context-fundamentals

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 models needed to interpret every other context-engineering decision. Use this for conceptual explanation, onboarding, and background reading. Route operational work to the specialized skills: debugging attention failures goes to context-degradation, token-efficiency work goes to context-optimization, conversation summarization goes to context-compression, and project-shape decisions go to project-development.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/context-fundamentals/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured conceptual foundation skill with concrete, actionable guidance and clean one-level-deep referencing. It can be tightened by trimming explanations of concepts Claude already knows, deduplicating the routing map, and linking the existing context_manager.py script.

Suggestions

Cut re-explanations of transformer attention / the U-shaped curve and the signal-density test to essentials, since Claude already knows these; keep only the skill's specific framing.

State the operational routing map once (e.g. in 'Integration') and reference it from 'When to Activate' and 'References' instead of repeating the full list three times.

Add a pointer to scripts/context_manager.py (e.g. a 'Tooling' line in References with a Read-when clause) so the bundled script is discoverable from the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but spends tokens explaining concepts Claude already knows (attention mechanics, the U-shaped curve, signal density) and repeats the operational routing map across 'When to Activate', 'Integration', and References.	3 / 5
Actionability	Gives concrete, executable guidance — 'place critical constraints at the beginning and end', progressive disclosure at three levels, activation thresholds, and numeric gotchas (70-80% utilization, 10-40% recall loss) — with a runnable system-prompt example; minor gaps only.	4 / 5
Workflow Clarity	Sequences a reading order and a two-part conceptual/operational decision split; as a conceptual skill with no destructive or batch operation, it avoids the validation cap and presents a coherent, if light, workflow.	4 / 5
Progressive Disclosure	Well-sectioned body with a one-level-deep reference (./references/context-components.md) carrying clear 'Read when' guidance; the bundle also ships scripts/context_manager.py, which the body never references, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states its conceptual scope, gives concrete triggers for when to use it, and explicitly routes operational work to sibling skills to avoid overlap. The main weakness is trigger phrasing that skews technical rather than matching the natural words a user would say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete conceptual actions — '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 models' — giving comprehensive coverage within its niche.	5 / 5
Completeness	Explicitly answers both 'what' (explain foundational context-engineering concepts, enumerated) and 'when' ('Use this for conceptual explanation, onboarding, and background reading') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing triggers ('conceptual explanation, onboarding, and background reading') but leans on technical jargon ('U-shaped attention curve', 'attention mechanics') and misses common synonyms a non-expert would naturally say.	4 / 5
Distinctiveness Conflict Risk	Holds a clear conceptual-foundation niche and explicitly routes operational work away ('debugging attention failures goes to context-degradation...'), minimizing conflict risk with adjacent skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: skills/context-fundamentals/SKILL.md
Commit: 6dbe1a1

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.