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.
49,492 skills from 2,391 repositories · updated 2 hours ago
10,571 skills
- gpio-baremetalOutlineDriven/outline-driven-developmentUse when configuring GPIO modes, alternate functions, pull resistors, or EXTI interrupts on STM32/nRF/ESP32-class MCUs. Not for register access rules: use mmio-and-bit-manipulation.OtherNo warnings★ 55↓ —
- ca-adrarbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 151↓ —
- cxc-looplidge-jun/codexclawUse for PABCD completion loops. Triggers: cxc-loop, continue until done, HOTL, repeated PABCD, 루프 돌려, 끝까지 해줘, docs-first.OtherNo warnings★ 52↓ —
- go-rust-reversecoco-research/cocoUse for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.OtherNo warnings★ 797↓ —
- Ticket TriageWYRE-AI/msp-claude-pluginsVendor-agnostic PSA ticket triage: priority determination, categorization, routing, and initial response practices applicable to Autotask, ConnectWise, HaloPSA, and other platforms.OtherNo warnings★ 52↓ —
- 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↓ —
- screenshot-critiquedzhng/skillsUse the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.OtherNo warnings★ 1.4K↓ —
- corrections-audithaabe/myceliumUse to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.OtherNo warnings★ 51↓ —
- diamond-assesshaabe/myceliumUse to evaluate the current state of a diamond. Checks theory gates, confidence levels, and recommends next action.OtherNo warnings★ 51↓ —
- metrics-detecthaabe/myceliumDetect which external metric sources apply to this product (GitHub, Plausible, Stripe, etc.) and configure adapters. Retrofit entry point for projects that started before v0.14; also runnable to refresh source list when the product grows.OtherNo warnings★ 51↓ —
- service-checkhaabe/myceliumUse to evaluate a service or feature against Downe's 15 principles of good services.OtherNo warnings★ 51↓ —
- metrics-pullhaabe/myceliumPull snapshots from all configured metric sources, compute deltas against prior snapshots, flag unexplained signals, and draft evidence entries for canvas files. One entry point for all external product/market metrics.OtherNo warnings★ 51↓ —
- deepline-triageNewgetaero-io/gtm-eng-skillsDiagnose failing, stuck, partial, or incorrect Deepline Plays, including when no Play is named. Use deepline-gtm for the primitives, reproduce safely, propose an evidence-backed fix, and apply it after approval. For customer troubleshooting; skip platform incident response.OtherNo warnings★ 73↓ —
- bvssh-checkhaabe/myceliumUse to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.OtherNo warnings★ 51↓ —
- Autotask Service CallsWYRE-AI/msp-claude-pluginsAutotask Service Call data model - the ServiceCall / ServiceCallTicket / ServiceCallTicketResource three-layer structure - covering fields, status codes, and how tickets and technicians (resources) are linked to scheduled work.OtherNo warnings★ 52↓ —
- NinjaOne DevicesWYRE-AI/msp-claude-pluginsNinjaOne device management: device details and updates, Windows service control, inventory, maintenance windows, reboot modes, and health-check workflows for Windows, Mac, and Linux endpoints running the NinjaRMM agent.OtherNo warnings★ 52↓ —
- 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↓ —
- Liongard EnvironmentsWYRE-AI/msp-claude-pluginsLiongard environments — the per-customer containers that own all agents, launchpoints, systems, detections, and metrics. Covers environment CRUD, the lightweight count endpoint, v2 environment groups, tiering, related-entity lookups, and integration mappings to PSA/RMM platforms.OtherNo warnings★ 52↓ —
- Crewhu SurveysWYRE-AI/msp-claude-pluginsCrewhu CSAT/NPS survey data: the list/search/get tools and the detractor/promoter sentiment slices, the trend, detractor-follow-up, promoter-recognition and per-tech roll-up workflows, and the edge cases that skew scores — sparse response counts, comment-only feedback, and tenant-local timestamps.OtherNo warnings★ 52↓ —
- Axcient VaultsWYRE-AI/msp-claude-pluginsAxcient x360Recover vaults: Private vs Cloud vault types, storage capacity, and the connectivity-loss alert threshold — including axcient_set_vault_threshold, the one tool in this plugin that changes alerting configuration rather than just reading it.OtherNo warnings★ 52↓ —
- Auvik AlertsWYRE-AI/msp-claude-pluginsAuvik alerts: severity tiers, status lifecycle, dismissal semantics, and the common alertName patterns that show up in MSP NOC queues.OtherNo warnings★ 52↓ —
- jtbd-maphaabe/myceliumMap the Jobs to be Done (functional, emotional, and social) that people are trying to get done. Based on Christensen's JTBD theory — applies to any object, not only software.OtherNo warnings★ 51↓ —
- cxc-skill-hublidge-jun/codexclawDeprecated alias. Use cxc-dev.OtherNo warnings★ 52↓ —
- Rootly On-CallWYRE-AI/msp-claude-pluginsRootly on-call visibility built on the get_oncall_handoff_summary, get_oncall_shift_metrics, get_shift_incidents, and check_oncall_health_risk tools: schedule and rotation coverage, structured shift handoffs, per-shift incident scoping, shift metric fields, and the burnout risk signals.OtherNo warnings★ 52↓ —