Agent-Skills-for-Context-Engineering

Name: Agent-Skills-for-Context-Engineering
Author: muratcankoylan

17kstars1.4kforks

How to install Agent-Skills-for-Context-Engineering?

muratcankoylan/agent-skills-for-context-engineering/agent-skills-for-context-engineering

$npx -y skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill Agent-Skills-for-Context-Engineering

Installs into the current project.

Summary

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating

Files · 1

View on GitHub

SKILL.md

1	# Agent Skills for Context Engineering
2
3	This collection provides structured guidance for building production-grade AI agent systems through effective context engineering.
4
5	## When to Activate
6
7	Activate these skills when:
8	- Building new agent systems from scratch
9	- Optimizing existing agent performance
10	- Debugging context-related failures
11	- Designing multi-agent architectures
12	- Creating or evaluating tools for agents
13	- Implementing memory and persistence layers
14	- Designing autonomous research or evaluation harnesses
15
16	## Skill Map
17
18	### Foundational Context Engineering
19
20	Understanding Context Fundamentals
21	Context is not just prompt text—it is the complete state available to the language model at inference time, including system instructions, tool definitions, retrieved documents, message history, and tool outputs. Effective context engineering means understanding what information truly matters for the task at hand and curating that information for maximum signal-to-noise ratio.
22
23	Recognizing Context Degradation
24	Language models exhibit predictable degradation patterns as context grows: the "lost-in-middle" phenomenon where information in the center of context receives less attention; U-shaped attention curves that prioritize beginning and end; context poisoning when errors compound; and context distraction when irrelevant information overwhelms relevant content.
25
26	### Architectural Patterns
27
28	Multi-Agent Coordination
29	Production multi-agent systems converge on three dominant patterns: supervisor/orchestrator architectures with centralized control, peer-to-peer swarm architectures for flexible handoffs, and hierarchical structures for complex task decomposition. The critical insight is that sub-agents exist primarily to isolate context rather than to simulate organizational roles.
30
31	Long-Horizon Prompting
32	Long-running autonomous agents and parallel orchestrations succeed or fail on the launch prompt. Pseudo-formal task briefs specify success predicates, non-counting outcomes, persistence rules with audit-gated return conditions, effort floors, diversity policies for parallel portfolios, and contamination guards, applying the discipline of formal verification linguistically to problems with no machine-checkable success condition.
33
34	Memory System Design
35	Memory architectures range from simple scratchpads to sophisticated temporal knowledge graphs. Vector RAG provides semantic retrieval but loses relationship information. Knowledge graphs preserve structure but require more engineering investment. The file-system-as-memory pattern enables just-in-time context loading without stuffing context windows.
36
37	Filesystem-Based Context
38	The filesystem provides a single interface for storing, retrieving, and updating effectively unlimited context. Key patterns include scratch pads for tool output offloading, plan persistence for long-horizon tasks, sub-agent communication via shared files, and dynamic skill loading. Agents use `ls`, `glob`, `grep`, and `read_file` for targeted context discovery, often outperforming semantic search for structural queries.
39
40	Hosted Agent Infrastructure
41	Background coding agents run in remote sandboxed environments rather than on local machines. Key patterns include pre-built environment images refreshed on regular cadence, warm sandbox pools for instant session starts, filesystem snapshots for session persistence, and multiplayer support for collaborative agent sessions. Critical optimizations include allowing file reads before git sync completes (blocking only writes), predictive sandbox warming when users start typing, and self-spawning agents for parallel task execution.
42
43	Tool Design Principles
44	Tools are contracts between deterministic systems and non-deterministic agents. Effective tool design follows the consolidation principle (prefer single comprehensive tools over multiple narrow ones), returns contextual information in errors, supports response format options for token efficiency, and uses clear namespacing.
45
46	### Operational Excellence
47
48	Context Compression
49	When agent sessions exhaust memory, compression becomes mandatory. The correct optimization target is tokens-per-task, not tokens-per-request. Structured summarization with explicit sections for files, decisions, and next steps preserves more useful information than aggressive compression. Artifact trail integrity remains the weakest dimension across all compression methods.
50
51	Context Optimization
52	Techniques include compaction (summarizing context near limits), observation masking (replacing verbose tool outputs with references), prefix caching (reusing KV blocks

