HoloViz Skills
A curated collection of Agent Skills for the HoloViz ecosystem — Panel, hvPlot, HoloViews, Param, and more.
Agent Skills are folders of instructions, scripts, and references that teach agents how to work effectively with a specific library or workflow. These skills help agents produce correct, idiomatic HoloViz code instead of guessing from stale training data.
Documentation
Visit https://holoviz-dev.github.io/holoviz-skills/ for the full list of skills and usage instructions. There, there are Copy Markdown icons at the top of each skill page to paste a skill directly into any AI chat if you prefer that over installing.
Installation
pip install holoviz-skills
holoviz-skills install # auto-detects tools on your machine
holoviz-skills install --global # install to global (~/) paths instead
Or target a specific tool:
holoviz-skills install --claude-code # .claude/skills/
holoviz-skills install --agent # .agents/skills/ (cross-tool standard, commit to git)
holoviz-skills install --codex # .agents/skills/ (OpenAI Codex)
holoviz-skills install --copilot # .github/skills/ (GitHub Copilot)
holoviz-skills install --cursor # .cursor/skills/
holoviz-skills install --windsurf # .windsurf/skills/
holoviz-skills install --cline # .cline/skills/
holoviz-skills install --jetbrains # .junie/skills/ (JetBrains / Junie)
holoviz-skills install --gemini-cli # .gemini/skills/
holoviz-skills install --antigravity # .agents/skills/ (Google Antigravity)
holoviz-skills install --kiro # .kiro/skills/
holoviz-skills install --kilo-code # .kilo/skills/ (Kilo Code)
holoviz-skills install --mistral-vibe # .vibe/skills/
Evaluation
The scripts/ directory contains an automated evaluation system that measures whether the skills improve Copilot's code generation quality. See scripts/README.md for details.
CI support for evaluations is also available through the Eval Command GitHub Actions workflow, including a maintainer @run-eval pull request comment trigger. See the GitHub Actions section in scripts/README.md.
Contributing
Contributions are welcome. See the documentation for details on how skills are structured and how to add a new one.
License
BSD — see LICENSE.txt.
Release files for holoviz-skills 2026.8.6
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| holoviz_skills-2026.8.6-py3-none-any.whl | Python 3 | none | any | Details |
Release files / holoviz_skills-2026.8.6-py3-none-any.whl
| Download URL | holoviz_skills-2026.8.6-py3-none-any.whl |
|---|---|
| Size | 161.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2b1e10a1df10835a115881fe5665a28a82676d8a5f094213424af0a9924fad00
|
|
BLAKE2b-256 checksum How to use checksums |
54cc9e3d7e78efe5a2d59541c5088d718dbc1f6257c6b2ed8fda15cd25918d81
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 6, 2026.
Transparency log