Helps you build AI agents that handle long sessions well, covering how to manage the context window, compress and hand off summaries, diagnose degraded performance, and evaluate agent output. Each part is a reusable skill you can apply to your own agent.
Claude Code
> /plugin marketplace add muratcankoylan/agent-skills-for-context-engineering> /plugin install context-engineering@context-engineering-marketplace
Codex
$ npx skills add muratcankoylan/agent-skills-for-context-engineering -a codex
Cursor
$ npx skills add muratcankoylan/agent-skills-for-context-engineering -a cursor
Gemini CLI
$ npx skills add muratcankoylan/agent-skills-for-context-engineering -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add muratcankoylan/agent-skills-for-context-engineering$ copilot plugin install context-engineering@context-engineering-marketplace
OpenCode
$ npx skills add muratcankoylan/agent-skills-for-context-engineering -a opencode
Windsurf
$ npx skills add muratcankoylan/agent-skills-for-context-engineering -a windsurf
A comprehensive, open collection of Agent Skills focused on context engineering and harness engineering principles for building production-grade AI agent systems. These skills teach the art and science of curating context, designing agent operating loops, and evaluating agent behavior across any agent platform.
Context engineering is the discipline of managing the language model's context window. Unlike prompt engineering, which focuses on crafting effective instructions, context engineering addresses the holistic curation of all information that enters the model's limited attention budget: system prompts, tool definitions, retrieved documents, message history, and tool outputs.
The fundamental challenge is that context windows are constrained not by raw token capacity but by attention mechanics. As context length increases, models exhibit predictable degradation patterns: the "lost-in-the-middle" phenomenon, U-shaped attention curves, and attention scarcity. Effective context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of desired outcomes.
This repository is cited in academic research as foundational work on static skill architecture:
"While static skills are well-recognized [Anthropic, 2025b; Muratcan Koylan, 2025], MCE is among the first to dynamically evolve them, bridging manual skill engineering and autonomous self-improvement."
These skills establish the foundational understanding required for all subsequent context engineering work.
| Skill | Description |
|---|---|
| context-fundamentals | Understand what context is, why it matters, and the anatomy of context in agent systems |
| context-degradation | Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash |
| context-compression | Design and evaluate compression strategies for long-running sessions |
These skills cover the patterns and structures for building effective agent systems.
| Skill | Description |
|---|---|
| multi-agent-patterns | Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures |
| long-horizon-prompting | NEW Write pseudo-formal task briefs for long-running autonomous agents and parallel orchestrations: exact success predicates, non-counting outcomes, audit-gated return conditions, per-worker handoff contracts, effort floors, and diversity policies, modeled on the published GPT-5.6 Sol Ultra Cycle Double Cover prompt and Sakana AI's MASS workflow contracts |
| memory-systems | Design short-term, long-term, and graph-based memory architectures |
| tool-design | Build tools that agents can use effectively |
| filesystem-context | Use filesystems for dynamic context discovery, tool output offloading, and plan persistence |
| hosted-agents | NEW Build background coding agents with sandboxed VMs, pre-built images, multiplayer support, and multi-client interfaces |
These skills address the ongoing operation and optimization of agent systems.
| Skill | Description |
|---|---|
| context-optimization | Apply compaction, masking, and caching strategies |
| self-managed-context | NEW Give the model read-write control over its own live context: context as an editable file, harness invariants (pinned prefix, edit gate, receipts, budget readouts, rollback), edit-position cache cost and suffix cache reuse, and steering or training context-editing strategy, based on Context Language Models |
| latent-briefing | Share task-relevant orchestrator state with workers via task-guided KV cache compaction when the worker runtime is controllable |
| evaluation | Build evaluation frameworks for agent systems |
| advanced-evaluation | Master LLM-as-a-Judge techniques: direct scoring, pairwise comparison, rubric generation, and bias mitigation |
| harness-engineering | Design autonomous agent harnesses with locked metrics, durable logs, novelty gates, rollback, and human approval boundaries |
| self-improvement-loops | NEW Build loops where the harness itself is the optimization target: RSI, meta-harness search, failure-driven self-edits, evolutionary scaffold search, and acceptance gates for self-modifying systems |
These skills cover the meta-level practices for building LLM-powered projects.
| Skill | Description |
|---|---|
| project-development | Design and build LLM projects from ideation through deployment, including task-model fit analysis, pipeline architecture, and structured output design |
These skills cover formal cognitive modeling for rational agent systems.
| Skill | Description |
|---|---|
| bdi-mental-states | NEW Transform external RDF context into agent mental states (beliefs, desires, intentions) using formal BDI ontology patterns for deliberative reasoning and explainability |
Each skill is structured for efficient context use. At startup, agents load only skill names and descriptions. Full content loads only when a skill is activated for relevant tasks.
These skills focus on transferable principles rather than vendor-specific implementations. The patterns work across Claude Code, Cursor, and any agent platform that supports skills or allows custom instructions.
