SAMSkillPlugin

SAM model of the SkillPlugin kind, generated from the Smarter platform’s JSON Schema.

Do not edit: run scripts/generate_sam_models.py. See smarter.models.sam.

class smarter.models.sam.skillplugin.SAMDependency(*, kind: str, name: str, **extra_data: Any)

Bases: SAMModel

A resource that depends on the resource that a manifest describes.

kind: str

Kind[String]: The SAM kind of the resource that depends on this resource, e.g. LLMClient.

Read only.

name: str

Name[String]: The name of the resource that depends on this resource.

Read only.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

class smarter.models.sam.skillplugin.SAMPluginCommonMetadata(*, annotations: None | list[dict[str, str | int | float | bool | date | datetime | UUID | bytes | list | dict[str, Any]]] = None, description: str | None, name: str, pluginClass: str, tags: list[str] | None = None, version: str | None, **extra_data: Any)

Bases: SAMModel

Smarter API Plugin Manifest - common Metadata class.

annotations: None | list[dict[str, str | int | float | bool | date | datetime | UUID | bytes | list | dict[str, Any]]]

The manifest annotations.

Used for storing arbitrary metadata as

key-value pairs. Example: [{‘smarter.sh/test-manifest/project-name’: ‘Scooby dooby do’}]. The key should be a valid url-friendly string. The value accepts multi-line string values (YAML block scalars) and various scalar types including str, int, float, bool, datetime.date, datetime.datetime, decimal.Decimal, uuid.UUID, bytes, list, dict.

description: str | None

The description for this resource.

Be brief. Keep it under 255 characters.

name: str

The camelCase name of the manifest resource.

pluginClass: str

The class of the plugin.

one of: [‘api’, ‘imagesearch’, ‘skill’, ‘sql’, ‘static’, ‘websearch’]

tags: list[str] | None

The tags of the manifest.

Used for generic resource categorization and search. Example: [‘tag1’, ‘tag2’]

version: str | None

The semantic version of the manifest.

Example: 0.1.0

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

class smarter.models.sam.skillplugin.SAMPluginCommonSpecPrompt(*, maxTokens: Annotated[int, Gt(gt=0)] | None = 2048, model: str | None = 'gpt-6-luna', provider: str | None = 'openai', systemRole: Annotated[str, StringConstraints(strip_whitespace=None, to_upper=None, to_lower=None, strict=None, min_length=None, max_length=32768, pattern=None, ascii_only=None)], temperature: Annotated[float, None, Interval(gt=None, ge=0.0, lt=None, le=1.0), None, None] | None = 1.0, **extra_data: Any)

Bases: SAMModel

Smarter API Plugin Manifest - Spec - Prompt class.

maxTokens: PositiveInt | None

Plugin.spec.prompt.maxTokens[int].

Optional. The maxTokens of the Plugin. Defaults to 2048. The maximum number of tokens the LLM should generate in the prompt response.

model: str | None

Plugin.spec.prompt.model[str] Optional.

The model of the Plugin. Defaults to gpt-6-luna. Must be one of: [‘chat-latest’, ‘gpt-4.1’, ‘gpt-4.1-2025-04-14’, ‘gpt-4.1-mini’, ‘gpt-4.1-mini-2025-04-14’, ‘gpt-4o’, ‘gpt-4o-2024-08-06’, ‘gpt-4o-2024-11-20’, ‘gpt-4o-mini’, ‘gpt-4o-mini-2024-07-18’, ‘gpt-5-search-api’, ‘gpt-5-search-api-2025-10-14’, ‘gpt-5.2’, ‘gpt-5.2-2025-12-11’, ‘gpt-5.4’, ‘gpt-5.4-2026-03-05’, ‘gpt-5.4-mini’, ‘gpt-5.4-mini-2026-03-17’, ‘gpt-5.5’, ‘gpt-5.5-2026-04-23’, ‘gpt-5.6-luna’, ‘gpt-5.6-sol’, ‘gpt-5.6-terra’, ‘gpt-6-astra’, ‘gpt-6-luna’, ‘gpt-6-sol’, ‘gpt-6.1-sol’]

provider: str | None

Plugin.spec.prompt.provider[str].

Optional. The provider of the LLM. Defaults to openai. The provider is the vendor name for the LLM service that will be used to generate the prompt response.

systemRole: constr(max_length=32768)

Plugin.spec.prompt.systemRole[str].

Required. The system role that the Plugin will use for the LLM text completion prompt. Be verbose and specific. Ensure that systemRole accurately conveys to the LLM how you want it to use the Plugin data that is returned. The maximum length is 32768 characters.

temperature: confloat(ge=0.0, le=1.0) | None

Plugin.spec.prompt.temperature[float] Optional.

