Skip to content
Back to search

pymc-modeling

MarketplaceWorks with Claude CodeGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pymc-labs--pymc-modeling/badge.svg)](/listings/pymc-labs--pymc-modeling)

HTML

<a href="/listings/pymc-labs--pymc-modeling"><img src="/api/listings/pymc-labs--pymc-modeling/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Local checkout

From the repository root, use the [Skills CLI](https://github.com/vercel-labs/skills):

npx skills add .

Choose the skills and agents you want.

For a local Claude Code managed bundle, run these commands from the repository root inside Claude Code:

/plugin marketplace add ./
/plugin install pymc-modeling@pymc-modeling

This local installation does not require the renamed marketplace to be published. Use a clean checkout for this installation: Claude Code can copy untracked files too, including a maintainer's `.pixi/` environments.

Or copy individual directories from `skills/` into your agent's supported skills location. Keep the whole directory, including references, any scripts and `LICENSE`. No custom installer or running service is required.

Published repository (publication required)

Use the following commands only after the matching skills and marketplace manifest have been published to `pymc-labs/pymc-modeling`. The published manifest must name both the marketplace and its plugin `pymc-modeling`. Until then, use the local-checkout instructions above. Local validation does not establish remote availability or successful remote plugin installation.

For the Skills CLI:

npx skills add pymc-labs/pymc-modeling

For a Claude Code managed bundle:

/plugin marketplace add pymc-labs/pymc-modeling
/plugin install pymc-modeling@pymc-modeling

