mixle.inference.skill module

Package a fitted model or callable as a reusable skill.

skill wraps a model, subgraph, or plain callable as a named Skill and stores it in a SkillRegistry. Skills carry description, tags, provenance, and any estimation certificate inherited from the wrapped object. Each skill is bound to stable implementation, artifact-state, and descriptor digests; registries reject a skill whose executable or bound state has drifted.

find(query) ranks skills by lexical overlap against the skill name, description, and tags. SkillRegistry.index() can also mirror skills into a Substrate when a workflow wants retrieval over the same capability catalog.

The wrapped callable is resolved from the object: explicit call= wins, then predict or __call__, then sampler for generative models.

class Skill(name, call, description='', tags=(), certificate=None, provenance=<factory>, implementation_digest='', artifact_digest='', descriptor_digest='', _artifact=None)[source]

Bases: object

A named, described, provenanced callable derived from a fitted artifact (or a plain function).

Parameters:
property guarantee: Any | None

The inherited estimation guarantee, if this skill wraps a certified model.

score(query)[source]

Lexical overlap of query with this skill’s name/description/tags, in [0, 1].

Parameters:

query (str)

Return type:

float

verify_identity()[source]

Whether executable code, bound state, and descriptive policy still match this skill.

Return type:

bool

class SkillRegistry[source]

Bases: object

A findable collection of skills – register once, retrieve by name or by query.

add(sk)[source]

Register a skill and return it for chaining.

Parameters:

sk (Skill)

Return type:

Skill

get(name)[source]

Return a registered skill by exact name.

Parameters:

name (str)

Return type:

Skill

all()[source]

Return all registered skills in insertion order.

Return type:

list[Skill]

find(query, k=5)[source]

The best k skills for query by lexical overlap (highest score first, ties by name).

Parameters:
Return type:

list[Skill]

best(query)[source]

The single best-matching skill for query (or None if nothing overlaps).

Parameters:

query (str)

Return type:

Skill | None

index(substrate)[source]

Mirror every skill into a Substrate for embedding-grade recall.

The registry’s own find is a lexical matcher; when a corpus grows past that, index the skills as artifact items and retrieve through the substrate instead. Returns the item ids.

Parameters:

substrate (Any)

Return type:

list[str]

default_registry()[source]

The process-wide default registry skill() writes to when no registry is given.

Return type:

SkillRegistry

skill(name, obj, *, description='', tags=(), call=None, provenance=None, registry=None)[source]

Package obj (a fitted model, a CreatedModel, or a function) as a reusable Skill and register it (see module docstring).

The estimation certificate is inherited from obj.certificate when present (so a certified model yields a certified skill). call overrides how the skill is invoked; otherwise a model verb (predict / __call__ / sampler) is used. The skill is added to registry (or the process default) and returned.

Parameters:
Return type:

Skill