JD.SemanticKernel.Extensions
JerrettDavis/JD.SemanticKernel.Extensions
Extensões Semantic Kernel: skills Claude, hooks, compactação e memória semântica
Ver no GitHubToolkit extensível para Microsoft Semantic Kernel que integra skills do Claude Code, hooks, gerenciamento de contexto e memória semântica em aplicações SK. Oferece compactação de janela de contexto com reranking MMR, decaimento temporal e persistência SQLite para construir agentes IA em produção.
Instalação
npx convez-ai JerrettDavis/JD.SemanticKernel.Extensions1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Carregar skills SKILL.md em aplicações Semantic Kernel
- Integrar hooks do Claude Code (PreToolUse, PostToolUse) como filtros SK
- Gerenciar contexto com compactação automática e sumarização hierárquica
- Implementar memória semântica com MMR reranking e decay temporal
- Descobrir e carregar servidores MCP de múltiplas fontes
Veredito

Solução madura e bem-arquitetada para integração profunda entre Semantic Kernel e Claude Code. Cobre necessidades reais de produção (contexto, memória, hooks), mas exige domínio de C# e SK para aproveitamento pleno.
README
A tradução para o português deste README ainda está na fila.
JD.SemanticKernel.Extensions
An extensible toolkit for Microsoft Semantic Kernel that bridges Claude Code skills, plugins, and hooks into SK applications, and adds context management primitives (compaction, semantic memory) for building production-grade AI agents.
Features
- 📝 Skills — Parse
SKILL.mdfiles (YAML frontmatter + markdown) intoKernelFunctionorPromptTemplate - 🔗 Hooks — Map Claude Code lifecycle events (
PreToolUse,PostToolUse, etc.) to SK'sIFunctionInvocationFilterandIPromptRenderFilter - 📦 Plugins — Load
.claude-plugin/directories with skills, hooks, and MCP configs - 🔌 MCP — Discover MCP servers from Claude Code, Claude Desktop, VS Code, Codex, Copilot, and JD canonical config with a PatternKit-backed provider chain
- 🗜️ Compaction — Transparent context window management with configurable triggers and hierarchical summarization
- 🧠 Memory — Semantic memory with MMR reranking, temporal decay scoring, and query expansion
- 💾 Memory.Sqlite — SQLite-backed persistent memory storage
- 🎯 Fluent API —
UseSkills(),UseHooks(),UsePlugins(),AddCompaction(),AddSemanticMemory()extension methods
Packages
Quick Start
dotnet add package JD.SemanticKernel.Extensions
Load Skills
using JD.SemanticKernel.Extensions.Skills;
var kernel = Kernel.CreateBuilder()
.AddOpenAIChatCompletion("gpt-4o", apiKey)
.UseSkills("./skills/") // Scans for SKILL.md files
.Build();
A SKILL.md file follows the Claude Code / AgentSkills.io format:
---
name: code-reviewer
description: Reviews code for quality issues
allowed-tools: [Read, Grep, Glob]
---
# Code Reviewer
Review the provided code for:
1. Bug risks
2. Security vulnerabilities
3. Performance issues
Input: $ARGUMENTS
Configure Hooks
using JD.SemanticKernel.Extensions.Hooks;
var kernel = Kernel.CreateBuilder()
.AddOpenAIChatCompletion("gpt-4o", apiKey)
.UseHooks(hooks =>
{
hooks.OnFunctionInvoking("Bash|Execute", async ctx =>
{
Console.WriteLine($"Validating: {ctx.Function.Name}");
});
hooks.OnFunctionInvoked("Write|Edit", async ctx =>
{
Console.WriteLine($"Post-edit hook: {ctx.Function.Name}");
});
hooks.OnPromptRendering(async ctx =>
{
Console.WriteLine("Prompt is about to render...");
});
})
.Build();
Load Plugins
using JD.SemanticKernel.Extensions.Plugins;
var kernel = Kernel.CreateBuilder()
.AddOpenAIChatCompletion("gpt-4o", apiKey)
.UsePlugins("./my-plugin/") // Single plugin directory
.UseAllPlugins("./plugins/") // All plugins in directory
.Build();
Plugin directories follow the .claude-plugin/ convention:
my-plugin/
├── .claude-plugin/
│ └── plugin.json # Manifest
├── skills/
│ └── reviewer/SKILL.md # Skills
├── hooks/
│ └── hooks.json # Hooks
└── .mcp.json # MCP servers (future)
Meta-Package (All-in-One)
using JD.SemanticKernel.Extensions;
var kernel = Kernel.CreateBuilder()
.AddOpenAIChatCompletion("gpt-4o", apiKey)
.AddClaudeCodeSkills("./skills/")
.AddClaudeCodePlugin("./my-plugin/")
.AddClaudeCodeHooks(hooks => hooks.OnFunctionInvoking(".*", _ => Task.CompletedTask))
.Build();
Context Compaction
Automatically compress chat history when it grows too large, preserving key context while staying within token limits.
