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.

62

Quality

73%

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

67%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.

A well-structured conceptual skill with concrete code examples for each of four validation layers and a worked example. Its main weakness is repetition of the core principle across several prose sections, which inflates token cost without adding information.

Suggestions

Merge 'Why Multiple Layers' and 'Key Insight' into the Overview or 'Applying the Pattern' to eliminate restating the 'single vs. multiple layers' contrast three times.

Replace '// ... proceed' placeholders in code examples with the actual next call so each layer snippet is fully copy-pasteable.

Expand the 'Test each layer' step into an explicit validate->fix->retry feedback loop with a concrete bypass example, given the skill's focus on making bugs impossible.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete code, but the core principle is restated across Overview, 'Why Multiple Layers', 'Key Insight', and 'Applying the Pattern', adding unnecessary explanation that could be tightened.

3 / 5

Actionability

Provides concrete TypeScript examples for all four layers plus a worked session example and a security JS snippet; examples are mostly executable with minor gaps ('// ... proceed').

4 / 5

Workflow Clarity

'Applying the Pattern' gives a clear 4-step sequence including a verification step ('Try to bypass layer 1, verify layer 2 catches it'), with most checkpoints present though recovery detail is brief.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear section headers and no bundle files needed; the inlined security section is a slightly separable concern but structure is otherwise good.

4 / 5

Total

15

/

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.

A strong description that clearly states both capability and trigger condition in third person, with concrete natural-language triggers. It is slightly abstract on specificity, naming the approach rather than enumerating concrete actions.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ('Validate at every layer data passes through') but does not enumerate multiple specific actions, so it is not comprehensive.

3 / 5

Completeness

Explicitly answers both what ('Validate at every layer data passes through to make bugs impossible') and when ('Use when invalid data causes failures deep in execution...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'invalid data causes failures deep in execution' and 'validation at multiple system layers' are reasonably natural phrases a debugging user would say, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The 'multiple system layers' and 'failures deep in execution' framing carves a fairly distinct niche, though 'validation' broadly could overlap with related testing/defensive skills.

4 / 5

Total

16

/

20

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.