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 22 minutes ago
9,543 skills
- scenario-maya-riggingscenario-labs/skillsUse when rigging a character, creature or prop in Maya: "rig this character", placing or orienting joints, Orient Joint doing nothing, IK/FK switch and matching, pole vector flips or elbow drift, space switching, foot roll, spline IK spine, offsetParentMatrix, blendMatrix or matrix rigging, controls and lockdown for animators, Quick Rig, HumanIK, AdvancedSkeleton or mGear, a game skeleton for Unreal or Unity, or a slow rig (parallel evaluation, profiling, GPU Override not kicking in).OtherNo warnings★ 1.2K↓ —
- scenario-blender-hairscenario-labs/skillsUse when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games. Also covers the Essentials hair node assets (Interpolate, Clump, Curl, Frizz, Noise, Trim), density masks, bald spots, parting lines, strand shading in Cycles or EEVEE, and slow grooms. Use it too when a hair script misbehaves headless, for example stale modifier inputs or curve sculpt brushes that do nothing.OtherNo warnings★ 1.2K↓ —
- ConnectWise Automate MonitorsWYRE-AI/msp-claude-pluginsConnectWise Automate monitor management: monitor types (internal, remote, agent, SNMP, script), categories, threshold configuration, templates, assignment methods (computer/group/client), and status evaluation.OtherNo warnings★ 52↓ —
- Huntress EscalationsWYRE-AI/msp-claude-pluginsHuntress SOC escalations: how an escalation differs from an incident, escalation priority levels, the list/get/resolve tools, escalation-to-incident correlation, and the already-resolved and not-found error cases.OtherNo warnings★ 52↓ —
- Inforcer AssessmentsWYRE-AI/msp-claude-pluginsInforcer assessments: listing a tenant's assessments (read-only) and triggering an assessment run — the one mutating action in the entire Inforcer surface. Covers what a run refreshes (the data behind alignment, secure score, and drift), its tenant-scoping, and the confirmation discipline it requires.OtherNo warnings★ 52↓ —
- agent-relayAgentWorkforce/relayUse when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and terminals.OtherNo warnings★ 1.1K↓ —
- scenario-roblox-gameplayscenario-labs/skillsUse when building Roblox gameplay systems: NPC or enemy AI that patrols, chases and attacks, state machines or behavior trees, 'NPC pathfinding stuck', 100 zombies lag the server, hitboxes, melee combos, M1 combat, 'hits register twice', raycasts, Spherecast, Shapecast, guns and projectiles, 'bullets go through walls', knockback and stun, LinearVelocity, VectorForce or AlignPosition movers, replacing BodyVelocity, cars and vehicles with suspension, 'car flips', VehicleSeat, network ownership of NPCs and vehicles, round loops, BindToSimulation logic.OtherNo warnings★ 1.2K↓ —
- gsd-list-workspacescoco-research/cocoUse when the user asks which GSD workspaces exist, or where their isolated work lives. Scans the workspaces root for WORKSPACE.md manifests and prints name, path, repo count, strategy and project status.OtherNo warnings★ 795↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- 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↓ —
- SalesBuildr QuotesWYRE-AI/msp-claude-pluginsSalesbuildr quotes: quote creation with product line items, quote search, and retrieving quote details, plus how quotes link to companies, contacts, and opportunities.OtherNo warnings★ 52↓ —
- m5-onboardthevibeworks/claude-code-docsEnd-to-end onboarding for a freshly-plugged-in M5Stack ESP32 device (Cardputer, Cardputer-Adv, Core, CoreS3, Stick) — detect on USB, flash UIFlow 2.0 firmware, and install the Claude Buddy MicroPython app bundle. Use whenever the user plugs in or wants to flash/provision/reset an M5Stack or ESP32 board, or says "m5-onboard go".OtherNo warnings★ 165↓ —
- tribunalarbiterForge/codeArbiterRun an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.OtherNo warnings★ 149↓ —
- 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↓ —
- 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-checkpointarbiterForge/codeArbiterPeriodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report.OtherNo warnings★ 149↓ —
- ca-overridearbiterForge/codeArbiterSanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.OtherNo warnings★ 149↓ —
- Dispatch PrioritizationWYRE-AI/msp-claude-pluginsPriority scoring and assignment for an unassigned PSA ticket queue: the scoring factors (SLA proximity, client tier, ticket age, technician load, skill/category match), how to combine them into an explainable ranked order rather than a black-box formula, and the tool-discovery pattern for finding which PSA and RMM connectors are actually live before calling any vendor's tools.OtherNo warnings★ 52↓ —
- Better Stack IncidentsWYRE-AI/msp-claude-pluginsBetter Stack incidents: incident records raised by uptime monitors or reported manually, and the triage, acknowledgment, and resolution lifecycle.OtherNo warnings★ 52↓ —
- relic-talkYlsssq926/relic.skillSoul Engine — Bring an awakened Relic alive for conversation. Trigger on /relic-talk, or when user wants to talk to, chat with, or invoke a Relic ("talk to grandma", "chat with Mimi", "跟XX聊天", "召唤XX", "让XX回我").OtherNo warnings★ 73↓ —
- consciousness-councilKalarisLabs/research-agent-skillsRun a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, needs help making a tough decision, asks for a council/panel/board discussion, wants to explore a problem from multiple angles, requests devil's advocate analysis, or says things like "what would different experts think about this", "help me think through this from all sides", "council mode", "mind council", or "deliberate on this". Also trigger when the user faces a dilemma, trade-off, or complex choice with no obvious answer.OtherNo warnings★ 76↓ —
- scenario-zbrush-sculptingscenario-labs/skillsUse when an agent sculpts organic forms in ZBrush 2026 (sculpt a head, bust or creature in ZBrush from a sphere, ZSpheres or primitives); when blocking primary and secondary forms, choosing DynaMesh, Sculptris Pro or subdivision levels, or setting ClayBuildup, Dam_Standard, Move or TrimDynamic; when using masks, polygroups, Morph Targets or layers; or when scripted strokes miss, do nothing, come out too strong or leave marks, or a re-DynaMesh does nothing or loses polygroups.OtherNo warnings★ 1.2K↓ —
punct-polish
taxueseek/plainspoken-writing
OtherUpdated 6 days ago
From the author
【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"。
Install
npx skills add taxueseek/plainspoken-writing --skill punct-polish -a claude-code
Installs to .claude/skills/punct-polish/ · 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/ai-common-mistakes.md
- references/en-copyedit.md
- references/scene-rules.md