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.
47,966 skills from 2,309 repositories · updated 11 hours ago
47,966 skills
- thermosmichael-denyer/pstack-claudeLaunch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.SecurityNo warnings★ 3.7K↓ —
- castai-hello-worldjeremylongshore/tons-of-skills-marketplaceRun a safe first CAST AI cluster connection that proves Cost Monitoring and agent health before enabling optimization. Use when starting a new evaluation, sandbox, or operator walkthrough. Trigger with: "CAST AI hello world", "try CAST AI safely", "connect my first CAST AI cluster".OtherNo warnings★ 2.9K↓ —
- tdd-guideforyourhealth111-pixel/Vibe-SkillsTest-first development route for TDD, writing failing tests first, RED -> GREEN -> REFACTOR, and behavior-changing feature/bug/refactor work. Do not use for already-failing test root-cause debugging, test-report packaging, or final completion evidence.TestingNo warnings★ 3.8K↓ —
- internal-commsdavepoon/buildwithclaudeA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).WritingNo warnings★ 3.7K↓ —
- thought-partnerjeremylongshore/tons-of-skills-marketplaceCollaborative thinking partner for exploring ideas, challenges, and decisions. Use when the user needs to analyze ambiguity, test assumptions, or compare options. Trigger with "think through", "explore", "brainstorm", "help me figure out", or an open-ended strategy or priority question.TestingNo warnings★ 2.9K↓ —
- i4h-workflowNVIDIA/skillsOrient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do not execute a known stage.ProductivityNo warnings★ 3.8K↓ —
- offensive-bluetooth-classicSnailSploit/Claude-RedBluetooth Classic (BR/EDR) attack methodology — device discovery, service enumeration via SDP, LMP/L2CAP layer attacks, legacy PIN cracking (BlueBorne / KNOB), Bluetooth file-transfer abuse (BlueSnarfing legacy), unauthenticated profile abuse (HSP, HFP, OPP), and modern relevance against older industrial / automotive / accessory targets. Use when in-scope devices use Bluetooth Classic (Bluetooth ≤ 4.0 BR/EDR) — common in legacy car kits, industrial sensors, older medical devices, and audio accessories.MediaNo warnings★ 9.9K↓ —
- content-quality-auditoraaron-he-zhu/aaron-marketing-skillsUse when auditing content quality, E-E-A-T, or publish readiness; runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan. Not for structural tags/headers alone — use on-page-seo-checker; not for domain/citation trust — use domain-authority-auditor. 内容质量/EEAT评分MarketingNo warnings★ 3K↓ —
- principle-model-the-domainmichael-denyer/pstack-claudeApply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.WritingNo warnings★ 3.7K↓ —
- openai-docsforyourhealth111-pixel/Vibe-SkillsUse when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.EngineeringNo warnings★ 3.8K↓ —
- fix-cimichael-denyer/pstack-claudeFind failing PR checks, inspect logs or external check links, and apply focused fixesOtherNo warnings★ 3.7K↓ —
- tao-train-dinov3NVIDIA/skillsDINOv3 continual self-supervised pre-training. Domain-adapts public DINOv3 ViT backbones on unlabeled images via teacher-student self-distillation (DINO + iBOT + KoLeo, optional Gram anchoring) and converts the EMA teacher into a timm-format backbone for downstream tasks. Trigger phrases include "train DINOv3", "DINOv3 SSL", "domain-adapt a foundation backbone", "continual pretraining", "self-supervised finetune DINOv3".ProductivityNo warnings★ 3.8K↓ —
- on-page-seo-checkeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "audit on-page SEO" or "diagnose why a single page dropped"; scores titles, meta, header structure, keyword placement, links, and images with prioritized fixes. Not for E-E-A-T / publish-readiness scoring — use content-quality-auditor; not for crawl / CWV / indexing — use technical-seo-checker. 页面SEO审计/排名诊断MarketingNo warnings★ 3K↓ —
- stop-that-shitlennney/stop-that-shitComplete requested work while preventing speculative defenses and scope creep. Use when considering extra hardening, reviewing possible overengineering, resolving repeated verification loops, following explicit task boundaries, or when the user invokes Stop That Shit. Ordinary use of validation, retries, or dependencies alone is not a trigger.PlanningNo warnings★ 3.4K↓ —Also in 1 other repo
