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.
47,307 skills from 2,272 repositories · updated 12 hours ago
10,066 skills
- Syncro InvoicesWYRE-AI/msp-claude-pluginsSyncro MSP invoices: invoice fields, line items, payment processing, and billing workflows.OtherNo warnings★ 51↓ —
- muyang-print-posteryokel1121/muyang-illustration-skills风格包含：复古剪影插画、复古电影插画、日式版画插画。用于收集用户指定的主体和具体风格，将主体原样填入对应固定配方并直接生成图片；不得展示提示词、扩写或改变色数。OtherNo warnings★ 209↓ —
- AI Services Market MCPNewagentskillexchange/skillsTeaches an agent to connect to the AI Services Market MCP server (https://aiservicesmarket.lol/mcp) and use its seven tools — search_skills, get_skill, search_use_cases, get_use_case, get_entitlement, create_checkout, claim_pro — to find installable agent skills, read full details and pricing, and generate Stripe checkout links for single skills or Pro subscriptions. Use when someone asks an agent to find, compare, or buy an AI agent skill.OtherNo warnings★ 58↓ —
- matlab-setup-gpumatlab/matlab-agentic-toolkitDetect and validate GPU availability for MATLAB GPU computing. Use when the user can't use their GPU, or is setting up or selecting a GPU. Triggers on: gpuDevice, GPU setup, check GPU, GPU not found, GPU not working, can't use GPU, GPU not available, unable to find a supported GPU device, compatible GPU, canUseGPU, validateGPU.OtherNo warnings★ 1.2K↓ —
- goalcoco-research/cocoPersistent project goal that survives across sessions and tools, with continuous-execution loop semantics. Use when someone asks to "set a goal", "what is my goal", "goal status", "keep working on X until done", "resume the goal", or wants work to continue across sessions until an objective is achieved. File-backed (.goal.md at project root); shared by every Coco-installed tool working in that repository.OtherNo warnings★ 794↓ —
- motherduck-ducklakemotherduckdb/agent-skillsDecide whether DuckLake fits a MotherDuck workload and operate it safely. Use whenever DuckLake, open table formats, or customer-owned buckets come up.OtherNo warnings★ 62↓ —Also in 1 other repo
- js-reversecoco-research/coco在使用 js-reverse-mcp 做前端 JavaScript 逆向时使用，适用于签名链路定位、页面观察取证、运行时采样、本地补环境复现与证据化输出。优先适配当前环境里的 js-reverse_* 工具，需要更强的浏览器/CDP/Hook 面时联动 jshookmcp。OtherNo warnings★ 794↓ —
- Syncro CustomersWYRE-AI/msp-claude-pluginsSyncro MSP customers: customer fields, contacts, sites and locations, and customer create, update, and search operations.OtherNo warnings★ 51↓ —
- seed-casebookOutlineDriven/outline-driven-developmentUse when a user opens a build cycle in a repo with an iteration convention and wants the casebook seeded with real content. Not for ongoing triage or multi-repo setup.OtherNo warnings★ 55↓ —
- apolloAnil-matcha/awesome-muse-connectorsSearch B2B contacts with Apollo.io: find people by title and company, enrich contacts and companies. Trigger phrases: apollo, find prospects, enrich contact.OtherNo warnings★ 1.4K↓ —
- minutes-tagsilverstein/minutesLightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- popular-international-productsjoomcode/joompulse-skillsFinds fast-growing international (imported) products inside ONE chosen category on JoomPulse — Mercado Livre (Brasil) or Shopee Brasil — and returns them as a product table with price, estimated sales and revenue, rating, reviews, time on air and the seller's standing. On Mercado Livre each row links to its JoomPulse page and points to JoomPro for sourcing; on Shopee each row links to the item and sourcing data is not available. Use when a seller wants the trending imported items in one category. Triggers: "popular international products in this category", "fast-growing imported products", "cross-border products on Shopee"; pt-BR "produtos internacionais em alta nessa categoria", "produtos importados que mais crescem", "produtos internacionais na Shopee", "produtos que vêm de fora na Shopee". Ask which marketplace when unclear; never mix the two. Sales and revenue are JoomPulse estimates, not real transactions. For the same search across all categories, use the all-categories international skill.OtherNo warnings★ 54↓ —
- motherduck-load-datamotherduckdb/agent-skillsLoad files, object storage, dataframes, or external databases into MotherDuck with bulk ingestion. Use for any import of data into MotherDuck.OtherNo warnings★ 62↓ —Also in 1 other repo
- ca-adrarbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 149↓ —
- huggingfaceAnil-matcha/awesome-muse-connectorsVerify your Hugging Face account and search the model hub. Read-only. Trigger phrases: hugging face, huggingface, hf model, search models.OtherNo warnings★ 1.4K↓ —
- ca-watcharbiterForge/codeArbiterWatch a PR's CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges.OtherNo warnings★ 149↓ —
- post-to-slackOutlineDriven/outline-driven-developmentUse when the user explicitly asks to share a message on Slack through an incoming webhook. Not for posting without an explicit request or for retrying an ambiguous delivery.OtherNo warnings★ 55↓ —
- Atera AgentsWYRE-AI/msp-claude-pluginsAtera RMM agents: agent records and fields, online/offline status, endpoint search and monitoring, PowerShell and script execution, and agent lifecycle.OtherNo warnings★ 51↓ —
- ca-auditarbiterForge/codeArbiterAssemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.OtherNo warnings★ 149↓ —
- reachai-onboardingw8123/EnterpriseAgentFrameworkIntegrate Java business systems with ReachAI SDK registration, instance heartbeat, gateway/embed access, and business capability source sync. Use when asked to connect a Spring Boot service to ReachAI, add reachai-capability-sdk or reachai-spring-boot2-starter, configure reachai.registry/reachai.project/reachai.capability, prepare @ReachCapability declarations, or verify SDK onboarding from a ReachAI manifest.OtherNo warnings★ 971↓ —
- ca-adr-statusarbiterForge/codeArbiterInspect ADR health read-only; optionally select one ADR with --adr N.OtherNo warnings★ 149↓ —
- fix-p0-issuesOutlineDriven/outline-driven-developmentUse when the user asks to fix P0s, address critical issues, or work on priorities from the weekly product briefing. Don't use for non-P0 issues or local bug fixes.OtherNo warnings★ 55↓ —
- ats-detectormohitagw15856/pm-claude-skillsWork out which applicant tracking system a job uses from its application link, and give the formatting rules that system parses safely. Use when asked which ATS does this company use, will my CV get through the ATS, is my CV ATS friendly, or how should I format for Workday, Greenhouse, Lever or Taleo. Produces the detected system with the evidence, a parsing-safe formatting checklist, the file type to upload, and a check of a supplied CV against the rules.OtherNo warnings★ 1.5K↓ —
- ca-checkpointarbiterForge/codeArbiterPeriodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.OtherNo warnings★ 149↓ —
torchforge-rl-training
KalarisLabs/research-agent-skills
OtherUpdated 4 days ago
From the author
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.
Install
npx skills add KalarisLabs/research-agent-skills --skill torchforge-rl-training -a claude-code
Installs to .claude/skills/torchforge-rl-training/ · 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
No warnings.
Why 82
Security100
Provenance62
Maintenance100
Licence100
Adoption32
Files (3)
- SKILL.md
- references/api-reference.md
- references/troubleshooting.md