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.
47,966 skills from 2,309 repositories · updated 6 hours ago
47,966 skills
- game-aigamedev-skills/awesome-gamedev-agent-skillsDesign NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A* pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state machine, behavior tree, blackboard, A*, navmesh, seek, or patrol/chase.DesignNo warnings★ 5.8K↓ —
- api-fuzzing-bug-bountyzebbern/claude-code-guideThis skill should be used when the user asks to "test API security", "fuzz APIs", "find IDOR vulnerabilities", "test REST API", "test GraphQL", "API penetration testing", "bug bounty API testing", or needs guidance on API security assessment techniques.EngineeringNo warnings★ 4.7K↓ —
- designlang-tokensManavarya09/design-extractUse when styling UI for postman.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.DesignNo warnings★ 4.4K↓ —
- code-testingdotnet/skillsALWAYS USE for test work that requires changes: write, add, generate, repair, or strengthen tests for existing code in xUnit, MSTest, NUnit, pytest, Vitest/Jest, Go, or another framework. Includes regression cases, failing or flaky tests, coverage-driven additions, and audit-then-fix requests. Focused work stays direct; broad or multi-stage work invokes test-engineer. DO NOT USE for only running tests, analysis-only audits, framework/platform migrations, a test blocked on a missing production seam (testability-obstacle), or MSTest API/configuration corrections that do not design new cases (writing-mstest-tests). Within an active test-engineer pipeline, reuse supplied guidance and do not re-enter this skill.TestingNo warnings★ 5.8K↓ —
- designlang-tokensManavarya09/design-extractUse when styling UI for mintlify.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.DesignNo warnings★ 4.4K↓ —
- genvm-lintinternet-court/internet-court-skillValidate GenLayer intelligent contracts with the GenVM linter.OtherNo warnings★ 7K↓ —
- cue-kind-definitiongrafana/skillsAuthor CUE kind definitions for grafana-app-sdk apps - schemas, versioning, field constraints, named type definitions, custom routes, and codegen configuration. Scaffolds kinds via `grafana-app-sdk project kind add`, writes spec/status schemas with type constraints (regex, enum, range), defines `#`-prefixed named types for reusable structs, registers versions in the app manifest, and runs `grafana-app-sdk generate` with explicit error recovery. Use when working with CUE kinds, adding a new resource type, adding a version to an existing kind, writing schema field constraints, defining `#Definition` types, adding custom routes, editing files under `kinds/`, or when the user asks to "model a resource", "add a CUE schema", or "write a kind" — even without saying "CUE" explicitly.OfficialWritingNo warnings★ 297↓ —
- godot-3d-essentialsgamedev-skills/awesome-gamedev-agent-skillsSet up a Godot 4.7 3D scene: Node3D transforms, Camera3D, lighting (DirectionalLight3D/OmniLight3D), WorldEnvironment for sky/ambient/tonemap/post, MeshInstance3D materials, and GridMap for tile-based 3D levels. Use when building a 3D scene in a Godot project, placing cameras/lights, configuring environment and post-processing, or working with Node3D/.tscn 3D content and GridMap.OtherNo warnings★ 5.8K↓ —
- test-gap-analysisdotnet/skillsFind caller-visible production changes existing tests would miss through pseudo-mutation analysis; verify candidates or close gaps only when requested. Includes read-only per-test composition for grading. Polyglot. USE FOR: would tests catch a bug, behavioral blind spots, surviving mutations. DO NOT USE FOR: concrete fix/feature revision proof (test-value-evidence); suite taxonomy (test-tagging); .NET coverage, Cobertura, plateaus or coverage-backed priorities (coverage-analysis); named CRAP (crap-score); new suites (code-testing); assertion/smell audits; mutation tools.TestingNo warnings★ 5.8K↓ —