- preference-frequency-manageraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "build a preference center", "set up a frequency opt-down ladder", "give people a step-down instead of unsubscribe", or "design a topic/cadence preference page"; produces a preference-center field spec, a frequency/topic opt-down ladder (down-tier paths that substitute for a hard unsubscribe), a preference-to-suppression mapping, and a SEND N-dimension sub-item note on preference-center / frequency options offered. Not for the lifecycle flow map or cadence governance — use email-sequence-designer; not for the consent/suppression record itself — use consent-registry; not for computing EQS or ruling the N1 unsubscribe veto — use email-quality-auditor. 邮件偏好中心/降频阶梯设计/退订替代降档DesignNo warnings★ 3K↓ —
- doca-perftestNewNVIDIA/skillsUse 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.TestingNo warnings★ 3.8K↓ —
- kiro-spec-initgotalab/cc-sddInitialize a new specification with detailed project descriptionPlanningNo warnings★ 3.7K↓ —
- swarmbacknotprop/pstackFan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.OtherNo warnings★ 3.2K↓ —
- principle-exhaust-the-design-spacemichael-denyer/pstack-claudeApply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.DesignNo warnings★ 3.7K↓ —
- clade-sdk-patternsjeremylongshore/tons-of-skills-marketplaceProduction-ready Anthropic SDK patterns — client config, retries, timeouts, Use when working with sdk-patterns patterns. error handling, TypeScript types, and async patterns. Trigger with "anthropic sdk", "claude client setup", "anthropic typescript", "anthropic python patterns".EngineeringNo warnings★ 2.9K↓ —
- shipping-across-surfaceskajisho5/ffmpeg-skillLand a change everywhere the same fact is stated — enumerating the full surface inventory (landing copy, docs, machine-readable summaries, changelog badges repeated across every page, sitemap, README, descriptions embedded in code, and untyped frontend consumers of typed responses), generating a surface instead of restating it, drift tests where you cannot generate, never hand-maintaining a copy of a surface another codebase owns, shipping a paired PR when you change a format a different codebase decodes, and keeping overloaded product words apart. Use when adding or renaming a user-facing feature, editing product/marketing copy or docs, renaming a serialized response field, changing a serialization or share-link format, wiring one repo's output into another's checks, or reviewing a PR that touched only one place a fact appears.TestingNo warnings★ 4.1K↓ —
- security-guardrailsdavepoon/buildwithclaudeAdversarial defense layer for the mortgage plugin — protects against prompt injection, system prompt extraction, PII leakage, workflow bypass, and social engineering attacks.SecurityNo warnings★ 3.7K↓ —
- 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↓ —
- social-measurement-loopaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "run the weekly social readout", "which denominator does our engagement rate use", or "which posts won this week and what changes next cycle"; produces the organic-social metric dictionary (every rate names its denominator — ERR engagement-by-reach vs ERI by-impressions vs ER-by-follower — locked across periods), median-not-mean per-post rollups with organic and boosted separated, EMV as labeled exec-translation only (never inside any score), an attributed CHAOSS/Orbit-style community-health readout with employees excluded, and the best/worst-performer write-back the next calendar cycle consumes. Not for dollar-ROI math or the ECHO profile result gate verdict — use roi-calculator and social-quality-auditor. 社媒周报/互动率分母/指标字典/复盘回写WritingNo warnings★ 3K↓ —
baoyu-wechat-summary
JimLiu/baoyu-skills
ProductivityUpdated Sep 10, 2026
From the author
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.
Install
npx skills add JimLiu/baoyu-skills --skill baoyu-wechat-summary -a claude-code
Installs to .claude/skills/baoyu-wechat-summary/ · 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: MIT
Safety checks on SKILL.md
- Uses sudoLow
Why 90
Security95
Provenance93
Maintenance85
Licence100
Adoption69
Files (6)
- EXTEND.md.example
- SKILL.md
- references/group-memory.md
- references/output-formats.md
- references/profiles.md
- references/setup.md