context-fundamentals

Name: context-fundamentals
Author: muratcankoylan

54installs1.4kforks

How to install context-fundamentals?

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

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

Installs into the current project.

Summary

This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped attention curve, why context quality matters more than quantity, and the mental mode

Files · 1

View on GitHub

SKILL.md

1	# Context Engineering Fundamentals
2
3	Context is the complete state available to a language model at inference time: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Context engineering is the discipline of curating the smallest high-signal token set that maximizes the likelihood of desired outcomes.
4
5	This skill is the conceptual foundation that every other skill in the collection builds on. It explains what context is, how attention mechanics work, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. It does not own operational work: debugging attention failures belongs to `context-degradation`, token-efficiency tactics belong to `context-optimization`, conversation summarization belongs to `context-compression`, file-based offloading belongs to `filesystem-context`, and project-shape decisions belong to `project-development`.
6
7	## When to Activate
8
9	Activate this skill when the work is conceptual:
10
11	- Explaining what context is and how attention mechanics constrain agent behavior.
12	- Onboarding new contributors who need the mental models before diving into operational skills.
13	- Reasoning about a context-related design decision from first principles (what does this constraint mean, why does this trade-off exist) before picking a specific tactic.
14	- Writing or reviewing documentation that needs to ground operational guidance in the underlying mechanics.
15
16	Do not activate this skill for operational work. The specialized skills handle the doing:
17
18	- Diagnosing lost-in-middle, context poisoning, or attention failures: `context-degradation`.
19	- Reducing token cost via masking, partitioning, prefix caching, budgets: `context-optimization`.
20	- Compressing a long session into a handoff summary: `context-compression`.
21	- Offloading large tool outputs or maintaining a durable scratchpad: `filesystem-context`.
22	- Deciding the shape of an LLM project or pipeline: `project-development`.
23
24	## Core Concepts
25
26	Treat context as a finite attention budget, not a storage bin. Every token added competes for the model's attention and depletes a budget that cannot be refilled mid-inference. The engineering problem is maximizing utility per token against three constraints: the hard token limit, the softer effective-capacity ceiling, and the U-shaped attention curve that penalizes information placed in the middle of context (claim-context-degradation-lost-middle-ruler).
27
28	Apply four principles when assembling context:
29
30	1. Informativity over exhaustiveness — include only what matters for the current decision; design systems that can retrieve additional information on demand.
31	2. Position-aware placement — place critical constraints at the beginning and end of context because long-context evaluations show middle-position information is less reliably recovered than edge-position information (claim-context-degradation-lost-middle-ruler).
32	3. Progressive disclosure — load skill names and summaries at startup; load full content only when a skill activates for a specific task.
33	4. Iterative curation — context engineering is not a one-time prompt-writing exercise but an ongoing discipline applied every time content is passed to the model.
34
35	## Detailed Topics
36
37	### The Anatomy of Context
38
39	System Prompts
40	Organize system prompts into distinct sections using XML tags or Markdown headers (background, instructions, tool guidance, output format). System prompts persist throughout the conversation, so place the most critical constraints at the beginning and end where attention is strongest.
41
42	Calibrate instruction altitude to balance two failure modes. Too-low altitude hardcodes brittle logic that breaks when conditions shift. Too-high altitude provides vague guidance that fails to give concrete signals for desired behavior. Aim for heuristic-driven instructions: specific enough to guide behavior, flexible enough to generalize — for example, numbered steps with room for judgment at each step.
43
44	Start minimal, then add instructions reactively based on observed failure modes rather than preemptively stuffing edge cases. Curate diverse, canonical few-shot examples that portray expected behavior instead

People who liked this also viewed

6 picks

Type

context-fundamentals

54installs1.4kforks

View on GitHub

How to install context-fundamentals?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Context Engineering Fundamentals
2
3	Context is the complete state available to a language model at inference time: system instructions, tool definitions, retrieved documents, message history, and tool outputs. Context engineering is the discipline of curating the smallest high-signal token set that maximizes the likelihood of desired outcomes.
4
5	This skill is the conceptual foundation that every other skill in the collection builds on. It explains what context is, how attention mechanics work, why context quality matters more than quantity, and the mental models needed to interpret every other context-engineering decision. It does not own operational work: debugging attention failures belongs to `context-degradation`, token-efficiency tactics belong to `context-optimization`, conversation summarization belongs to `context-compression`, file-based offloading belongs to `filesystem-context`, and project-shape decisions belong to `project-development`.
6
7	## When to Activate
8
9	Activate this skill when the work is conceptual:
10
11	- Explaining what context is and how attention mechanics constrain agent behavior.
12	- Onboarding new contributors who need the mental models before diving into operational skills.
13	- Reasoning about a context-related design decision from first principles (what does this constraint mean, why does this trade-off exist) before picking a specific tactic.
14	- Writing or reviewing documentation that needs to ground operational guidance in the underlying mechanics.
15
16	Do not activate this skill for operational work. The specialized skills handle the doing:
17
18	- Diagnosing lost-in-middle, context poisoning, or attention failures: `context-degradation`.
19	- Reducing token cost via masking, partitioning, prefix caching, budgets: `context-optimization`.
20	- Compressing a long session into a handoff summary: `context-compression`.
21	- Offloading large tool outputs or maintaining a durable scratchpad: `filesystem-context`.
22	- Deciding the shape of an LLM project or pipeline: `project-development`.
23
24	## Core Concepts
25
26	Treat context as a finite attention budget, not a storage bin. Every token added competes for the model's attention and depletes a budget that cannot be refilled mid-inference. The engineering problem is maximizing utility per token against three constraints: the hard token limit, the softer effective-capacity ceiling, and the U-shaped attention curve that penalizes information placed in the middle of context (claim-context-degradation-lost-middle-ruler).
27
28	Apply four principles when assembling context:
29
30	1. Informativity over exhaustiveness — include only what matters for the current decision; design systems that can retrieve additional information on demand.
31	2. Position-aware placement — place critical constraints at the beginning and end of context because long-context evaluations show middle-position information is less reliably recovered than edge-position information (claim-context-degradation-lost-middle-ruler).
32	3. Progressive disclosure — load skill names and summaries at startup; load full content only when a skill activates for a specific task.
33	4. Iterative curation — context engineering is not a one-time prompt-writing exercise but an ongoing discipline applied every time content is passed to the model.
34
35	## Detailed Topics
36
37	### The Anatomy of Context
38
39	System Prompts
40	Organize system prompts into distinct sections using XML tags or Markdown headers (background, instructions, tool guidance, output format). System prompts persist throughout the conversation, so place the most critical constraints at the beginning and end where attention is strongest.
41
42	Calibrate instruction altitude to balance two failure modes. Too-low altitude hardcodes brittle logic that breaks when conditions shift. Too-high altitude provides vague guidance that fails to give concrete signals for desired behavior. Aim for heuristic-driven instructions: specific enough to guide behavior, flexible enough to generalize — for example, numbered steps with room for judgment at each step.
43
44	Start minimal, then add instructions reactively based on observed failure modes rather than preemptively stuffing edge cases. Curate diverse, canonical few-shot examples that portray expected behavior instead

People who liked this also viewed

6 picks

Type