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 9 hours ago
9,541 skills
- fine-tuning-with-trlKalarisLabs/research-agent-skillsFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.OtherNo warnings★ 76↓ —
- squareAnil-matcha/awesome-muse-connectorsWork with Square: list locations and payments, create orders, push Terminal checkouts, charge payment sources, and refund payments. Trigger phrases: square, square terminal, process payment, refund payment, point of sale.OtherNo warnings★ 1.4K↓ —
- duan-jianyeswaylq/master-skill段建业视角. 大陆当代盲派代表 / 北方盲派核心 / 师承郝金阳口诀派 / 字卜文 / 体系化《段氏理象学》编撰者. 把"看八字"从"取格定用神"的子平静态结构, 换成"取象 + 主宾体用 + 虚实 + 应期"的盲派动态象法. 用途: 当用户问"我这个八字是什么格" / "用神是什么" / "我什么时候能发财" / "婚姻何时动" / "盲派和子平差在哪" 时, 用段建业视角先把命局当成一幅"活的画"来读 — 每个字是事象代号, 不立刻取格, 不轻易下吉凶定论. 当用户提到 "段建业" / "盲派" / "段氏理象学" / "取象" / "主宾体用" / "虚实" / "应期" / "郝金阳" / "北京盲派班" 时使用. 即使用户只是说 "用盲派看一下" / "象法批一下" 也应触发.OtherNo warnings★ 174↓ —
- repo-mapmohitagw15856/pm-claude-skillsNavigate a codebase by map instead of reading files wholesale — a deterministic stdlib script that emits the tree with line counts and top-level symbols, plus the read-the-map-first discipline that cuts exploration tokens by an order of magnitude. Use when asked explore this repo efficiently, stop re-reading the whole codebase, make a map of this project, or which files should the agent actually open. Produces the compact map with its token math (map vs. everything), the navigation discipline, and the open-only-what-matches rule.OtherNo warnings★ 1.5K↓ —
- spotifyAnil-matcha/awesome-muse-connectorsWork with Spotify: read your profile, playlists, top tracks and artists, search the catalog, and (with confirmation) create playlists, add tracks, and save tracks to your library. Trigger phrases: spotify, my playlists, my top tracks, top artists, save track, search spotify.OtherNo warnings★ 1.4K↓ —
- close-doneOutlineDriven/outline-driven-developmentUse when the user wants to batch-close resolved or outdated tracker items. The agent never closes tracker items itself. Not for individual closure or items still under active work.OtherNo warnings★ 55↓ —
- stripeAnil-matcha/awesome-muse-connectorsRead-only Stripe visibility: balance, recent charges, customers. Trigger phrases: stripe, revenue, charges, balance, customers.OtherNo warnings★ 1.4K↓ —
- minutes-tagsilverstein/minutesLightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.OtherNo warnings★ 1.6K↓ —Also in 1 other repo
- calendlyAnil-matcha/awesome-muse-connectorsRead and manage Calendly: list scheduled events, event types, invitees, and availability schedules; cancel bookings. Trigger phrases: calendly, my meetings, scheduled events, cancel booking.OtherNo warnings★ 1.4K↓ —
- wayfinderOutlineDriven/outline-driven-developmentUse when a greenfield project or large feature build will not fit in a single agent session. Don't use for implementation, remote credential changes, or work that fits in one session.OtherNo warnings★ 55↓ —
- heaptrackOutlineDriven/outline-driven-developmentUse when tracking heap allocations on Linux with heaptrack: allocation hotspots, peak heap, temporary allocations, leaks, or a diff of two runs via heaptrack_print. Not for heap errors: use valgrind.OtherNo warnings★ 55↓ —
- issue-nowOutlineDriven/outline-driven-developmentUse when a human asks to compare one closed or stale tracker issue with current reality and mark it done or update it. Don't use for bulk issue reconciliation or multi-issue sweeps.OtherNo warnings★ 55↓ —
- car-tcomohitagw15856/pm-claude-skillsCompare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly payment. Use when asked should I lease or buy a car, is it cheaper to keep my old car, what does this car really cost per month, or new vs used total cost. Produces the ranked scenario totals, per-month true cost, the assumption ledger, and the not-modeled list.OtherNo warnings★ 1.5K↓ —
- valgrindOutlineDriven/outline-driven-developmentUse when running Valgrind Memcheck for heap errors, leaks, or uninitialised reads on an unmodified binary, or Cachegrind, Callgrind, or Massif profiling. Not for ASan builds: use sanitizers.OtherNo warnings★ 55↓ —
