Skip to main content

kedro-skills

Python Version PyPI Version License

Distribute AI coding skills to Kedro projects. One command installs contextual guidance selected by the task or matching files — across Cursor, GitHub Copilot, Claude Code, and Codex CLI.

Installation

pip install kedro-skills

Quick start

# Inside any Kedro project:
kedro skills list
kedro skills install kedro-catalog-config

This writes managed files into your Kedro project. They should be committed to git so the whole team benefits.

Outside a Kedro project, the commands use the current directory instead.

Available skills

Skill Activates on Guidance
kedro-build-demo Requests for a new demo or proof of concept A new, small end-to-end Kedro demo with a working result, an offline HTML walkthrough and Kedro-Viz guidance; other audience material only on request
kedro-catalog-config conf/**/*.yml, conf/**/*.yaml Data catalog entries: dataset types, factories, credentials, interpolation
kedro-deploy-databricks databricks.yml, resources/*.yml, conf/**/databricks*.yml, conf/**/databricks/**/*.yml, .github/workflows/*databricks*.yml (and .yaml) Deploying to Databricks: choosing a path, packaging, conf and environments, volumes, secrets, nodes to tasks, checking before deploying
kedro-explain-project src/**/pipeline_registry.py, src/**/settings.py Explaining an existing project: pipelines, data flow, catalog, configuration and Kedro-Viz
kedro-llm-context-nodes src/**/pipelines/**/*.py The llm_context_node API for composing LLMs, prompts and tools
kedro-parameters-and-config conf/**/parameters*.yml and conf/**/credentials*.yml Parameters, credentials, configuration interpolation and runtime overrides.
kedro-testing-pipelines tests/**/*.py Node unit tests, in-memory pipeline tests and KedroSession smoke tests

What it writes

my-kedro-project/
├── .agents/skills/kedro-catalog-config/SKILL.md              # canonical (Agent Skills standard)
├── AGENTS.md                                                 # content discovery (Cursor, Copilot, Codex CLI)
├── .cursor/rules/kedro-catalog-config.mdc                    # glob-scoped activation (Cursor)
├── .github/instructions/kedro-catalog-config.instructions.md # glob-scoped activation (Copilot)
└── .claude/skills/kedro-catalog-config/SKILL.md              # Claude Code (inline copy, always discoverable)

AGENTS.md is the content-discovery channel — one file reaches Cursor, Copilot, and Codex CLI. .cursor/rules/ and .github/instructions/ add glob-scoped activation for skills with file patterns. Skills with paths: [], such as kedro-build-demo, use their descriptions instead: their wrappers omit file patterns, and their AGENTS.md blocks apply only to matching requests. They can be installed in an empty folder before a project exists.

If you installed the earlier PR preview as build-demo, run kedro skills uninstall build-demo with that preview still installed, before upgrading the package. Then install kedro-build-demo. The preview name is not an alias for the new name.

CLI reference

Command Description
kedro skills list Show available skills and their install status
kedro skills install <id> Install a skill for all supported IDEs
kedro skills install --all Install every available skill
kedro skills install --ide cursor,claude Restrict to specific IDEs
kedro skills install --force Overwrite even if files were hand-edited
kedro skills update Re-render all installed skills (picks up package upgrades)
kedro skills update --force Overwrite modified files during update
kedro skills uninstall <id> Remove a skill and all its managed files
kedro skills uninstall --force Remove even if files were hand-edited

IDE-specific notes

  • Claude Code: Reads .claude/skills/<id>/SKILL.md directly. The skill is always discoverable (no paths: scoping in the Claude copy). If you want AGENTS.md content in Claude sessions too, add @AGENTS.md to a CLAUDE.md file.
  • Cursor: .cursor/rules/*.mdc uses globs: for matching files, or a description with alwaysApply: false for agent-selected relevance when no paths are specified.
  • GitHub Copilot: .github/instructions/*.instructions.md uses applyTo: for matching files, or a description for on-demand discovery when no paths are specified.
  • Codex CLI: Reads AGENTS.md natively. Each skill block states whether it applies to matching files or matching requests.

How to try it out

# Install kedro-skills from source (in the kedro-skills repo root)
pip install .

# Create a test Kedro project
pip install kedro
kedro new --name test-project -s spaceflights-pandas
cd test-project

# See what's available
kedro skills list

# Install the kedro-catalog-config skill
kedro skills install kedro-catalog-config

# Check what was written
ls .agents/skills/kedro-catalog-config/SKILL.md
cat AGENTS.md
ls .cursor/rules/
ls .github/instructions/
ls .claude/skills/kedro-catalog-config/

# Running install again is safe — nothing changes
kedro skills install kedro-catalog-config --ide cursor,copilot,claude

# If you hand-edit a managed file, update will let you know
echo "modified" > .cursor/rules/kedro-catalog-config.mdc
kedro skills update          # refuses and names the modified file
kedro skills update --force  # overwrites your edit with the managed version

# Clean removal when you no longer need a skill
kedro skills uninstall kedro-catalog-config
kedro skills list            # back to "not installed"

Telemetry

When kedro-telemetry is installed (it ships with Kedro), the install, update and uninstall commands report anonymous usage events:

Event Properties
kedro_skills_install skill_id, target_ides (sorted, comma-separated), install_all (whether --all was used), success
kedro_skills_update skills_updated (count), drift_detected (whether locally modified skill files were found), success
kedro_skills_uninstall skill_id

Skill ids are reported when they match a skill shipped with this package; anything else is sent as unknown. kedro skills list sends no event. No skill content, file paths, project details or personal data are ever sent. The standard Kedro telemetry opt-out (DO_NOT_TRACK, KEDRO_DISABLE_TELEMETRY, or a .telemetry file with consent: false) disables these events too.

Development

See README_DEV.md for setup, running tests, authoring skills, and releasing.

Metadata

Release files for kedro-skills 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for kedro-skills 0.3.0
File Size Uploaded Provenance Actions
kedro_skills-0.3.0.tar.gz 63.1 kB With provenance Details for kedro_skills-0.3.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for kedro-skills 0.3.0
File Interpreter ABI Platform Actions
kedro_skills-0.3.0-py3-none-any.whl Python 3 none any Details for kedro_skills-0.3.0-py3-none-any.whl

Total release size: 138.4 kB

Release files / kedro_skills-0.3.0.tar.gz

Download URL kedro_skills-0.3.0.tar.gz
Size 63.1 kB
Tags Source
SHA-256 checksum
How to use checksums
e87f9bbaf8fb6cbdccbc57fa183a639b30c597a5b698cc82ee81557d7d1dc472
BLAKE2b-256 checksum
How to use checksums
36bb83848cbb78ebff8e8af5570269118a72640e5c570d91eede221fa671b1c1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 12, 2026.

Transparency log

Release files / kedro_skills-0.3.0-py3-none-any.whl

Download URL kedro_skills-0.3.0-py3-none-any.whl
Size 75.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
36317be3776fd86d39dfe62d2b371836bb3d73b93342818fee976b4f2c8aa74b
BLAKE2b-256 checksum
How to use checksums
8148d07fe2ca55259dd43aa6d53ce1dbb6c4b0d9ab1bd5165d85d1edb5e6b80f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 12, 2026.

Transparency log

Security for kedro-skills 0.3.0

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.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for kedro_skills-0.3.0.tar.gz

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 Nov 12, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page