Skip to main content

ai-hats-library

The agent library for ai-hats — the portable content the framework composes into role prompts: skills, roles, traits, and rules, plus the runtime hooks they ship. It is a data-only package (YAML + Markdown + a few hook scripts); it holds no framework runtime code and has zero dependencies.

Two ways to use it

1. Drop-in for any Claude Code user (no ai-hats, no pip). The skills are in the standard Claude Code Agent-Skill format (SKILL.md frontmatter). Clone this package and copy the ones you want into ~/.claude/skills/:

git clone https://github.com/muratovv/ai-hats
cp -r ai-hats/packages/ai-hats-library/src/ai_hats_library/core/skills/systematic-debugging ~/.claude/skills/

The ai-hats composition metadata rides in a namespaced ai_hats: frontmatter key that non-ai-hats agents simply ignore — so every SKILL.md stays drop-in.

2. As the content dependency of ai-hats. ai-hats pins this package (ai-hats-library>=…) and resolves its built-in library layer from it via importlib.resources. The precedence stack layers user overrides on top, last-wins: built-in (this package) < ~/.ai-hats < project libraries.

Layout

src/ai_hats_library/
  core/     # engine fundament — universal skills, base traits, global rules, pipelines
  usage/    # opinionated catalog — domain roles, dev::/env:: traits, opt-in skills
  hooks/    # runtime hook sources materialized into consuming projects

core/ and usage/ are the two library layers (core first = lowest priority). Local development against ai-hats uses the AI_HATS_LIBRARY_ROOT environment override pointed at a checkout of this package.

Versioning

Semantic versioning on the format schema (skill frontmatter + composition schema + resolver expectations), decoupled from ai-hats's own version. The shipped schema_version (in manifest.yaml) is the contract; ai-hats pins a compatible range and fails loud on a library newer than it understands. MAJOR = breaking schema change, MINOR = skills/roles added, PATCH = content fix.

License

MIT — see LICENSE. Third-party-derived skills carry their own upstream attribution in-tree (metadata.yaml upstream: blocks + per-skill LICENSE files); see the repository-root THIRD_PARTY_NOTICES.

Release files for ai-hats-library 0.7.4

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

Source distribution (sdist)

Source distribution for ai-hats-library 0.7.4
File Size Uploaded
ai_hats_library-0.7.4.tar.gz 936.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ai-hats-library 0.7.4
File Interpreter ABI Platform
ai_hats_library-0.7.4-py3-none-any.whl Python 3 none any Details

Total release size: 2.2 MB

Release files / ai_hats_library-0.7.4.tar.gz

Download URL ai_hats_library-0.7.4.tar.gz
Size 936.0 kB
Tags Source
SHA-256 checksum
How to use checksums
293806c7f884d675b61efe1d63fcb78578254bed365d1c37b5e354983d75817d
BLAKE2b-256 checksum
How to use checksums
3c914ad33f94c83bb0982d6cb9e6899ca734a9a49221c063a11d4772941e0b80
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 20, 2026.

Transparency log

Release files / ai_hats_library-0.7.4-py3-none-any.whl

Download URL ai_hats_library-0.7.4-py3-none-any.whl
Size 1.3 MB
Tags Python 3
SHA-256 checksum
How to use checksums
ee23005456fc04f9c6e9c46c626f3d424f0a7119f8b8b4e1b8684a3f8754e5ac
BLAKE2b-256 checksum
How to use checksums
0bcfad22063a2f218ba663da3af76e21ac073b9ecfc30e367d4ff9fe7b55c6b3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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 Sep 20, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.7.4 This release

2 release files

0.7.3

2 release files

0.7.2

2 release files

0.7.1

2 release files

0.7.0

2 release files

0.6.6

2 release files

0.6.5

2 release files

0.6.4

2 release files

0.6.2

2 release files

0.6.1

2 release files

0.6.0

2 release files

0.5.7

2 release files

0.5.1

2 release files

0.5.0

2 release files

0.4.0

2 release files

0.3.1

2 release files

0.3.0

2 release files

0.2.0

2 release files

0.1.0

2 release files

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