Choose either the plugin or the Skills CLI/manual installation, not both, to avoid duplicate skills.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 22 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "pymc-modeling",
  3. "version": "6.4.0",
  4. "owner": { "name": "PyMC Labs" },
  5. "metadata": { "description": "Agent skills for PyMC, PyTensor, prior elicitation, ArviZ and MLflow tracking." },
  6. "plugins": [
  7. {
  8. "name": "pymc-modeling",
  9. "version": "6.4.0",
  10. "description": "Bayesian modeling, prior elicitation, ArviZ diagnostics, PyTensor workflows and MLflow tracking.",
  11. "source": "./",
  12. "strict": false,
  13. "skills": [
  14. "./skills/pymc-modeling",
  15. "./skills/prior-elicitation",
  16. "./skills/arviz-diagnostics",
  17. "./skills/pytensor-workflows",
  18. "./skills/pymc-mlflow"
  19. ]
  20. }
  21. ]
  22. }
README.md · README · 175 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # pymc-modeling
  2. Agent skills for Bayesian modeling with PyMC, PyTensor and ArviZ, and experiment
  3. tracking with MLflow. Each skill is a folder of instructions and focused references in the
  4. [Agent Skills format](https://agentskills.io/specification).
  5. ## Skills
  6. | Skill | Use it for |
  7. |---|---|
  8. | [pymc-modeling](skills/pymc-modeling/SKILL.md) | Model specification, inference, predictions, specialized model families and pymc-extras workflows |
  9. | [prior-elicitation](skills/prior-elicitation/SKILL.md) | Prior selection, elicitation, predictive checks and shrinkage |
  10. | [arviz-diagnostics](skills/arviz-diagnostics/SKILL.md) | MCMC diagnostics, predictive checks, LOO and model comparison |
  11. | [pytensor-workflows](skills/pytensor-workflows/SKILL.md) | Symbolic graphs, shapes, compilation, gradients and custom Ops |
  12. | [pymc-mlflow](skills/pymc-mlflow/SKILL.md) | MLflow experiment tracking, DataTree artifacts, PyMC-Marketing autologging and MMM persistence |
  13. ## Install
  14. ### Local checkout
  15. From the repository root, use the [Skills CLI](https://github.com/vercel-labs/skills):
  16. ```bash
  17. npx skills add .
  18. ```
  19. Choose the skills and agents you want.
  20. For a local Claude Code managed bundle, run these commands from the repository
  21. root inside Claude Code:
  22. ```text
  23. /plugin marketplace add ./
  24. /plugin install pymc-modeling@pymc-modeling
  25. ```
  26. This local installation does not require the renamed marketplace to be published.
  27. Use a clean checkout for this installation: Claude Code can copy untracked
  28. files too, including a maintainer's `.pixi/` environments.
  29. Or copy individual directories from `skills/` into your agent's supported skills
  30. location. Keep the whole directory, including references, any scripts and `LICENSE`.
  31. No custom installer or running service is required.
  32. ### Published repository (publication required)
  33. Use the following commands only after the matching skills and marketplace
  34. manifest have been published to `pymc-labs/pymc-modeling`. The published manifest
  35. must name both the marketplace and its plugin `pymc-modeling`. Until then, use
  36. the local-checkout instructions above. Local validation does not establish remote
  37. availability or successful remote plugin installation.
  38. For the Skills CLI:
  39. ```bash
  40. npx skills add pymc-labs/pymc-modeling
  41. ```
  42. For a Claude Code managed bundle:
  43. ```text
  44. /plugin marketplace add pymc-labs/pymc-modeling
  45. /plugin install pymc-modeling@pymc-modeling
  46. ```
  47. Choose either the plugin or the Skills CLI/manual installation, not both, to
  48. avoid duplicate skills.
  49. ## Use
  50. Ask your agent to perform a relevant task, or invoke the skill by name using
  51. your agent's skill mechanism. For example:
  52. - “Build a hierarchical model for these grouped observations.”
  53. - “Check whether these priors imply plausible outcomes.”
  54. - “Diagnose this posterior and assess whether LOO is reliable.”
  55. - “Find the shape or gradient error in this PyTensor graph.”
  56. - “Use pymc-extras to marginalize latent states or fit and forecast a structural time series.”
  57. Current modeling guidance uses the [checked stack](skills/pymc-modeling/references/pymc-extras.md#resolve-compatibility-before-choosing-an-api) and ArviZ's DataTree API.
  58. References retain explicitly named older-release cautions where they help existing projects. Check each reference's version scope.
  59. Use the consuming project's compatible Python environment.
  60. Optional packages support only the workflows that need them.
  61. Do not replace a working environment just to install these instructions.
  62. The [MLflow skill](skills/pymc-mlflow/SKILL.md) supports ordinary PyMC tracking
  63. without PyMC-Marketing. Its optional integration examples target PyMC-Marketing
  64. 1.2.0, which requires PyMC `>=6.3.1,<6.4.0` and ArviZ `>=1.2.0,<2.0`, plus a
  65. separate MLflow installation. Saving posterior artifacts, restoring native
  66. models and registering MMM prediction wrappers are distinct from deploying a
  67. service; the references make those boundaries explicit.
  68. The generic [MLflow tracking example](skills/pymc-mlflow/references/tracking.md) records its verified stack and compatibility limits.
  69. PyMC-Marketing 1.2.0's built-in MMM pyfunc prediction route forwards an unsupported
  70. `original_scale` argument. The [MMM reference](skills/pymc-mlflow/references/mmm-persistence.md)
  71. documents this reproduced upstream limitation and the working native
  72. restoration/prediction route; wrapper registration is not a serving guarantee.
  73. The [pymc-extras guide](skills/pymc-modeling/references/pymc-extras.md) routes to
  74. inference, exact/approximate marginalization, specialized distributions,
  75. state-space forecasting, prior factories and model-building tools. Its examples
  76. distinguish supported recovery from approximation error.
  77. Inspect installed APIs when adapting them to another release.
  78. ## Release versions
  79. Release tags use `vMAJOR.MINOR.PATCH`.
  80. `MAJOR.MINOR` identifies the primary target PyMC series.
  81. `PATCH` tracks revisions to this plugin, not the PyMC patch release.
  82. For example, `v6.4.1` can revise the skills for the PyMC 6.4 series.
  83. The [compatibility guide](skills/pymc-modeling/references/pymc-extras.md#resolve-compatibility-before-choosing-an-api) records exact checked versions and dependency bounds.
  84. Individual references retain their stated compatibility limits.
  85. The marketplace and plugin versions match the release tag without its `v` prefix.
  86. ## Maintainer checks
  87. These checks exercise the educational custom Op and its CPU backends, not the
  88. full set of modeling examples or accelerator hardware. They do not install
  89. anything into a consuming project's environment.
  90. Use Pixi 0.83.0 or newer for the platform-specific glibc declaration.
  91. See the [checked stack and dependency bounds](skills/pymc-modeling/references/pymc-extras.md#resolve-compatibility-before-choosing-an-api) for the extras environment and the shared PyTensor version.
  92. The Linux test environments require glibc 2.35 or newer. From this repository:
  93. ```bash
  94. pixi run --locked test
  95. pixi run --locked -e jax test -m jax
  96. pixi run --locked -e pytorch test -m pytorch
  97. pixi run --locked -e mlx test -m mlx
  98. ```
  99. For the compatible PyMC Extras stack without changing the default environment:
  100. ```bash
  101. pixi install --locked -e extras
  102. pixi run --locked -e extras python -c "import pymc_extras; print(pymc_extras.__version__)"
  103. ```
  104. This environment includes histogram and grouped NetCDF support for executing the
  105. extras reference examples. The existing pytest suite does not validate all extras
  106. features; runtime checks of documented examples do not establish scientific
  107. adequacy or accelerator compatibility.
  108. The default environment checks the base Op and Numba; other backend tests skip
  109. when their optional packages are absent. The named environments install the
  110. corresponding backend, with CPU-only PyTorch and MLX packages. `pixi.lock` records
  111. exact resolved versions, and each pytest session prints the versions actually
  112. exercised. Tests compare values to SciPy and weighted derivatives and curvature
  113. to analytic references, and check support boundaries and input errors.
  114. The GitHub Actions workflow runs the four custom-Op test environments with the lockfile,
  115. not the optional extras examples.
  116. Use `pixi run --locked check` to lint tests and skill scripts.
  117. Use `pixi run --locked format` for regression-test formatting.
  118. These maintainer tools are not needed to install or use the skills.
  119. The MLflow references contain standalone Python examples for manual tracking,
  120. autologging and native MMM/CLV restoration; they are not covered by the custom-Op
  121. pytest suite. Execute them in separate processes and disposable working
  122. directories with their version-matched dependencies. Their checks exercise
  123. artifact content, searchable metadata and restored predictions, not scientific
  124. adequacy. The MMM reference separates its intentional upstream-failure
  125. reproduction from the successful native and local-registry examples.
  126. ## License
  127. Adapted from [pymc-labs/pymc-modeling](https://github.com/pymc-labs/pymc-modeling/tree/b41e66104685ba06fce89091cf0706e9bc21872e).
  128. Licensed under [MIT](LICENSE). Each skill includes the same license for
  129. standalone distribution, including the original PyMC Labs copyright notice.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.