People who liked this also viewed

6 picks

Type

Agent-Skills-for-Context-Engineering

17kstars1.4kforks

View on GitHub

How to install Agent-Skills-for-Context-Engineering?

muratcankoylan/agent-skills-for-context-engineering/agent-skills-for-context-engineering

$npx -y skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill Agent-Skills-for-Context-Engineering

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Agent Skills for Context Engineering
2
3	This collection provides structured guidance for building production-grade AI agent systems through effective context engineering.
4
5	## When to Activate
6
7	Activate these skills when:
8	- Building new agent systems from scratch
9	- Optimizing existing agent performance
10	- Debugging context-related failures
11	- Designing multi-agent architectures
12	- Creating or evaluating tools for agents
13	- Implementing memory and persistence layers
14	- Designing autonomous research or evaluation harnesses
15
16	## Skill Map
17
18	### Foundational Context Engineering
19
20	Understanding Context Fundamentals
21	Context is not just prompt text—it is the complete state available to the language model at inference time, including system instructions, tool definitions, retrieved documents, message history, and tool outputs. Effective context engineering means understanding what information truly matters for the task at hand and curating that information for maximum signal-to-noise ratio.
22
23	Recognizing Context Degradation
24	Language models exhibit predictable degradation patterns as context grows: the "lost-in-middle" phenomenon where information in the center of context receives less attention; U-shaped attention curves that prioritize beginning and end; context poisoning when errors compound; and context distraction when irrelevant information overwhelms relevant content.
25
26	### Architectural Patterns
27
28	Multi-Agent Coordination
29	Production multi-agent systems converge on three dominant patterns: supervisor/orchestrator architectures with centralized control, peer-to-peer swarm architectures for flexible handoffs, and hierarchical structures for complex task decomposition. The critical insight is that sub-agents exist primarily to isolate context rather than to simulate organizational roles.
30
31	Long-Horizon Prompting
32	Long-running autonomous agents and parallel orchestrations succeed or fail on the launch prompt. Pseudo-formal task briefs specify success predicates, non-counting outcomes, persistence rules with audit-gated return conditions, effort floors, diversity policies for parallel portfolios, and contamination guards, applying the discipline of formal verification linguistically to problems with no machine-checkable success condition.
33
34	Memory System Design
35	Memory architectures range from simple scratchpads to sophisticated temporal knowledge graphs. Vector RAG provides semantic retrieval but loses relationship information. Knowledge graphs preserve structure but require more engineering investment. The file-system-as-memory pattern enables just-in-time context loading without stuffing context windows.
36
37	Filesystem-Based Context
38	The filesystem provides a single interface for storing, retrieving, and updating effectively unlimited context. Key patterns include scratch pads for tool output offloading, plan persistence for long-horizon tasks, sub-agent communication via shared files, and dynamic skill loading. Agents use `ls`, `glob`, `grep`, and `read_file` for targeted context discovery, often outperforming semantic search for structural queries.
39
40	Hosted Agent Infrastructure
41	Background coding agents run in remote sandboxed environments rather than on local machines. Key patterns include pre-built environment images refreshed on regular cadence, warm sandbox pools for instant session starts, filesystem snapshots for session persistence, and multiplayer support for collaborative agent sessions. Critical optimizations include allowing file reads before git sync completes (blocking only writes), predictive sandbox warming when users start typing, and self-spawning agents for parallel task execution.
42
43	Tool Design Principles
44	Tools are contracts between deterministic systems and non-deterministic agents. Effective tool design follows the consolidation principle (prefer single comprehensive tools over multiple narrow ones), returns contextual information in errors, supports response format options for token efficiency, and uses clear namespacing.
45
46	### Operational Excellence
47
48	Context Compression
49	When agent sessions exhaust memory, compression becomes mandatory. The correct optimization target is tokens-per-task, not tokens-per-request. Structured summarization with explicit sections for files, decisions, and next steps preserves more useful information than aggressive compression. Artifact trail integrity remains the weakest dimension across all compression methods.
50
51	Context Optimization
52	Techniques include compaction (summarizing context near limits), observation masking (replacing verbose tool outputs with references), prefix caching (reusing KV blocks

People who liked this also viewed

6 picks

Type