Menu
Build and publish the Weave Python SDK to PyPI. Use when releasing a new version.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Bump the Weave Python SDK version for release. Use when preparing a new release.
Add Weave (Weights & Biases) observability to an LLM or agent codebase. This covers calling `weave.init()`, setting up authentication, and choosing between OTEL auto-instrumentation and the explicit Session SDK agent-logging APIs (Turn, LLM, Tool, SubAgent), based on the libraries the code already uses. Works for Python and TypeScript/Node. Use this whenever the user wants to instrument, trace, or add observability, logging, or monitoring to an agent, chatbot, RAG pipeline, or LLM app. This includes phrasings like "log my agent to weave", "add agent tracing", "get my agent into the Weave Agents tab", "instrument this with the weave session sdk", "trace my tool calls", or "set up weave logging", even when the user does not name a specific API.
| name | publish-pypi |
| description | Build and publish the Weave Python SDK to PyPI. Use when releasing a new version. |
This replicates the GitHub Actions publish-pypi-release workflow.
$ARGUMENTS can be test to publish to Test PyPI, or empty for production PyPIFirst, run a dry-run to build and verify the package:
uv run ./scripts/publish_pypi_release.py --dry-run
If the user wants to publish to Test PyPI (or $ARGUMENTS contains "test"):
uv run ./scripts/publish_pypi_release.py --test
If the user wants to publish to production PyPI:
uv run ./scripts/publish_pypi_release.py
Before publishing, ensure the user has set up authentication. Options:
TWINE_API_KEY environment variable (recommended for production)TWINE_TEST_API_KEY environment variable (for Test PyPI).pypirc file in home directoryIf authentication fails, help the user set up their credentials.
Remind the user to verify the package: