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.
46,100 skills from 2,198 repositories · updated 9 hours ago
9,541 skills
- PandaDoc RecipientsWYRE-AI/msp-claude-pluginsPandaDoc recipients and e-signature mechanics: recipient roles (signer, approver, viewer, CC), signing-order behavior, multi-party MSP signing scenarios, completion tracking via `has_completed`, recipient fields, and the document statuses that restrict adding or changing recipients.OtherNo warnings★ 52↓ —
- devexpress-blazor-toolbarDevExpress/agent-skillsBuild and configure the DevExpress Blazor Toolbar (DxToolbar) — an adaptive command bar for Blazor apps. Use when adding toolbars/command bars, configuring DxToolbarItem buttons, drop-down menus, overflow/adaptivity, icons/tooltips/links, checked and radio-group items, data binding, item templates (ChildContent/Template), and triggering actions like form submission. Also use for DxToolbar, DxToolbarItem, adaptive toolbar, overflow menu, command bar, and toolbar feature comparisons or migration scenarios.OtherNo warnings★ 66↓ —
- mcd-saver-strategisthujjun/mcd-saver-strategist麦门省钱精算师。当用户在麦当劳（麦当劳/麦麦/金拱门/麦乐送/到店取餐）点餐，并希望"最省钱、凑满减、把优惠券用到极致、性价比最高、在预算内吃好"时使用；也适用于"帮我看看这些券怎么用最划算""我想吃XX但想便宜点""30块钱能吃到什么"这类诉求。它通过麦当劳 MCP 拉取门店菜单、可用优惠券、营养信息，再用确定性组合优化算法穷举出总价最低的合规点餐方案，并在用户确认后下单。OtherNo warnings★ 1.5K↓ —
- cipp-opsWYRE-AI/msp-claude-pluginsCIPP's own operational layer rather than the tenants it manages: GDAP role definitions and pending invites, the CIPP scheduler, and the ping/version/log endpoints used to diagnose why other CIPP tools fail silently.OtherNo warnings★ 52↓ —
- Nutanix VM ManagementWYRE-AI/msp-claude-pluginsWorking the vmm namespace through `vmm_execute`: VM inventory and lookup on AHV clusters, resolving names to extId UUIDs, reading VM configuration (disks, NICs, GPUs, power state), OData filters for VM queries, and the read-only boundaries around VM lifecycle actions.OtherNo warnings★ 52↓ —
- verify-thisOutlineDriven/outline-driven-developmentUse when a measurable claim needs before/after proof. Not for fact-checking or done-claim gating: use verify-both-ways or verification-before-completion.OtherNo warnings★ 55↓ —
- sanctions-screeninglawve-ai/awesome-legal-skillsComplete sanctions and export control analysis tool — individual designations, sectoral sanctions, dual-use goods, payment systems (SWIFT/USD), and extraterritorial regimes (EAR/ITAR/ FDPR US, ECL China). Triggers: "is X sanctioned?", "can I do business with X?", "can I sell Y to Z?", "pétrole Russie", "biens à double usage", "gel des avoirs", "sanctions internationales", "liste OFAC", "liste UE", "double usage", "embargo", "licence d'exportation", "SWIFT", "paiement en dollars", "US goods", "FDPR", "EAR", "ITAR", "BIS", "ECL chine", "no re-export clause", "sanctions sectorielles", "puis-je travailler avec X?", or any transaction involving a foreign person, product, sector, destination country, or payment in USD/EUR. Always adapt to user profile. Always run for any sanctions or export control query — even vague or exploratory ones.OtherNo warnings★ 911↓ —
- 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↓ —
- ca-adr-statusarbiterForge/codeArbiterInspect ADR health read-only; optionally select one ADR with --adr N.OtherNo warnings★ 149↓ —
- 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
- lobAnil-matcha/awesome-muse-connectorsPrint and mail physical letters and postcards through Lob, verify US addresses, and cancel pieces before production. Trigger phrases: lob, send postcard, send letter, direct mail, print and mail.OtherNo warnings★ 1.4K↓ —
- final-grainOutlineDriven/outline-driven-developmentUse when asked to push an already-working artifact to finished composition, texture, and feel. Not for remote or irreversible changes. Not for hygiene routing: use clean-and-true.OtherNo warnings★ 55↓ —
- skill-idTserenTserenov/FMT-exocortex-templateOne line — used in CLAUDE.md system-reminder and the skill catalog.OtherNo warnings★ 63↓ —
