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 5 hours ago
9,541 skills
- 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↓ —
- binutilsOutlineDriven/outline-driven-developmentUse when building static archives with ar, stripping or converting binaries, mapping crash addresses with addr2line, or demangling C++ symbols. Not for ELF analysis: use elf-inspection.OtherNo warnings★ 55↓ —
- linearAnil-matcha/awesome-muse-connectorsWork with Linear: view your assigned issues and create issues. Trigger phrases: linear, linear issue, ticket.OtherNo warnings★ 1.4K↓ —
- principlesOutlineDriven/outline-driven-developmentUse when a request names a working principle (subtract before you add, idempotent operations, never block on the human) or asks which principle applies. Not for running a repair: use strike-the-root.OtherNo warnings★ 55↓ —
- sparse-autoencoder-trainingKalarisLabs/research-agent-skillsProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.OtherNo warnings★ 76↓ —
- featurecounts-rna-countingjaechang-hits/SciAgent-SkillsCounts RNA-seq reads overlapping GTF gene features. Takes sorted STAR BAMs plus GTF; outputs a per-gene tab-delimited matrix across samples. Handles strandedness (0/1/2), paired-end, multi-sample batch counting in one command, and outputs assignment statistics. Use Salmon for alignment-free quantification; use featureCounts when STAR BAMs already exist.OtherNo warnings★ 384↓ —
- watch-forOutlineDriven/outline-driven-developmentUse when monitoring a file, log, endpoint, or artifact for drift or errors, or polling a target until a predicate holds. Modes: watch (default), until. Not for source or remote-system changes.OtherNo warnings★ 55↓ —
- cross-gccOutlineDriven/outline-driven-developmentUse when compiling for ARM, AArch64, RISC-V, or MIPS from x86-64 with a GCC cross toolchain: triplets, sysroots, pkg-config, CMake toolchain files, QEMU. Not for Zig: use zig-cross.OtherNo warnings★ 55↓ —
- ste-koreanOutlineDriven/outline-driven-developmentUse when Korean tech docs need unofficial ASD-STE controlled wording, single-step procedures, unified terms; not for plain readability (use plain-korean), official or English STE.OtherNo warnings★ 55↓ —
- cpp-modulesOutlineDriven/outline-driven-developmentUse when a C++ project adopts C++20 modules: named modules, partitions, header units, the global module fragment, CMake CXX_MODULES, or a BMI lookup error. Not for flag basics: use clang.OtherNo warnings★ 55↓ —
- flamegraphsOutlineDriven/outline-driven-developmentUse when turning perf, DTrace, pprof, or async-profiler stacks into an SVG flamegraph with the FlameGraph scripts, reading one, or diffing two profiles. Not for collecting data: use linux-perf.OtherNo warnings★ 55↓ —
- 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↓ —
- Microsoft 365 TeamsWYRE-AI/msp-claude-pluginsMicrosoft Teams through Microsoft Graph: the Team/Channel/Member/Meeting/Tab object model, team and channel enumeration, membership and ownership changes, online meetings, usage reporting, and the causes behind Teams access failures.OtherNo warnings★ 52↓ —
- gsd-helpcoco-research/cocoUse when the user asks what GSD commands exist or how to use GSD. Outputs the complete GSD command reference verbatim, with no project analysis, status, or next-step suggestions.OtherNo warnings★ 795↓ —
- Microsoft 365 UsersWYRE-AI/msp-claude-pluginsThe Entra ID user object as M365's central identity: key properties and their MSP relevance, account status values, the license assignment model, Graph patterns for listing/searching/creating/disabling users, MFA status checking, and the onboarding and offboarding sequences.OtherNo warnings★ 52↓ —
- Clio MattersWYRE-AI/msp-claude-pluginsClio matters -- the case/client-file object that almost everything else in Clio hangs off of: the matter status lifecycle, linking a matter to a client contact, practice areas, custom fields, and matter numbering.OtherNo warnings★ 52↓ —
- cipp-tenantsWYRE-AI/msp-claude-pluginsThe top-level CIPP scope: enumerating managed M365 tenants, retrieving tenant detail, and the accepted `tenantFilter` identifier formats (default domain, custom domain, GUID, `allTenants`). Also covers stale-cache detection and the two common tenant-resolution failure modes.OtherNo warnings★ 52↓ —
- Clio ContactsWYRE-AI/msp-claude-pluginsClio contacts -- the people and companies connected to matters: person vs. company contact types, and how a contact relates to the matters they are party to (client, opposing party, witness, and other roles).OtherNo warnings★ 52↓ —
- Atera DevicesWYRE-AI/msp-claude-pluginsAtera device monitors: HTTP, SNMP, and TCP monitor types for network devices, services, and applications, plus monitor configuration, thresholds, and polling behavior.OtherNo warnings★ 52↓ —
- Auvik DevicesWYRE-AI/msp-claude-pluginsAuvik device records: device types, manageStatus and onlineStatus, lifecycle and warranty fields, and choosing between the v1 list endpoint and the detailed device endpoints.OtherNo warnings★ 52↓ —
- Atera TicketsWYRE-AI/msp-claude-pluginsAtera service desk tickets: ticket fields, statuses, priorities, comments, work hours, and billing duration.OtherNo warnings★ 52↓ —
- cipp-standardsWYRE-AI/msp-claude-pluginsCIPP's tenant-baseline enforcement model: the Report/Alert/Remediate standards modes and how to roll them out, on-demand standards evaluation, Best Practice Analyser reports, and SPF/DKIM/DMARC domain health results with their remediation actions.OtherNo warnings★ 52↓ —
- Autotask CRMWYRE-AI/msp-claude-pluginsAutotask CRM entities - companies (accounts), contacts, and sites/locations - including field references, company type classifications, and how these records underpin tickets, contracts, and projects for MSP account management.OtherNo warnings★ 52↓ —
- Domotz Power OutletsWYRE-AI/msp-claude-pluginsDomotz PDU and smart-outlet control: listing outlets and their power state, and the one non-GET tool the Domotz server exposes — switching an outlet on, off, or cycling it. Covers the confirm argument, why it is advisory, and the pre-flight checks that belong before a mains interruption.OtherNo warnings★ 52↓ —
motherduck-connect
motherduckdb/agent-skills
OtherUpdated 4 days ago
From the author
Set up or troubleshoot MotherDuck connections, the MotherDuck MCP server in AI clients, authentication, client runtimes, and read scaling.
Install
npx skills add motherduckdb/agent-skills --skill motherduck-connect -a claude-code
Installs to .claude/skills/motherduck-connect/ · 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 (4)
- SKILL.md
- references/CONNECTION_GUIDE.md
- references/MCP_SETUP.md
- references/RUNTIME_SELECTION.md