Skill agen
Skill untuk Claude Code, Codex, Cursor, dan agen lain dari direktori skills.sh: jumlah instalasi, status audit keamanan, dan perintah untuk menambahkan skill.
Skill tidak terikat pada satu agen: npx skills add memasangnya ke agen mana pun yang didukung. Tanpa -a, CLI mencari agen di komputer Anda dan menanyakan ke mana skill ditambahkan.
Diperbarui · Sumber: skills.sh
Ditampilkan: 15 · ditemukan: 15 · dari 10.000 di direktori
-
uv-package-manager wshobson/agents
Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.
16.092 Gagal -
Creates and edits parametric CAD parts and assemblies as Python build123d models that cadgen's engine builds and the CAD Viewer shows live; exports STEP, STL, 3MF, GLB and xbf files on request; resolves prompt references, measures geometry, and articulates or animates assemblies. Use for 3D CAD modeling, editing a model script (any change to a part's or assembly's `.py`), organizing a CAD project, exporting or converting CAD files, Quick Edit prompts, mechanisms, and explode or showcase animations. Opens and reviews existing XBF, STEP/STP, STL, 3MF and GLB files in the CAD Viewer.
15.744 Gagal -
marimo-pair marimo-team/marimo-pair
Drive a live marimo notebook as a workspace: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes. Use when the user wants to start a marimo notebook or pair on an active marimo session.
14.318 Gagal -
temporal-python-testing wshobson/agents
Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.
11.556 Gagal -
notebooklm teng-lin/notebooklm-py
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API. Do not use for the generic Gemini API or unrelated content creation.
10.262 Gagal -
python-pro jeffallan/claude-skills
Use when building Python 3.11+ applications requiring type safety, async programming, or robust error handling. Generates type-annotated Python code, configures mypy in strict mode, writes pytest test suites with fixtures and mocking, and validates code with black and ruff. Invoke for type hints, async/await patterns, dataclasses, dependency injection, logging configuration, and structured error handling.
9.356 Gagal -
fastapi-expert jeffallan/claude-skills
Use when building high-performance async Python APIs with FastAPI and Pydantic V2. Invoke to create REST endpoints, define Pydantic models, implement authentication flows, set up async SQLAlchemy database operations, add JWT authentication, build WebSocket endpoints, or generate OpenAPI documentation. Trigger terms: FastAPI, Pydantic, async Python, Python API, REST API Python, SQLAlchemy async, JWT authentication, OpenAPI, Swagger Python.
6.625 Gagal -
pandas-pro jeffallan/claude-skills
Performs pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working with pandas DataFrames, data cleaning, aggregation, merging, or time series analysis. Invoke for data manipulation tasks such as joining DataFrames on multiple keys, pivoting tables, resampling time series, handling NaN values with interpolation or forward-fill, groupby aggregations, type conversion, or performance optimization of large datasets.
6.320 Gagal -
django-expert vintasoftware/django-ai-plugins
Expert Django backend development guidance. Use when creating Django models, views, serializers, or APIs; debugging ORM queries or migrations; optimizing database performance; implementing authentication; writing tests; or working with Django REST Framework. Follows Django best practices and modern patterns.
5.992 Gagal -
devcontainer-setup trailofbits/skills
Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding devcontainer support to a project, setting up isolated development environments, or configuring sandboxed Claude Code workspaces.
5.956 Gagal -
django-expert jeffallan/claude-skills
Use when building Django web applications or REST APIs with Django REST Framework. Invoke when working with settings.py, models.py, manage.py, or any Django project file. Creates Django models with proper indexes, optimizes ORM queries using select_related/prefetch_related, builds DRF serializers and viewsets, and configures JWT authentication. Trigger terms: Django, DRF, Django REST Framework, Django ORM, Django model, serializer, viewset, Python web.
4.645 Gagal -
cuopt-developer nvidia/skills
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
2.757 Gagal -
modal k-dense-ai/scientific-agent-skills
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.
2.161 Gagal -
setup marketcalls/vectorbt-backtesting-skills
Set up the Python backtesting environment. Detects OS, creates virtual environment, installs dependencies (openalgo, ta-lib, vectorbt, plotly), and creates the backtesting folder structure.
2.134 Gagal -
harvard-artifacts-etl-analytics reason-machines/data-skills
Build ETL pipelines and analytics dashboards for Harvard Art Museums API data with Python, SQL, and Streamlit
2.015 Gagal
Deskripsi ditulis oleh pembuatnya sendiri, dalam bahasa Inggris. Baca kode skill di repositorinya sebelum menginstalnya.
Apa itu skill
Skill adalah folder berisi berkas SKILL.md dan, bila perlu, skrip yang dimuat agen AI ketika tugasnya cocok. Bayangkan sebagai panduan khusus: agen tidak perlu dijelaskan ulang di setiap percakapan karena ia membaca instruksi skill tepat pada waktunya. Direktori ini memuat skill dari skills.sh untuk Claude Code, Codex, Cursor, dan agen lain.
Yang ditampilkan halaman ini
- nama, pembuat, dan repositori setiap skill;
- jumlah instalasi dan status audit keamanan;
- perintah untuk menambahkan skill, lengkap dengan tombol “Salin perintah”.
Direktori berisi 10 000 skill dengan instalasi terbanyak dan disinkronkan setiap hari. Tab “Sedang tren” mengurutkan berdasarkan tambahan instalasi dalam 7 hari terakhir. Tersedia filter topik dan agen serta kotak pencarian; setiap tampilan memuat paling banyak 100 skill.
Memahami status audit
Status berasal dari audit yang diterbitkan skills.sh: “Lolos”, “Peringatan”, “Gagal”, dan “Belum diaudit”. Audit yang lolos bukan jaminan. Skill bisa memuat skrip yang berjalan di komputer Anda, jadi baca kodenya di repositori sebelum memasang, terutama bila skill meminta akses ke berkas, jaringan, atau kredensial.
Kebiasaan memasang yang aman
Saring berdasarkan agen yang Anda pakai dan topik tugas. Buka repositorinya, baca SKILL.md dan skripnya. Utamakan skill berstatus “Lolos” dengan pembuat yang jelas identitasnya. Salin perintahnya dan pasang dulu di proyek uji sebelum dipakai untuk pekerjaan sungguhan. Jika skill tidak lagi diperlukan, hapus agar agen tidak memuatnya tanpa sengaja.
Contoh skill yang berguna
Ada skill untuk menulis dokumentasi, menjalankan tes, merapikan kode frontend, atau bekerja dengan basis data. Filter topik membantu menemukannya. Pilih yang sesuai tumpukan teknologi Anda. Jangan memasang terlalu banyak sekaligus. Beberapa skill yang benar-benar dipakai lebih bermanfaat daripada puluhan yang jarang tersentuh.
Catatan
Deskripsi skill ditulis sendiri oleh pembuatnya dalam bahasa Inggris dan tidak diterjemahkan. Jumlah instalasi dihitung oleh skills.sh. Untuk memilih agen yang akan memakai skill, lihat halaman agen pemrograman.