- decision-lifecyclearbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 149↓ —
- scenario-godot-gameplayUpdatedscenario-labs/skillsUse when building gameplay systems in Godot 4.7: enemy AI that patrols, chases and attacks, state machines, behavior trees (LimboAI), NavigationAgent3D pathfinding and avoidance for 100 to 1000 enemies, 'agents stack up' or 'path is empty', hitbox and hurtbox combat, fast bullets going through walls, save and load, inventory, quests, dialogue (Dialogue Manager), input remapping, procedural dungeons, or measuring agent counts and frame time headless.OtherNo warnings★ 1.2K↓ —
- simulink-sanitize-modelmatlab/simulink-agentic-toolkitSanitize and anonymize a Simulink model for external sharing. Use when stripping proprietary content, anonymizing block/signal names, removing metadata, or creating a shareable reproduction model for bug reports. Do NOT use for simply copying or sharing a model internally.OtherNo warnings★ 1.3K↓ —
- Inforcer Audit EventsWYRE-AI/msp-claude-pluginsInforcer's read-only record of changes and activity: searching and filtering auditEvents by type and date window (the search is account-wide — there is no tenant filter), enumerating the event-type catalog to build valid filters, and the continuationToken paging audit searches require.OtherNo warnings★ 52↓ —
- vdvTserenTserenov/FMT-exocortex-templateВДВ-скилл — генератор и аудитор описания стадийного процесса по 6 принципам Вход·Действие·Выход. Используй для построения описания нового процесса (/vdv build) или проверки готового описания (/vdv audit).OtherNo warnings★ 63↓ —
- Autotask Tool DiscoveryWYRE-AI/msp-claude-pluginsThe Autotask MCP lazy-loading pattern - four meta-tools (list_categories, list_category_tools, execute_tool, router) that expose the full 39+ tool catalog progressively instead of loading every tool schema upfront, plus the natural-language router for intent-based tool lookup.OtherNo warnings★ 52↓ —
- trendspygaahl/skillsFree Google Trends data - real-time trending topics and keyword analysis over time (interest over time, related queries, interest by region).OtherNo warnings★ 164↓ —
- Strix•CSRF 测试asdfgh1445/ctf-super-hubStrix CSRF 测试手册,覆盖 token 绕过、SameSite、CORS 误配与状态变更滥用;触发名:strix-csrfOtherNo warnings★ 840↓ —
- luna-chat-coderOsteoporosis/luna-chat-coderKeep repository development reliable from chat by using the sandbox work container first, recovering exact GitHub state, and using bounded Actions missions when normal sandbox or GitHub paths are insufficient.OtherNo warnings★ 67↓ —
- Keeper KSM Notation QueriesWYRE-AI/msp-claude-pluginsThe KSM notation string grammar accepted by `get_field`: the three-part `<record>/<type>/<field-path>` shape, the four field-path forms (plain, indexed, property, indexed-property), `field` vs `custom_field` vs `file` selectors, how the record segment is classified as a UID or a title, which characters the validator rejects outright, and how the returned value is masked.OtherNo warnings★ 52↓ —
- radargaliprandi/job-seekerRegisters the user on job platforms, configures alerts with profile keywords, sets up career site alerts (big tech + target companies), creates a Gmail filter to route alerts to a Job Alerts folder.OtherNo warnings★ 59↓ —
hume-ai
Anil-matcha/awesome-muse-connectors
OtherUpdated Oct 13, 2026
From the author
Hume AI Octave TTS and EVI speech-to-speech configs: synthesize speech and manage EVI configs. Trigger phrases: hume, hume ai, octave tts, EVI config.
Install
npx skills add Anil-matcha/awesome-muse-connectors --skill hume-ai -a claude-code
Installs to .claude/skills/hume-ai/ · 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
Runs bundled scriptsNo network use seenLicence: MIT
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 82
Security85
Provenance78
Maintenance100
Licence100
Adoption51
Files (2)
- SKILL.md
- bin/hume-ai.py