- discoverevo-hq/evoInitialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first experiment. Use when the user invokes /evo:discover, mentions setting up evo, wants to instrument a codebase for autonomous optimization, or asks to start a new evo run on a project.OtherNo warnings★ 1.5K↓ —Also in 1 other repo
- scenario-zbrush-pose-printUpdatedscenario-labs/skillsUse when posing a sculpt or preparing it for 3D printing in ZBrush: "pose this character", Transpose Master, TPoseMesh, Gizmo posing with masks, ZSphere rig, Proxy Pose, weapon in the hand, stretching after posing, "3D print this", 1/6 scale statue, miniature, resin or FDM, hollowing, wall thickness, drain holes, keys and pins, cutting into parts, 3D Print Hub, Scale Master, Decimation Master, STL or 3MF, size in millimeters.OtherNo warnings★ 1.2K↓ —
- 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↓ —
- andy-grove-intelswaylq/master-skillAndy Grove 视角. Intel 前 CEO, 《High Output Management》/《Only the Paranoid Survive》作者, Operator-Engineer 流派 (流派 B) 奠基者, OKR 之父 (John Doerr 的源头). 把 CEO 工作当工程系统管: 产出 = 组织产出, 经理杠杆率, OKR, 战略拐点 (SIP), 建设性对抗. 用途: 当用户问 "组织效率 / 中层管理 / OKR 怎么定 / 会议怎么开 / 什么时候该全力转向 (战略拐点判断) / 数据驱动经营" 类问题时, 用 Grove 的 经营科学镜片先把 "杠杆率在哪 + 拐点信号是噪音还是信号" 盘清楚再给判断. 当用户提到 "Andy Grove" "Grove" "High Output Management" "OKR 源头" "战略拐点" "strategic inflection point" "Only the Paranoid Survive" "经理杠杆率" 时使用. 即使用户只是说 "用 Grove 思路看一下" 也应触发.OtherNo warnings★ 174↓ —
- io-uringOutlineDriven/outline-driven-developmentUse when building Linux servers with liburing, batching SQEs, multi-shot operations, provided buffer rings, registered files and buffers, or zero-copy send. Not for packet I/O: use af-xdp.OtherNo warnings★ 55↓ —
- sujet-crfpa-allison-fiorentinolawve-ai/awesome-legal-skills>Ce skill génère des sujets d'entraînement pour les deux épreuves écrites de consultation du CRFPA : l'épreuve de droit des obligations (tronc commun) et l'épreuve de spécialité (civil, affaires, social, pénal, administratif, international et européen, fiscal). Chaque sujet est accompagné d'une grille de notation détaillée sur 20 points. Vous ciblez un thème précis, ou vous laissez le skill procéder à un tirage au sort couvrant l'ensemble du programme. Connexion aux MCP OpenLegi et GoodLegal requise : toutes les références d'articles et d'arrêts sont vérifiées sur les sources officielles, sans citation inventéeOtherNo warnings★ 911↓ —
- conan-vcpkgOutlineDriven/outline-driven-developmentUse when adding C/C++ dependencies with Conan or vcpkg, managing binary compatibility, integrating with CMake via conanfile.txt or vcpkg.json, or choosing between Conan and vcpkg.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
- 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↓ —
- 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↓ —
scenario-godot-performance-export
scenario-labs/skills
UpdatedOtherUpdated 15 hours ago
From the author
Use when a Godot game stutters, drops frames, hitches when entering new areas, overheats a phone, or must ship: profiling and Performance monitors, CPU or GPU bound, draw calls, MultiMesh, occlusion culling, LOD, shader compilation hitches, export to macOS, Windows, Linux, Steam, Android (APK, AAB, keystore), iOS (Xcode), web (itch.io, COOP/COEP headers, SharedArrayBuffer, JavaScript interop), build size budgets, demo and DLC builds, signing and notarization.
Install
npx skills add scenario-labs/skills --skill scenario-godot-performance-export -a claude-code
Installs to .claude/skills/scenario-godot-performance-export/ · 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
Runs bundled scriptsNo network use seenLicence: MIT
Safety checks on SKILL.md
- Uses sudoLow
- Ships scripts we have not reviewedLow
Why 82
Security85
Provenance77
Maintenance100
Licence100
Adoption50
Files (15)
- SKILL.md
- references/critique.md
- references/expert-notes.md
- references/gui-paths.md
- references/procedures.md
- references/sources.md
- scripts/agentkit/perf/mobile_touch.gd
- scripts/agentkit/perf/perf_audit.gd
- scripts/agentkit/perf/perf_bench.gd
- scripts/agentkit/perf/perf_fixes.gd
- scripts/agentkit/perf/perf_logger.gd
- scripts/agentkit/perf/perf_stress.gd
- +3 more