context-engineering

Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/customaize-agent/skills/context-engineering/SKILL.md

Quality

Content

58%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.

The skill delivers strong, well-sequenced multi-agent workflow templates with clear validation checkpoints, but fails badly on token efficiency and progressive disclosure: it is a 1261-line monolith that re-explains concepts Claude already knows instead of splitting into one-level-deep reference files.

Suggestions

Split the body into separate reference files (e.g., fundamentals.md, degradation-patterns.md, multi-agent-workflows.md, optimization.md) and reduce SKILL.md to a concise overview with one-level-deep links, fixing the progressive_disclosure and conciseness problems together.

Cut conceptual exposition Claude already knows (definitions of context, attention mechanics, lost-in-middle theory) and keep only the actionable templates, thresholds, and decision rules.

Trim the worked-example tables and duplicated aggregation/output-format blocks that restate the same logic in prose and code; reference one canonical template instead of repeating the pattern per workflow.

Dimension	Reasoning	Score
Conciseness	The ~1257-line body is noticeably verbose and extensively explains concepts Claude already knows (what context is, attention mechanics, lost-in-middle), padding the context budget with redundant conceptual exposition.	2 / 5
Actionability	The multi-agent workflow templates provide concrete, mostly copy-paste-ready prompt blocks with decision thresholds and structured output formats, with only minor placeholder gaps.	4 / 5
Workflow Clarity	Workflows are clearly sequenced with numbered steps, explicit decision thresholds, and validation/feedback loops (e.g., hallucination detection Step 1-5 with risk thresholds and a regenerate-on-failure path).	5 / 5
Progressive Disclosure	This is a monolithic single-file document with no references directory and no links to separate files; content that clearly belongs split (fundamentals, degradation, workflows, optimization) is all inlined.	2 / 5
	Total	13 / 20 Passed

Description

78%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 is well-structured, third-person, and cleanly answers both what the skill does and when to use it with concrete trigger phrases. Its main weakness is the abstract verb 'Understand' in the 'what' clause, which understates the concrete capabilities the body actually delivers.

Dimension	Reasoning	Score
Specificity	The description names the domain ('components, mechanics, and constraints of context in agent systems') but relies on a single abstract verb ('Understand') rather than listing concrete actions, matching the anchor for naming the domain with minimal concrete actions.	3 / 5
Completeness	It explicitly answers both 'what' ('Understand the components, mechanics, and constraints of context in agent systems') and 'when' ('Use when writing, editing, or optimizing commands, skills, or sub-agents prompts') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Phrases like 'writing, editing, or optimizing commands, skills, or sub-agents prompts' give good coverage of natural terms users would say, though a few synonyms and concrete file/extension triggers are missing.	4 / 5
Distinctiveness Conflict Risk	The 'context engineering for agent prompts' niche is mostly distinct with minimal overlap risk, though it could overlap slightly with general prompt-engineering skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1262 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/customaize-agent/skills/context-engineering/SKILL.md
Commit: 23e2428

Reviewed: 18 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.