break; the ECHO O3 rule) — plus a sentiment-weighted SOV variant (sentiment labeled Estimated unless human-coded) and a Wikipedia-pageviews attention-share alternative; built from keyless listening connectors, gdelt.py news echo, and user exports — public counts only, closed platforms are never scraped. Not for backlink or offsite SEO signals — use offsite-signal-analyzer. 声量份额/竞品声量对比/提及份额/注意力份额BrowserNo warnings★ 3K↓ —
- brand-strategyjeremylongshore/tons-of-skills-marketplaceBuild or review a seven-part brand strategy covering identity, audience, positioning, messaging, visual principles, channels and measurement. Use when creating a brand brief, defining positioning or revising brand messaging. Trigger with "create brand strategy", "build brand brief" or "brand messaging".EngineeringNo warnings★ 2.9K↓ —
hunt-regressions
trailofbits/skills
OtherUpdated 3 days ago
From the author
Use when discovering possible regressions from a pinned change and its callers before reproduction.
Install
npx skills add trailofbits/skills --skill hunt-regressions -a claude-code
Installs to .claude/skills/hunt-regressions/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (CC-BY-SA-4.0) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: CC-BY-SA-4.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance87
Maintenance100
Licence80
Adoption61
Files (1)
- SKILL.md