How do I install the Semantic Kernel Foundation skill?

Run npx skillmds@latest add ryan-brosas/semantic-kernel-foundation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Semantic Kernel Foundation safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Semantic Kernel Foundation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Semantic Kernel Foundation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Semantic Kernel Foundation?

ryan-brosas (@ryan-brosas) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Semantic Kernel Foundation by ryan-brosas

Name: Semantic Kernel Foundation
Author: ryan-brosas

Semantic Kernel Foundation

Use when porting Semantic Kernel's Python kernel-core machinery — filter call-stack onion, corrective tool-call feedback, bounded auto-invoke loop, exception smuggling, OTel-gated telemetry, decorator-time metadata, argument coercion, copy-on-add plugin registries, the {{...}} prompt-template block engine, HTML trust gates, AI service selection/registration, tool-view generation, prompt-config parsing ladders, Jinja2/Handlebars helper-binding/sandbox, streaming auto-invoke twin, .NET method-function/filter mirrors, and the agents plane (Assistant run lifecycle, requires-action handoff, Responses auto-invoke loop, agent merge twins, function-choice gate, Azure AI run lifecycle + approval gate, Azure streaming event plane, request-prep flattening, handoff turn-taking, .NET FunctionChoiceBehavior twin, the AutoGen-style actor runtime (envelope queue, intervention gate, routed handlers, subscriptions, serialization registry, telemetry links), Responses streaming item mapping, and the AgentChannel protocol).

ryan-brosas 358b4be 67 files · 370.1 KB Updated Sep 17, 2026

File contents

Semantic Kernel: kernel-core invocation foundation

Foundation contract

This is a cold, source-specific foundation, not an operational procedure. It is historical, revision-pinned evidence rather than timeless guidance. Current project source, tests, requirements, and runtime behavior outrank this projection and decide what ships.

Provenance and revision

Source record: semantic-kernel; portable upstream identity, license, coverage caveats, and retrieval history are preserved in the index.
Recorded revision: main@b39d95a34435f4c1d55dd00c86120ce118d847e1.
Full provenance, coverage caveats, boundaries, and preserved evidence: references/index.md.

Topic map

Representative topics: Filter onion; Corrective feedback; Bounded auto- invoke; Error absorption; Stream smuggling; Telemetry wrapper; Decorator contract; Type parsing ladder.
Scope and retrieval questions: references/index.md#use-this-for.
Complete capsule chooser: references/index.md#load-the-matching-source-dump.
Detailed grouped map: references/index.md#capsule-map.
Source limitations and portability boundaries: references/index.md#boundaries.

Retrieval

Open the index, choose one capsule matching the active question, and load only that capsule. Revalidate its cited source and revision before relying on it. Do not bulk-load the inventory, treat historical claims as current truth, or apply this foundation as a procedure.

---name: semantic-kernel-foundationdescription: Use when porting Semantic Kernel's Python kernel-core machinery — filter call-stack onion, corrective tool-call feedback, bounded auto-invoke loop, exception smuggling, OTel-gated telemetry, decorator-time metadata, argument coercion, copy-on-add plugin registries, the {{...}} prompt-template block engine, HTML trust gates, AI service selection/registration, tool-view generation, prompt-config parsing ladders, Jinja2/Handlebars helper-binding/sandbox, streaming auto-invoke twin, .NET method-function/filter mirrors, and the agents plane (Assistant run lifecycle, requires-action handoff, Responses auto-invoke loop, agent merge twins, function-choice gate, Azure AI run lifecycle + approval gate, Azure streaming event plane, request-prep flattening, handoff turn-taking, .NET FunctionChoiceBehavior twin, the AutoGen-style actor runtime (envelope queue, intervention gate, routed handlers, subscriptions, serialization registry, telemetry links), Responses streaming item mapping, and the AgentChannel protocol).---# Semantic Kernel: kernel-core invocation foundation## Foundation contractThis is a cold, source-specific foundation, not an operational procedure. It ishistorical, revision-pinned evidence rather than timeless guidance. Currentproject source, tests, requirements, and runtime behavior outrank thisprojection and decide what ships.## Provenance and revision- Source record: `semantic-kernel`; portable upstream identity, license, coverage caveats, and retrieval history are preserved in the index.- Recorded revision: `main@b39d95a34435f4c1d55dd00c86120ce118d847e1`.- Full provenance, coverage caveats, boundaries, and preserved evidence: `references/index.md`.## Topic map- Representative topics: Filter onion; Corrective feedback; Bounded auto- invoke; Error absorption; Stream smuggling; Telemetry wrapper; Decorator contract; Type parsing ladder.- Scope and retrieval questions: `references/index.md#use-this-for`.- Complete capsule chooser: `references/index.md#load-the-matching-source-dump`.- Detailed grouped map: `references/index.md#capsule-map`.- Source limitations and portability boundaries: `references/index.md#boundaries`.## RetrievalOpen the index, choose one capsule matching the active question, and load onlythat capsule. Revalidate its cited source and revision before relying on it. Donot bulk-load the inventory, treat historical claims as current truth, or applythis foundation as a procedure.

Frequently asked questions