Scripts and examples demonstrate concepts using Python pseudocode that works across environments without requiring specific dependency installations.
This repository is a Claude Code Plugin Marketplace containing context engineering skills that Claude automatically discovers and activates based on your task context.
Step 1: Add the Marketplace
Run this command in Claude Code to register this repository as a plugin source:
/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering
Step 2: Install the Plugin
Option A - Browse and install:
Browse and install pluginscontext-engineering-marketplacecontext-engineeringInstall nowOption B - Direct install via command:
/plugin install context-engineering@context-engineering-marketplace
This installs all published skills in a single plugin. Skills are activated automatically based on your task context.
| Skill | Activate When |
|---|---|
context-fundamentals | Establishing context-window mental models, planning agent architecture, or explaining how context components affect model behavior |
context-degradation | Diagnosing attention failures, context poisoning, lost-in-middle behavior, or degraded agent performance across long sessions |
context-compression | Preserving useful state while reducing conversation, tool-output, or trajectory size under context pressure |
context-optimization | Improving token efficiency, retrieval precision, prefix reuse, masking, partitioning, or budget allocation for agent systems |
self-managed-context | Letting the model decide what stays in its live context: context-as-a-file editing, self-editing harness invariants, mid-context edit cost under prefix caching, budget readouts and nudges, and steering or training context-editing strategy |
latent-briefing | Sharing orchestrator trajectory with workers via task-guided KV cache compaction when the worker runtime is controllable and the models are compatible |
multi-agent-patterns | Choosing coordination patterns, isolating context across agents, designing handoffs, or evaluating whether parallel agents are justified |
long-horizon-prompting | Writing or evaluating the launch prompt for a long-running autonomous agent or parallel orchestration: success predicates, non-counting outcomes, persistence and stop rules, adversarial audit gates, per-worker output contracts, and portfolio diversity policies |
memory-systems | Persisting cross-session knowledge, tracking entities over time, choosing memory frameworks, or designing retrieval and update semantics |
tool-design | Defining agent-tool contracts, consolidating tool surfaces, improving descriptions, or making tool errors actionable |
filesystem-context | Moving large or durable context into files, creating scratchpads, supporting just-in-time discovery, or coordinating agents through shared artifacts |
hosted-agents | Running coding agents in remote sandboxes, background environments, warm pools, or multiplayer agent infrastructure |
evaluation | Creating deterministic checks, rubrics, regression suites, production monitoring, or quality gates for agent behavior |
advanced-evaluation | Using LLM judges, pairwise comparison, calibration, bias mitigation, or human-aligned quality assessment |
harness-engineering | Designing autonomous loops with locked evaluators, editable surfaces, durable logs, novelty gates, rollback, and approval boundaries |
self-improvement-loops | Building loops that modify themselves: failure-driven harness self-edits, meta-harness search, evolutionary scaffold search, context mechanism evolution, and acceptance gates for self-modification |
project-development | Deciding whether an LLM is appropriate, shaping batch pipelines, creating staged artifacts, or estimating operational cost |
bdi-mental-states | Modeling beliefs, desires, intentions, rational action traces, or neuro-symbolic state transformations for agents |
This repository ships as an Open Plugins plugin. Hosts discover skills from the repo-root skills/ directory (each subdirectory contains a SKILL.md file). The manifest lives at .plugin/plugin.json.
Cursor (recommended):
.plugin/plugin.json and discovers the repo-root skills/ directory through the Open Plugins manifest..cursor/skills/. Do not rely on repository symlinks; they are fragile on Windows and in plugin packaging.Codex / GitHub Copilot CLI / other Open Plugins hosts:
.plugin/plugin.json and discovers all published skills under skills/.Stars on GitHub
View @muratcankoylan’s profileRuns an autonomous loop for SaaS content marketing and copywriting, with commands to initialize, run, check status, and cancel it. A stop hook keeps the loop going when an agent stops.
@muratcankoylanSee 12 agent-skills-for-context-engineering alternatives
A personal AI assistant that runs on your own computer and answers through messaging channels such as Slack, Telegram and WhatsApp. Its skills cover browser automation, canvas panels, app previews and shareable diffs.
@openclawGives your AI agent a learning loop: it turns past work into reusable skills, keeps notes across sessions, and searches its own earlier conversations. It can also run on a cheap server and be reached from chat apps like Telegram.
@nousresearchA single CLAUDE.md file with behavioral guidelines to reduce common LLM coding mistakes, such as overcomplication and unstated assumptions. It is derived from Andrej Karpathy's observations on coding pitfalls and helps Claude Code write, review, and refactor code more carefully.
@forrestchangClaude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by running routine tasks, explaining complex code, and handling git workflows through natural language commands.
@anthropics-2Install it with the command on its page. It includes advanced-evaluation, bdi-mental-states, context-compression. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it