By FVossebeld
Microsoft-native adaptation of context engineering for production-grade agent systems. Bundles the core context and harness engineering skills with Azure and Microsoft Foundry defaults for managed hosted agents, Foundry IQ, Foundry Toolbox, Azure AI Search, Fabric, Entra identity, Responsible AI guardrails, publishing, and memory/state. Ships with a researcher operating system (rubrics, mechanism registry, claim provenance, run state machine, adversarial benchmarks, continuous loop).
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup policies for context stored outside the prompt.
This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR preparation, and human approval boundaries.
This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, self-spawning agents, or Modal-style sandboxes.
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.
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization.
A Microsoft-native adaptation of the Agent Skills for Context Engineering collection.
The default context-engineering package now installs both the core context-engineering skills and the Azure AI / Microsoft Foundry implementation skills. This is not a separate extension layered on afterward. The standard distribution is intended to help agents move from mechanism-level context engineering to Microsoft-native architecture choices by default: Microsoft Foundry Agent Service and Hosted Agents, Foundry IQ, Foundry Toolbox, Azure AI Search, Fabric, Entra identity, Responsible AI guardrails, publishing, and Azure memory/state.
For Claude Code, copy and run these two commands:
/plugin marketplace add FVossebeld/agent-skills-for-context-engineering
/plugin install context-engineering@context-engineering-marketplace
That installs the full standard package: 24 skills, including the Azure and Microsoft-native adaptation skills. There is no separate Azure install step.
For Open Plugins compatible tools, use this manifest URL:
https://raw.githubusercontent.com/FVossebeld/agent-skills-for-context-engineering/main/.plugin/plugin.json
For local use or inspection:
git clone https://github.com/FVossebeld/agent-skills-for-context-engineering.git
Context engineering is the discipline of curating everything that enters a model's context window: system prompts, tool definitions, retrieved documents, message history, tool outputs, memory, files, and operating-loop state. The core skills teach the transferable mechanisms. The Azure skills bind those mechanisms to Microsoft products, identity boundaries, deployment surfaces, governance controls, and operational caveats.
Default bias:
skills/azure/skills/researcher/ for deterministic gates, mechanism provenance, activation fixtures, and benchmark reportingThe default Claude marketplace manifest is:
.claude-plugin/marketplace.json
The default Open Plugins manifest is:
.plugin/plugin.json
The older Azure-only manifests remain available as subset install paths for environments that want only Microsoft-native binding skills, but they are no longer the primary distribution contract:
.plugin/plugin.azure.json
.claude-plugin/marketplace.azure.json
npx claudepluginhub fvossebeld/agent-skills-for-context-engineering --plugin context-engineeringUltra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.