The temperature of the Plugin. Defaults to 1.0. Should be between 0 and 1.0. The higher the temperature, the more creative the response. The lower the temperature, the more predictable the response.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

class smarter.models.sam.skillplugin.SAMPluginCommonSpecSelector(*, directive: str, searchTerms: list[str] | None = None, **extra_data: Any)

Bases: SAMModel

Smarter API Plugin Manifest - Spec - Selector class.

directive: str

Plugin.spec.selector.directive[str]: Required.

the kind of selector directive to use for the Plugin. Must be one of: [‘search_terms’, ‘always’, ‘llm’]

searchTerms: list[str] | None

Plugin.spec.selector.searchTerms[list].

Optional. The keyword search terms to use when the Plugin directive is ‘search_terms’. Keywords are most effective when constrained to 1 or 2 words each and lists are limited to a few dozen items.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

class smarter.models.sam.skillplugin.SAMPluginCommonStatus(*, accountNumber: str, created: datetime, dependencies: list[SAMDependency] | None = None, modified: datetime, recordLocator: str, username: str, **extra_data: Any)

Bases: SAMModel

Smarter API Plugin Manifest - Status class.

accountNumber: str

Plugin.status.account_number: The account owner of this Plugin.

Read only.

created: datetime

The date in which this resource was created.

Read only.

dependencies: list[SAMDependency] | None

Dependencies[List]: The resources that depend on this resource, and that must be deleted, or stop referring to it, before it can be deleted.

Lists only the resources that you can read. Read only.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

modified: datetime

The date in which this resource was most recently changed.

Read only.

recordLocator: str

RecordLocator[String]: An optional identifier used to locate the resource record associated with this manifest.

Read only.

username: str

Plugin.status.account_number: The Smarter user who created this Plugin.

Read only.

class smarter.models.sam.skillplugin.SkillSource(*, url: str, **extra_data: Any)

Bases: SAMModel

Smarter API - SkillPlugin.spec.skillData.source: the remote location of a skill.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

url: str

SkillPlugin.spec.source.url[str]: the https URL of the skill.

Either a GitHub URL of a skill directory (e.g. https://github.com/anthropics/skills/tree/main/skills/pdf) or of a SKILL.md file, or any https URL of a SKILL.md file. The skill and its bundled files are retrieved when the manifest is applied.

class smarter.models.sam.skillplugin.SkillData(*, resources: dict[str, str | None] | None = None, skill: str | None = None, source: SkillSource | None = None, **extra_data: Any)

Bases: SAMModel

Smarter API - SkillPlugin.spec.skillData: an Agent Skill.

Exactly one of skill or source is required.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

resources: dict[str, str | None] | None

SkillPlugin.spec.resources[obj]: the skill’s bundled files, e.g. references/, scripts/ and assets/, keyed by their path relative to the skill root, as SKILL.md refers to them.

Only valid with ‘skill’.

skill: str | None

SkillPlugin.spec.skill[str]: the verbatim contents of a SKILL.md file: YAML frontmatter, containing at least ‘name’ and ‘description’, followed by Markdown instructions.

Use a YAML literal block scalar (|) to preserve the Markdown exactly. See https://agentskills.io/specification

source: SkillSource | None

SkillPlugin.spec.source[obj]: the remote location of the skill, in lieu of ‘skill’.

class smarter.models.sam.skillplugin.SAMSkillPluginSpec(*, prompt: SAMPluginCommonSpecPrompt, selector: SAMPluginCommonSpecSelector, skillData: SkillData, **extra_data: Any)

Bases: SAMModel

Smarter API Manifest - SkillPlugin.spec.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

prompt: SAMPluginCommonSpecPrompt

Plugin.spec.prompt[obj]: the LLM prompt engineering to apply to the Plugin.

selector: SAMPluginCommonSpecSelector

Plugin.spec.selector[obj]: the selector logic to use for the Plugin.

skillData: SkillData

SkillPlugin.spec.skillData[obj]: the Agent Skill that the SkillPlugin provides to the LLM.

class smarter.models.sam.skillplugin.SAMSkillPlugin(*, apiVersion: str, kind: str, metadata: SAMPluginCommonMetadata, spec: SAMSkillPluginSpec, status: SAMPluginCommonStatus | None = None, **extra_data: Any)

Bases: SAMModel

Smarter API Manifest - Skill Connection Model.

model_config = {'extra': 'allow', 'populate_by_name': True, 'protected_namespaces': (), 'regex_engine': 'python-re', 'use_attribute_docstrings': True}

Configuration for the model, should be a dictionary conforming to [`ConfigDict`][pydantic.config.ConfigDict].

apiVersion: str

ApiVersion[String]: Required.

The API version of the AbstractSAMBase.

kind: str

Kind[String]: Required.

The kind of resource described by the manifest.

metadata: SAMPluginCommonMetadata

Plugin.metadata[obj]: Required, the Plugin metadata.

spec: SAMSkillPluginSpec

SkillPlugin.spec[obj]: Required, the SkillPlugin specification.

status: SAMPluginCommonStatus | None

Plugin.status[obj]: Optional, Read-only.

Stateful status information about the Plugin.