context-fundamentals

This skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.

1.07x

Quality

63%

Does it follow best practices?

Impact

100%

1.07x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is context-fundamentals in muratcankoylan/Agent-Skills-for-Context-Engineering

Quality

Content

35%

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

A well-organized but verbose conceptual overview that re-explains material Claude already knows and leans on abstract principles over actionable, executable guidance. It uses one real reference well but leaves detailed content inline and an orphaned bundle script unreferenced.

Suggestions

Trim or move the foundational explanations (definition of context, attention mechanics, position encoding) into the reference file so the body only adds what Claude does not already know.

Replace abstract principles in Practical Guidance with concrete, copy-paste-ready patterns (e.g., example compaction-trigger code or a worked budget-monitoring snippet).

Reference scripts/context_manager.py from the body or remove it, so all bundle files are discoverable and none are orphaned.

Dimension	Reasoning	Score
Conciseness	The ~180-line body extensively explains concepts Claude already knows (what context is, attention n² relationships, position encoding, diminishing returns), e.g. "Context is the complete state available to a language model at inference time" and "For n tokens, this creates n² relationships that must be computed and stored."	1 / 3
Actionability	Offers some concrete elements (an XML prompt-structure example, a progressive doc-loading example, and a specific 70-80% compaction threshold), but the bulk of guidance is abstract direction like "Treat context as a finite resource" and "Design for context degradation" with no executable code.	2 / 3
Workflow Clarity	Presents numbered Guidelines and sectioned Practical Guidance, but it is a conceptual overview framed as principles rather than a sequenced operational workflow, with no validation checkpoints or feedback loops.	2 / 3
Progressive Disclosure	A real one-level-deep reference is clearly signaled ("[Context Components Reference](./references/context-components.md)", which exists), but large amounts of detailed conceptual content remain inline and the bundled scripts/context_manager.py is never referenced from the body.	2 / 3
	Total	7 / 12 Passed

Description

92%

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 with explicit trigger phrasing and clear what/when coverage. Its main weakness is overlap risk with sibling context skills on the broader architectural and debugging triggers.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete trigger actions such as "understand context", "explain context windows", "design agent architecture", "debug context issues", and "optimize context usage", which are specific actions in the domain rather than vague language.	3 / 3
Completeness	Explicitly answers both "what" ("Provides foundational understanding of context engineering for AI agent systems") and "when" ("This skill should be used when the user asks to...") with explicit triggers.	3 / 3
Trigger Term Quality	Provides broad coverage of natural phrases a user would actually say ("explain context windows", "debug context issues", "optimize context usage") plus topic mentions like attention mechanics and context budgeting.	3 / 3
Distinctiveness Conflict Risk	Has a clear context-engineering niche with distinct triggers, but broad phrases like "design agent architecture" and "debug context issues" overlap with closely related sibling skills (context-degradation, context-optimization) referenced in the body.	2 / 3
	Total	11 / 12 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/context-fundamentals/SKILL.md
Commit: f627ab5

Reviewed: about 8 hours 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.