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 6 hours ago
9,541 skills
- cesiumjs-viewer-setupCesiumGS/cesiumjs-skillsCesiumJS viewer setup - Viewer, CesiumWidget, widgets, Ion token, Scene configuration, SceneMode, factory helpers, geocoders, platform services. Use when initializing a CesiumJS application, configuring viewer widgets, setting Ion access tokens, creating default terrain or imagery, or bootstrapping a 3D globe.OtherNo warnings★ 193↓ —
- find-skillsnaveedharri/benai-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.OtherNo warnings★ 76↓ —Also in 2 other repos
- recallOutlineDriven/outline-driven-developmentUse when asked to recover prior work and current status before resuming. Not for handoff snapshots: use handoff. Not for source or remote-system changes.OtherNo warnings★ 55↓ —
- motherduck-connectmotherduckdb/agent-skillsSet up or troubleshoot MotherDuck connections, the MotherDuck MCP server in AI clients, authentication, client runtimes, and read scaling.OtherNo warnings★ 62↓ —Also in 1 other repo
- pm-1on1sborghei/Claude-SkillsStructured PM 1:1 templates by partner type — manager, engineering-manager partner, designer, IC reports, cross-functional — grounded in Radical Candor, the GROW coaching model, and the Manager Tools 1:1 framework.OtherNo warnings★ 1K↓ —
- laya-integrationwdobry/laya-playgroundAdd fast, local, typed decisions to any project with Laya, an open-source non-generative decision model (pip install laya). It classifies, routes, scores and answers yes/no questions about a piece of text, returning calibrated probabilities in roughly 20-35 ms on a laptop GPU, with no LLM call and no data leaving the machine. Use this skill whenever the user wants to classify or route text, triage tickets or emails, detect spam, phishing, toxicity or intent, put a guardrail in front of an agent or LLM, score something against a rubric, or replace an LLM-based classifier to cut latency or cost. Also use it when they mention Laya, Jev, a "System 1 model", "typed decisions" or a "decision model", even if they never name Laya.OtherNo warnings★ 192↓ —
- ConnectWise Automate AlertsWYRE-AI/msp-claude-pluginsConnectWise Automate alert management: alert sources (monitors, scripts, events), severity levels, lifecycle states, acknowledgment, resolution, history tracking, and PSA ticket creation from alerts.OtherNo warnings★ 52↓ —
- Axcient DevicesWYRE-AI/msp-claude-pluginsAxcient x360Recover protected devices (servers and workstations): SERVER/WORKSTATION typing, the current/previous health-status model, local vs vault vs cloud usage and recovery-point timestamps, AutoVerify screenshot verification, and restore points.OtherNo warnings★ 52↓ —
- msvc-clOutlineDriven/outline-driven-developmentUse when building C or C++ on Windows with cl.exe or clang-cl: GCC-to-MSVC flag translation, /MT versus /MD, PDB output, or an LNK error. Not for MinGW cross builds from Linux: use cross-gcc.OtherNo warnings★ 55↓ —
- lov-media-acquisitionlovstudio/skillsUse when a selected media release must be downloaded, raced, resumed, or recovered. 通过 aria2 默认执行容量预检、候选测速、持续观测与慢源切换；适用于“开始下载，太慢就换源”。OtherNo warnings★ 73↓ —
- motherduck-exploremotherduckdb/agent-skillsFind and understand MotherDuck databases, tables, columns, shares, and sample data, including which tables hold a given kind of data. Use first when a MotherDuck workspace or schema is unfamiliar.OtherNo warnings★ 62↓ —Also in 1 other repo
- 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↓ —
- goalcoco-research/cocoPersistent project goal that survives across sessions and tools, with continuous-execution loop semantics. Use when someone asks to "set a goal", "what is my goal", "goal status", "keep working on X until done", "resume the goal", or wants work to continue across sessions until an objective is achieved. File-backed (.goal.md at project root); shared by every Coco-installed tool working in that repository.OtherNo warnings★ 795↓ —
- muyang-print-posteryokel1121/muyang-illustration-skills风格包含：复古剪影插画、复古电影插画、日式版画插画。用于收集用户指定的主体和具体风格，将主体原样填入对应固定配方并直接生成图片；不得展示提示词、扩写或改变色数。OtherNo warnings★ 213↓ —
