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

56%

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

42%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.

This is a conceptual/foundational skill whose body is dominated by explanations of concepts Claude already knows, with useful but sparse actionable heuristics and no real sequenced workflow. Progressive disclosure is undercut by an unreferenced script bundle and inlined reference-grade content.

Suggestions

Cut the textbook exposition of concepts Claude already knows (attention mechanics, position encoding, what system prompts/tool definitions are) and keep only the non-obvious heuristics and thresholds.

Link to scripts/context_manager.py from the body (e.g., in Practical Guidance or a new Tools section) so the existing bundle is discoverable, and move the duplicated conceptual detail into references/context-components.md.

Replace the vague "External resources" bullets (no URLs) with either concrete links or a single sentence directing Claude to retrieve current sources on demand.

Dimension	Reasoning	Score
Conciseness	The ~185-line body extensively explains concepts Claude already knows (what context is, what system prompts and tool definitions are, n^2 attention mechanics, position encoding), which is padded; genuine heuristic nuggets (70-80% compaction, attention-favored positions) are mixed in but do not offset the verbosity.	2 / 5
Actionability	Concrete actionable heuristics are present (compaction at 70-80%, place critical info at beginning/end, XML/Markdown section templates, named techniques like observation masking and selective retention), but most of the body is conceptual exposition rather than directly executable guidance.	3 / 5
Workflow Clarity	There is no real multi-step task workflow; the "Guidelines" are an unsequenced principle list and the only step pattern is a trivial 2-step progressive-loading example, so sequence exists but checkpoints and a genuine workflow with feedback loops are absent.	3 / 5
Progressive Disclosure	One reference is clearly signaled one level deep ([Context Components Reference](./references/context-components.md)), but the 11KB scripts/context_manager.py bundle is never referenced from the body, the body inlines conceptual exposition that overlaps the reference file, and "External resources" are vague bullets with no URLs — more than minor organization gaps.	3 / 5
	Total	11 / 20 Passed

Description

70%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.

The description gives excellent explicit trigger guidance and names its niche clearly, with no first/second-person voice issues. Its main weakness is an abstract capability statement ("provides foundational understanding") that keeps specificity and completeness just below the top anchors.

Suggestions

Replace the abstract "Provides foundational understanding of context engineering" with one or two concrete skill actions (e.g., "Explains context components, diagnoses context-budget issues, and recommends progressive-disclosure strategies for AI agent systems").

Add a couple of natural synonyms / variations to the trigger list (e.g., "context length", "token budget", "lost in the middle") to broaden the natural-term coverage toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	The domain (context engineering) is clearly named and concrete action-verbs appear ("design agent architecture", "debug context issues", "optimize context usage"), but the literal capability clause "Provides foundational understanding" is generic and the concrete verbs are framed as user triggers rather than skill actions, so coverage is not comprehensive.	3 / 5
Completeness	Both halves are present: an explicit "should be used when" trigger clause with concrete phrases (the "when") and a "Provides foundational understanding of context engineering" statement (the "what"), but the "what" is abstract compared to the concrete-what anchor at 5.	4 / 5
Trigger Term Quality	Strong natural trigger phrases users would actually say ("understand context", "explain context windows", "debug context issues") plus domain keywords, but terms like "attention mechanics" and "context budgeting" lean technical and synonym/variation coverage is limited, falling short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It targets a fairly specific niche (context engineering for AI agent systems) with distinctive triggers (context windows, progressive disclosure, context budgeting), but "design agent architecture" and "debug context issues" are broad enough to overlap with closely related sibling skills.	4 / 5
	Total	15 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/context-fundamentals/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.