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.
46,095 skills from 2,198 repositories · updated 4 minutes ago
9,543 skills
- USDCtoFiat Cash-Outagentskillexchange/skillsAdd non-custodial Base USDC-to-fiat cash-out with @usdctofiat/offramp cashout({ mode: "fast" | "best" }). Use when an agent must sell USDC from a real viem WalletClient into Venmo, Cash App, Revolut, PayPal, Zelle, Monzo, or Chime without an exchange account.OtherNo warnings★ 58↓ —
- maintain-verification-skilldsebban/skillsPeriodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /skill:maintain-verification-skill or "audit the verify skill".OtherNo warnings★ 69↓ —
- homeyAnil-matcha/awesome-muse-connectorsRead and control devices on a Homey Pro hub or Homey cloud account: lights, thermostats, locks, blinds, Flows. Trigger phrases: homey, homey pro, homey flow, athom.OtherNo warnings★ 1.4K↓ —
- schemafcakyon/claude-codex-settingsUse when adding, fixing, or reviewing structured data: JSON-LD for articles, products, FAQs, breadcrumbs, organizations, and local businesses, and what to do when markup doesn't earn a rich result.OtherNo warnings★ 1.2K↓ —
- dsh-marker-readeralibaba/skill-upDecode the marker fixture used by the DeepSeek Harness integration example.OtherNo warnings★ 1.4K↓ —
- mock-enginealibaba/skill-upAn evaluation and evolution tool for Agent Skills.OtherNo warnings★ 1.4K↓ —
- oma-backendfirst-fluke/oh-my-agentImplement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.OtherNo warnings★ 1.4K↓ —
- onboardOutlineDriven/outline-driven-developmentUse when the user asks for onboarding, orientation, a repository tour, or where to start. Produces an evidence-backed seven-section map, deep-reads real files, and asks for the next move.OtherNo warnings★ 55↓ —
- NinjaOne TicketsWYRE-AI/msp-claude-pluginsNinjaOne's built-in ticketing system, which integrates with device monitoring: ticket creation and updates, core/status/metadata fields, status and priority values with SLA targets, log entry types, device linkage, tagging patterns, and error codes.OtherNo warnings★ 52↓ —
- principle-explain-the-numberdsebban/skillsApply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.OtherNo warnings★ 69↓ —
- benchmark-checklistdsebban/skillsVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.OtherNo warnings★ 69↓ —
- Blumira MSPWYRE-AI/msp-claude-pluginsBlumira's MSP path group (`/msp/*`): managed-account enumeration, cross-account and per-account finding queries, per-account device, agent-key and user management, and how MSP paths differ from org paths.OtherNo warnings★ 52↓ —
- reorderOutlineDriven/outline-driven-developmentUse when asked to reorder a drifted listing under one stated principle, moving items only and rewording nothing. Not for deliberately ranked listings: use reorder-respect-deliberate.OtherNo warnings★ 55↓ —
- in-your-own-wordsdsebban/skillsRestate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /skill:in-your-own-words.OtherNo warnings★ 69↓ —
- automate-medsebban/skillsUse for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via the authoring-a-skill playbook + unslop, optionally pulling fresh evidence from recent session history.OtherNo warnings★ 69↓ —
- no-commentsdsebban/skillsSpawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.OtherNo warnings★ 69↓ —
- Keeper Secret DiscoveryWYRE-AI/msp-claude-pluginsLocating the right Keeper record without reading any of them: the metadata returned by `list_secrets`, `search_secrets` and `list_folders`, how record UIDs, titles and folders relate, what `search_secrets` actually matches on (and what it silently does not), the query strings its validator rejects, and why an empty result set usually means scope rather than absence.OtherNo warnings★ 52↓ —
- smartthingsAnil-matcha/awesome-muse-connectorsRead status and send commands to Samsung SmartThings devices: lights, locks, thermostats, sirens, garage doors. Trigger phrases: smartthings, samsung smart home, unlock the door, smartthings thermostat.OtherNo warnings★ 1.4K↓ —
- philips-hueAnil-matcha/awesome-muse-connectorsControl Philips Hue lights locally: list lights and rooms, set brightness/color, activate scenes, read sensors. Trigger phrases: philips hue, hue lights, my lights.OtherNo warnings★ 1.4K↓ —
- io-uringOutlineDriven/outline-driven-developmentUse when building Linux servers with liburing, batching SQEs, multi-shot operations, provided buffer rings, registered files and buffers, or zero-copy send. Not for packet I/O: use af-xdp.OtherNo warnings★ 55↓ —
- constitutional-aiKalarisLabs/research-agent-skillsAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.OtherNo warnings★ 76↓ —
- calendlyAnil-matcha/awesome-muse-connectorsRead and manage Calendly: list scheduled events, event types, invitees, and availability schedules; cancel bookings. Trigger phrases: calendly, my meetings, scheduled events, cancel booking.OtherNo warnings★ 1.4K↓ —
- punct-polishtaxueseek/plainspoken-writing【标点打磨】AI写中文最常见的毛病就是标点：半角逗号、缺少中西空格、直引号、破折号滥用……这个技能一次性解决。覆盖中文散文、技术文档、中英混排、社交媒体四种场景，代码和URL完全不动，还具备英文标点校对能力。 触发：检查标点、修正标点、标点有问题、标点规范、半角改全角、中西空格、标点符号检查、punctuation、fix punctuation。 Not for：纯英文文本校对（→ 英文编辑工具）、纯代码文件、用户明确说"不要改标点"。OtherNo warnings★ 68↓ —
- Human Risk ScoringWYRE-AI/msp-claude-pluginsExplainable per-user and per-org human risk scoring from training-completion status, phishing-simulation failure history, and optional real-world click/attack-targeting signal: the weighted factor table, three-tier bucketing, per-org rollup as a distribution rather than a blended number, and graceful degradation when only some inputs are connected.OtherNo warnings★ 52↓ —
motherduck-load-data
motherduckdb/agent-skills
OtherUpdated 4 days ago
From the author
Load files, object storage, dataframes, or external databases into MotherDuck with bulk ingestion. Use for any import of data into MotherDuck.
Install
npx skills add motherduckdb/agent-skills --skill motherduck-load-data -a claude-code
Installs to .claude/skills/motherduck-load-data/ · 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 (2)
- SKILL.md
- references/INGESTION_PATTERNS.md