- 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↓ —
- muyang-cinematic-narrativeyokel1121/muyang-illustration-skills风格包含：清冷夏日插画、童话巨宠插画。用于收集用户指定的主体和具体风格，将主体原样填入对应固定配方并直接生成图片；不得展示提示词、扩写动作、场景或叙事。OtherNo warnings★ 213↓ —
- weights-and-biasesKalarisLabs/research-agent-skillsLogs and tracks machine learning experiments with Weights & Biases (W&B, wandb): metrics, hyperparameters, checkpoints, sweeps, artifacts with lineage, model registry, custom charts and shareable reports. Includes integrations for PyTorch, HuggingFace Transformers, PyTorch Lightning and Keras/TensorFlow. Use when logging training runs and comparing them across configurations, running automated hyperparameter sweeps, versioning datasets and models as artifacts, registering model versions, or sharing results with a team workspace. Use when setting up wandb.init for offline or unstable-connection training. Not for general data versioning outside ML runs.OtherNo warnings★ 76↓ —
- evolving-ai-agentsKalarisLabs/research-agent-skillsProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.OtherNo warnings★ 76↓ —
- muyang-fashion-colorblockyokel1121/muyang-illustration-skills风格包含：蓝白时尚插画、韩系蓝白插画、黄黑撞色插画、粉蓝撞色插画。用于收集用户指定的主体和具体风格，将主体原样填入对应固定配方并直接生成图片；不得展示提示词、扩写、改写或混合风格。OtherNo warnings★ 213↓ —
- scenario-blender-texturing-shadingUpdatedscenario-labs/skillsUse when texturing, shading or look-developing in Blender: building a PBR material from a texture set, displacement, procedural materials, edge wear, dirt, grime, color variation, decals, box or triplanar mapping on meshes without UVs, stylized character skin (subsurface, pores), eyes and cornea, hand-painted stylized textures, texture painting or painting masks headless. Also when a material looks plastic, CG, waxy or blown out, color spaces are wrong, or EEVEE and Cycles disagree.OtherNo warnings★ 1.2K↓ —
- 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↓ —
- teachdsebban/skillsExplain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.OtherNo warnings★ 69↓ —
- messagingmatteotitta/repo-structure-in-houseBuilds a product messaging library from your positioning, your website and customer evidence: a description, the status quo and alternatives, pain points with their knock-on consequences, capabilities, functional, emotional and social benefits, branded features, the cost of doing nothing, common objections with responses, and core messaging blocks (tagline, elevator pitch, value props, proof, per-audience lines). Every claim sourced. Triggers: "product messaging", "messaging library", "messaging framework", "value props", "capabilities and benefits", "what are our differentiators in words". Run after /positioning. Not for choosing the position itself (use /positioning).OtherNo warnings★ 70↓ —
roadrunner-convert-lanelet2-to-rrhd
matlab/matlab-agentic-toolkit
OtherUpdated 3 days ago
From the author
Convert Lanelet2 maps (.osm) to RoadRunner HD Map (.rrhd) format using MATLAB. Use when converting Lanelet2 maps into RoadRunner Scene Builder, building driving scenes from open-source map data, or transforming road network definitions for simulation.
Install
npx skills add matlab/matlab-agentic-toolkit --skill roadrunner-convert-lanelet2-to-rrhd -a claude-code
Installs to .claude/skills/roadrunner-convert-lanelet2-to-rrhd/ · Each command fetches the skill straight from GitHub with the open skills CLI.
No download: this skill’s licence (Custom or unclear) does not let us redistribute its files. The install commands fetch them from GitHub instead.
What it can touch
Instructions onlyNo network use seenLicence: Custom or unclear
Safety checks on SKILL.md
No warnings.
Why 82
Security100
Provenance77
Maintenance100
Licence45
Adoption50
Files (22)
- SKILL.md
- manifest.yaml
- references/buildRRHD.md
- references/detectGeoReference.md
- references/discoverRelations.md
- references/enforcementGate.md
- references/extractGeometry.md
- references/extractJunctions.md
- references/extractLanelets.md
- references/extractNonLaneElements.md
- references/extractSemantics.md
- references/extractTopology.md
- +10 more