CtrlK
BlogDocsLog inGet started
Tessl Logo

defense-in-depth-validation

Validate at every layer data passes through to make bugs impossible. Use when invalid data causes failures deep in execution, requiring validation at multiple system layers.

64

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/defense-in-depth-validation/skills/defense-in-depth-validation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

Actionable and workflow-clear with real code and a validation checkpoint, but held back by minor restated explanations and a monolithic structure that offers no progressive disclosure beyond section headers.

Suggestions

Collapse the 'Why Multiple Layers' and 'Key Insight' sections into the overview to remove restated phrasing and tighten the token budget.

Consider moving the security defense-in-depth application and/or the worked session example into a reference file linked one level deep from the body to add genuine progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly lean and code-driven, but the 'Why Multiple Layers' and 'Key Insight' sections restate the core principle ('Add checks at every layer'), so it could be tightened; it is not a 3 because some tokens re-earn their place.

2 / 3

Actionability

Each of the four layers ships complete, copy-paste-ready TypeScript/JavaScript code, and the security section adds an executable Express/DB example, matching fully executable guidance.

3 / 3

Workflow Clarity

'Applying the Pattern' gives a clear 4-step sequence with an explicit validation checkpoint ('Test each layer - Try to bypass layer 1, verify layer 2 catches it') and the worked session example reinforces the data-flow trace, providing feedback loops.

3 / 3

Progressive Disclosure

The skill is a single well-sectioned ~150-line file with no bundle files or one-level references, and its length exceeds the under-50-line simple-skill allowance that would let progressive disclosure score 3 on organization alone.

2 / 3

Total

10

/

12

Passed

Description

75%

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 solid, third-person description with an explicit trigger clause and a clear niche. It is slightly held back by relying on a single action verb and somewhat technical trigger phrasing.

Suggestions

Broaden specificity by naming the concrete layer types inline (e.g., 'Validate input at entry points, business logic, and environment guards') so multiple distinct actions are visible.

Soften trigger terms toward natural user phrasing, adding variants like 'when data causes errors far from where it originates' alongside 'deep in execution'.

DimensionReasoningScore

Specificity

The description states a concrete action ('Validate at every layer data passes through') but relies on a single verb applied across layers rather than listing multiple distinct concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It clearly states what the skill does ('Validate at every layer... to make bugs impossible') and provides an explicit 'Use when...' trigger, satisfying both what and when.

3 / 3

Trigger Term Quality

'Use when invalid data causes failures deep in execution, requiring validation at multiple system layers' offers some relevant keywords, but 'deep in execution' and 'multiple system layers' lean technical and omit common phrasings a user would naturally say.

2 / 3

Distinctiveness Conflict Risk

The layered defense-in-depth validation niche has distinct triggers tied to deep-execution failures, making it unlikely to fire for unrelated skills; voice is third-person imperative, so no penalty applies.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
secondsky/claude-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.