CtrlK
BlogDocsLog inGet started
Tessl Logo

context-engineering

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A compact, well-structured overview with excellent progressive disclosure and token efficiency. Its weakness is actionability and workflow_clarity, since it offers directive thresholds rather than executable inline examples or validation-gated procedures.

Suggestions

Add one short inline executable snippet (e.g., a sample invocation of context_analyzer.py with expected output) to lift actionability toward copy-paste ready.

For destructive or batch operations referenced by the scripts, include an explicit validate-then-proceed checkpoint so workflow_clarity can reach the top anchor.

Turn the Four-Bucket Strategy into a sequenced decision procedure (when to Write vs Select vs Compress vs Isolate) with explicit triggers for each step.

DimensionReasoningScore

Conciseness

The body is a lean bullet/table overview that assumes Claude's competence and avoids explaining concepts Claude already knows; every section earns its tokens.

3 / 3

Actionability

Concrete thresholds ('Warning at 70%, trigger optimization at 80%', '50-70% reduction, <5% quality loss') and named scripts give real guidance, but the inline guidance is directive rather than copy-paste executable, so it sits between abstract and fully executable.

2 / 3

Workflow Clarity

The Four-Bucket Strategy and numbered Guidelines provide a sequence, but this is a knowledge-map overview rather than a fragile multi-step operation, so validation checkpoints and feedback loops are absent.

2 / 3

Progressive Disclosure

A clear overview with a well-signaled Quick Reference table linking to nine real one-level-deep reference files plus two scripts, all verified to exist, giving easy navigation.

3 / 3

Total

10

/

12

Passed

Description

100%

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 well-crafted description: third person, explicit 'Use when' triggers, many concrete actions, and a distinctive niche. It cleanly satisfies the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems') in third person, matching the top anchor rather than the domain-plus-some-actions level.

3 / 3

Completeness

Explicitly answers 'what' ('Master context engineering... Covers...') and 'when' with a clear 'Use when' clause listing concrete triggers, satisfying the top anchor.

3 / 3

Trigger Term Quality

Covers natural phrases a practitioner would say ('debugging context failures', 'optimizing token usage', 'multi-agent coordination', 'LLM-powered pipelines'), giving good coverage of likely user language.

3 / 3

Distinctiveness Conflict Risk

The context-engineering-for-agent-systems niche with distinct triggers is unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
mrgoonie/claudekit-skills
Reviewed

Table of Contents

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.