- okx-dex-marketinternet-court/internet-court-skillHARD BLOCK — never use for prediction-market/Polymarket UpDown queries; route to okx-dapp-discovery when a named DApp (Polymarket/Aave/Hyperliquid/PancakeSwap/Morpho) appears with a timeframe, or 涨跌/updown for BTC/ETH/SOL/XRP/BNB/DOGE/HYPE. Otherwise, read-only on-chain DEX data, 6 groups: TOKEN (search, hot/热门, liquidity, holders/whale, risk metadata, cluster/持仓集中度, trade history, top traders); MARKET (price/价格, K线/OHLC, index price, wallet PnL/胜率, trade history); SIGNAL (smart money/KOL/whale tracking, buy signals/信号, leaderboard/牛人榜); SOCIAL (news/新闻, sentiment/情绪, token vibe/热度, KOL leaderboard); TRENCHES (pump.fun/meme launches/新盘/扫链, dev reputation, bundle/sniper detection/捆绑狙击者, co-investor — read-only; buy/snipe → okx-dapp-discovery); WS (onchainos ws CLI, or custom WebSocket script/脚本). Also owns Market API payment/x402, quota/额度, and MARKET_API_*_OVER_QUOTA/confirming:true for all 6 groups.FinanceNo warnings★ 7K↓ —
- survival-craftinggamedev-skills/awesome-gamedev-agent-skillsBuild a survival-crafting game: resource gathering, inventory, crafting and a tech tree, needs (hunger/thirst/temperature), and base building. Use for a survival or crafting/base-building game.OtherNo warnings★ 5.8K↓ —
- vectorizationdotnet/skillsDesign, implement, optimize, and review SIMD code in .NET. USE FOR: vectorizing scalar loops with TensorPrimitives, Vector64/128/256/512, or platform hardware intrinsics; reviewing existing SIMD code, including the generic Vector type, for contract equivalence, tail handling, memory safety, portability, fallbacks, and measured performance. DO NOT USE FOR: performance work unrelated to SIMD or vectorization.DesignNo warnings★ 5.8K↓ —
- roblox-uigamedev-skills/awesome-gamedev-agent-skillsBuild production Roblox interfaces with ScreenGui/PlayerGui lifecycle, responsive UDim2 layouts, safe insets, reusable editable Instances, cross-device input and selection, restrained motion, cleanup, and multi-viewport verification. Use for Roblox HUDs, inventories, shops, settings, ability bars, ScrollingFrames, AutomaticSize, GuiService, gamepad focus, touch UI, or UI that clips, resets on respawn, looks generic, or was generated as one giant LocalScript.DesignNo warnings★ 5.8K↓ —
- build-parallelismdotnet/skillsAnalyze an MSBuild solution, solution filter, or Build.proj that schedules multiple project files. USE FOR: measured idle worker nodes, `-m` that does not scale, a serial ProjectReference critical path, graph builds, or an MSBuild task that builds a Projects list. Requires at least two distinct project files whose scheduling or throughput must be analyzed. DO NOT USE for non-MSBuild build systems.ProductivityNo warnings★ 5.8K↓ —
- visual-novelgamedev-skills/awesome-gamedev-agent-skillsBuild a visual novel: a branching script, character and background display, a text box with choices, save/load, backlog, and skip/auto. Use for a VN, dating sim, or branching story game.OtherNo warnings★ 5.8K↓ —
- multi-sheet-reading-and-analysisOpenSenseNova/SenseNova-Skills用于读取多工作表Excel文件，动态评估数据量以启用Parquet大文件优化，并执行正则清洗、分类汇总、线性拟合及生成带格式的图表与结果文件。DocumentsNo warnings★ 6K↓ —
- unreal-packaginggamedev-skills/awesome-gamedev-agent-skillsPackage and ship an Unreal Engine 5 project: the Platforms menu Package Project flow, build configurations (Development vs Shipping), cooking content, packaging settings and the Game Default Map, and command-line builds with RunUAT BuildCookRun. Use when packaging a build, making a shipping build, cooking content, configuring packaging settings, or when the user mentions package Unreal, cook content, shipping build, or BuildCookRun.OtherNo warnings★ 5.8K↓ —
- hunt-sstielementalsouls/Claude-BugHunterHunt server-side template injection (SSTI) across Jinja2 (Flask/Django), Twig (Symfony), Freemarker (Java), ERB (Rails), Spring, Velocity, Mako, Thymeleaf, Smarty. Detection probes use double-curly and dollar-curly math expressions evaluated server-side. Once an engine is fingerprinted, escalate to RCE via the engine-specific class-walker, callback-registrar, or Execute-utility patterns documented in disclosed reports. Detection patterns: error messages reveal engine, blank or numeric eval reveals expression mode. Targets: email templates, PDF/report generators, CMS preview features, error pages with user input. Use when hunting RCE via template rendering, when content shows engine fingerprints, when finding endpoints that compose strings with user input before render.DocumentsNo warnings★ 5.4K↓ —
