openapi-to-agent-skills
Convert OpenAPI specifications to Agent Skills format — structured markdown documentation optimized for AI agents.
Installation
pip install openapi-to-agent-skills
Usage
openapi-to-agent-skills <path-or-url-to-openapi-spec> [OPTIONS]
Options
| Option | Description | Default |
|---|---|---|
-o, --output |
Output directory | ./output |
-n, --name |
Skill name (derived from API title if omitted) | |
--include-tags |
Only include these tags (comma-separated) | |
--exclude-tags |
Exclude these tags (comma-separated) | |
--exclude-deprecated |
Exclude deprecated operations | False |
-t, --templates |
Custom templates directory | |
-a, --assets |
Static assets directory overlaid onto output | |
--exclude-paths |
Exclude paths matching prefixes (comma-separated) | |
-g, --group-by |
Grouping strategy: tags, path, auto |
auto |
--case-strategy |
lowercase for case-insensitive filesystem safety |
|
-f, --force |
Overwrite existing output directory | False |
-q, --quiet |
Suppress output except errors | False |
Examples
# From a local file
openapi-to-agent-skills api.yaml -o ./skills
# From a URL
openapi-to-agent-skills https://petstore3.swagger.io/api/v3/openapi.json -o ./skills
# Filter by tags
openapi-to-agent-skills api.yaml --include-tags users,orders
# Case-safe output for Windows/macOS
openapi-to-agent-skills api.yaml --case-strategy lowercase
Output Structure
<skill-name>/
├── SKILL.md # Entry point with YAML frontmatter
└── references/
├── authentication.md # Auth schemes (if any)
├── resources/
│ └── <tag>.md # One per resource group
├── operations/
│ └── <operationId>.md # One per operation
└── schemas/
└── <prefix>/
├── _index.md
└── <SchemaName>.md # One per schema
Programmatic Usage
from openapi_to_skills import convert_openapi_to_skill
from openapi_to_skills.types import ConvertOptions
import yaml
with open("api.yaml") as f:
spec = yaml.safe_load(f)
convert_openapi_to_skill(spec, ConvertOptions(output_dir="./output"))
License
MIT
Metadata
Release files for openapi-to-agent-skills 0.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| openapi_to_agent_skills-0.3.2.tar.gz | 16.2 kB | Without provenance | Details for openapi_to_agent_skills-0.3.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| openapi_to_agent_skills-0.3.2-py3-none-any.whl | Python 3 | none | any | Details for openapi_to_agent_skills-0.3.2-py3-none-any.whl |
Total release size: 37.1 kB
Release files / openapi_to_agent_skills-0.3.2.tar.gz
| Download URL | openapi_to_agent_skills-0.3.2.tar.gz |
|---|---|
| Size | 16.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
72ed494e56a275c09af545a52dc9f18aac8744a06242ec0fe1ac73b1fea1998a
|
|
BLAKE2b-256 checksum How to use checksums |
ece4ce1ee218f47d8f687a0eae660ff1e1e2fbe1e31239c1cd2dcdd88162dbcd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.10
|
Release files / openapi_to_agent_skills-0.3.2-py3-none-any.whl
| Download URL | openapi_to_agent_skills-0.3.2-py3-none-any.whl |
|---|---|
| Size | 20.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6ce87489251ce2f9d7c6ec193f98710060c4ee667a06b7d723696b4f08131854
|
|
BLAKE2b-256 checksum How to use checksums |
efa0f6ebd395f045fb46d05b95da3a9528ef9b61cc8e80807d30dd60bbead888
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.10
|
Security for openapi-to-agent-skills 0.3.2
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
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.