Zum Hauptinhalt springen
Dieser Inhalt ist noch nicht in Ihrer Sprache verfügbar und wird auf Englisch angezeigt.

Latent Briefing

Skill Aktiv

This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.

Zweck

To provide a detailed explanation and implementation guidance for using Latent Briefing to optimize memory sharing and reduce token costs in hierarchical multi-agent systems.

Funktionen

  • Explains representation-level memory sharing via KV cache compaction.
  • Details the adaptation of Attention Matching for multi-agent inference.
  • Discusses three inference-time modifications: task-guided queries, shared masks, and MAD thresholding.
  • Outlines infrastructure preconditions and decision frameworks for choosing memory sharing mechanisms.

Anwendungsfälle

  • Designing orchestrator-worker systems needing to share prior state efficiently.
  • Evaluating KV cache compaction as an alternative to text summarization for cross-agent state transfer.
  • Debugging token explosion in recursive or hierarchical agent graphs.
  • Implementing or studying task-conditioned selective retention in LLM inference.

Nicht-Ziele

  • Replacing text-based summarization or RAG where those methods are sufficient or preferable.
  • Providing a deployable tool; this skill is for conceptual understanding and implementation guidance.
  • Working with API-only stacks where KV state is inaccessible.

Practical Utility

  • info:Production readinessThe skill outlines a detailed technical approach and use cases, but its readiness for production hinges on the user's ability to control the worker inference runtime for KV state manipulation.

Maintenance

  • warning:Commit recencyThe last commit was on 2026-04-14, over 3 months ago, suggesting potential unmaintained status.

Trust

  • warning:Issues Attention6 issues opened and 2 closed in the last 90 days, indicating a low closure rate (33%) and potentially slow maintainer response.

Installation

Zuerst Marketplace hinzufügen

/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering
/plugin install Agent-Skills-for-Context-Engineering@context-engineering-marketplace

Qualitätspunktzahl

75 /100
Analysiert about 17 hours ago

Vertrauenssignale

Letzter Commitabout 1 month ago
Sterne15.6k
LizenzMIT
Status
Quellcode ansehen

Ähnliche Erweiterungen

Context Optimization

100

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.

Skill
muratcankoylan

Stream Chain

99

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

Skill
ruvnet

Context Compression

100

This skill should be used when the user asks to "compress context", "summarize conversation history", "implement compaction", "reduce token usage", or mentions context compression, structured summarization, tokens-per-task optimization, or long-running agent sessions exceeding context limits.

Skill
muratcankoylan

Init

100

Erstellt, aktualisiert oder optimiert eine AGENTS.md-Datei für ein Repository mit minimalen, hochgradig aussagekräftigen Anweisungen, die nicht entdeckbare Codierungs-Konventionen, Eigenheiten der Werkzeuge, Workflow-Präferenzen und projektspezifische Regeln abdecken, die Agenten nicht aus dem Code ableiten können. Verwenden Sie dies beim Einrichten von Agent-Anweisungen oder der Claude-Konfiguration für ein neues Repository, wenn eine vorhandene AGENTS.md zu lang, generisch oder veraltet ist, wenn Agenten wiederholt vermeidbare Fehler machen oder wenn sich die Repository-Workflows geändert haben und die Agent-Konfiguration bereinigt werden muss. Wendet einen Entdeckbarkeitsfilter an – der alles weglässt, was Claude aus README, Code, Konfiguration oder Verzeichnisstruktur lernen kann – und ein Qualitätstor, um zu überprüfen, ob jede Zeile korrekt und betrieblich relevant bleibt.

Skill
mcollina

External Context

100

Invoke parallel document-specialist agents for external web searches and documentation lookup

Skill
Yeachan-Heo

Swarm Orchestration

100

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Skill
ruvnet