- godot-physicsgamedev-skills/awesome-gamedev-agent-skillsUse Godot 4.7 physics bodies and detection in 2D and 3D: RigidBody, StaticBody, Area, and CharacterBody; collision layers vs masks; contact/overlap signals; and raycasts (RayCast nodes and direct space-state queries). Use when configuring collision layers/masks, detecting overlaps with Area2D/Area3D, applying forces to a RigidBody, or casting rays in a Godot project (.tscn with physics bodies), including 3D projects running Jolt Physics, the default 3D engine for projects created in 4.6+.ScienceNo warnings★ 5.8K↓ —
- hunt-grpcelementalsouls/Claude-BugHunterHunt gRPC vulnerabilities — server reflection enabled (enumerate all services/methods), missing authentication / metadata-stripping on internal endpoints, plaintext gRPC over HTTP/2, internal endpoint disclosure, proto file leakage, gRPC-Web/grpc-gateway transcoding injection, and HTTP/2 Rapid Reset DoS (CVE-2023-44487). Use when target exposes port 50051 / 443 / 8443 / 9090 with HTTP/2, when grpcurl/grpcui detects reflection, when an Envoy or grpc-gateway proxy is fronting a microservice, or when recon reveals a microservice architecture.SecurityNo warnings★ 5.4K↓ —
- deep-module-refactorzebbern/claude-code-guideExplore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.EngineeringNo warnings★ 4.7K↓ —
- designlang-tokensManavarya09/design-extractUse when styling UI for planetscale.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.DesignNo warnings★ 4.4K↓ —
- fleet-managementgrafana/skillsManage a fleet of Grafana Alloy collectors with Fleet Management — author Alloy pipelines once, target them via attribute matchers (`env="production"`, regex `region=~"us-.*"`), push remotely via OpAMP without restarting collectors. Covers pipeline create / update / matcher RPCs, collector attribute API, `remotecfg` bootstrap block (standalone + Helm), pre-deploy `alloy fmt` validation, the local Alloy UI at port 12345 for component health, and post-deploy `REMOTE_CONFIG_STATUS_APPLIED` verification. Use when standing up a Cloud Alloy fleet, pushing a config change to 200 collectors, hunting why one collector shows `REMOTE_CONFIG_STATUS_FAILED`, validating River syntax before saving, or wiring `discovery.kubernetes` → `prometheus.remote_write` — even when the user says "configure Alloy", "remote config the collectors", "push pipeline", "OpAMP", "collector is unhealthy", or "manage agent config centrally" without naming Fleet Management.OfficialDevOpsNo warnings★ 297↓ —
- migrate-mstest-v1v2-to-v3dotnet/skillsUse this skill before answering or editing whenever an MSTest v1/v2 project is being upgraded or repaired for v3. Triggers include QualityTools assembly references; MSTest.TestFramework/TestAdapter 1.x-2.x; "upgrade to MSTest v3"; comparing v1 and v2 migration paths; choosing MSTest or MSTest.Sdk; CS0411/CS1503 after a v3 package bump; DataRow type mismatch, MSTEST0014, or "Test data doesn't match method parameters"; .testsettings/LegacySettings to .runsettings; timeout changes; and net5.0 or other dropped v3 TFMs. Still use it when packages say 3.x but migration source errors or legacy settings remain. Preserve VSTest/MTP. Do not use for a clean v3 project, v3-to-v4, framework conversion, or runner-only migration.TestingNo warnings★ 5.8K↓ —
openrlhf-training
Orchestra-Research/AI-Research-SKILLs
PlanningUpdated Oct 11, 2026
From the author
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill openrlhf-training -a claude-code
Installs to .claude/skills/openrlhf-training/ · 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 onlyUses the networkLicence: MIT
Safety checks on SKILL.md
- Uses sudoLow
Why 91
Security95
Provenance90
Maintenance100
Licence100
Adoption65
Files (5)
- SKILL.md
- references/algorithm-comparison.md
- references/custom-rewards.md
- references/hybrid-engine.md
- references/multi-node-training.md