using JD.SemanticKernel.Extensions.Compaction;
var kernel = Kernel.CreateBuilder()
.AddOpenAIChatCompletion("gpt-4o", apiKey)
.Build();
// Register compaction as transparent middleware
kernel.Services.AddCompaction(options =>
{
options.TriggerMode = CompactionTriggerMode.ContextPercentage;
options.Threshold = 0.70; // Compact at 70% of context window
options.MaxContextWindowTokens = 128_000; // Model's context limit
options.PreserveLastMessages = 10; // Always keep recent messages
options.MinMessagesBeforeCompaction = 5; // Don't compact short conversations
});
Trigger modes:
TokenThreshold— Compact when estimated tokens exceed an absolute countContextPercentage— Compact when usage exceeds a percentage of the context window
Token estimation:
var tokens = TokenEstimator.EstimateTokens("Hello world"); // ~2 tokens
var historyTokens = TokenEstimator.EstimateTokens(chatHistory); // Includes overhead
Semantic Memory
Store, search, and retrieve context-relevant information with embedding-based similarity, MMR diversity reranking, and temporal decay scoring.
using JD.SemanticKernel.Extensions.Memory;
// Register with in-memory backend
kernel.Services.AddSemanticMemory(options =>
{
options.DefaultSearchOptions = new MemorySearchOptions
{
TopK = 10,
MinRelevanceScore = 0.7,
UseMmrReranking = true,
MmrLambda = 0.7, // Balance relevance vs diversity
UseTemporalDecay = true,
TemporalDecayRate = 0.01,
};
});
SQLite persistence:
using JD.SemanticKernel.Extensions.Memory.Sqlite;
kernel.Services.AddSqliteMemoryBackend("Data Source=memory.db");
Key capabilities:
- MMR reranking — Maximal Marginal Relevance for diverse search results
- Temporal decay — Recent memories rank higher with configurable decay rate
- Query expansion — Automatically generate alternative queries for broader recall
- Pluggable backends —
InMemoryBackend(default),SqliteMemoryBackend, or implementIMemoryBackend
Hook Event Mapping
| Claude Code Event | SK Filter |
|---|---|
PreToolUse | IFunctionInvocationFilter.OnFunctionInvokingAsync |
PostToolUse | IFunctionInvocationFilter.OnFunctionInvokedAsync |
UserPromptSubmit | IPromptRenderFilter.OnPromptRenderingAsync |
Stop / SubagentStop | IAutoFunctionInvocationFilter |
SessionStart / SessionEnd | IExtensionEventBus (custom) |
PreCompact / Notification | IExtensionEventBus (custom) |
Related Projects
| Project | Description |
|---|---|
| JD.SemanticKernel.Connectors.ClaudeCode | Claude Code authentication provider for SK |
| JD.SemanticKernel.Connectors.GitHubCopilot | GitHub Copilot authentication provider for SK |
Building
dotnet restore
dotnet build
dotnet test
License
MIT © JD