CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

token-storage-security

Use when reviewing authentication implementation, setting up a new auth system, or evaluating whether the current token storage approach exposes the application to XSS-based token theft.

Quality

80%

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 ./skills/token-storage-security/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured instruction skill: concrete patterns to check and fix, an appropriate split between the overview body and a single well-signaled reference file holding the code examples. The only notable gaps are a slightly redundant opening paragraph that re-explains a concept Claude already knows and the absence of an explicit re-validation step after applying fixes.

DimensionReasoningScore

Conciseness

The body is lean with tightly scoped sections, but the opening paragraph ("localStorage is accessible to any JavaScript running on the page...") explains a concept Claude already knows and duplicates the Quick Reference bullet ("localStorage is readable by any JavaScript on the page") — minor over-explanation that could be trimmed.

4 / 5

Actionability

Highly concrete, executable guidance throughout: exact API calls to flag ("localStorage.setItem, sessionStorage.setItem, or document.cookie"), exact cookie flags ("Secure and SameSite=Strict (or Lax)"), exact HTTP methods ("POST, PUT, PATCH, and DELETE"), and specific fixes. Per the rubric's instruction-skill note, the absence of inline code is not penalized since the guidance is fully actionable and the code examples are properly deferred to the reference.

5 / 5

Workflow Clarity

Clear task-mode structure (Quick Reference → Check → Fix → Explain → Code Review) with a checklist-style Quick Reference and a Check section defining what to verify, but there is no fix-then-recheck feedback loop after applying the Fix steps. Not a destructive or batch operation, so the workflow cap at 3 does not apply.

4 / 5

Progressive Disclosure

Scored against the actual bundle: the ~45-line body is a proper overview with one clearly signaled, one-level-deep reference ("For full implementation details, code examples, and framework-specific guidance, see `references/rule.md`"), and references/rule.md exists (containing the code examples) with no chained .md references. Content is appropriately split between overview and detail, making navigation easy.

5 / 5

Total

18

/

20

Passed

Description

66%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 well-constructed trigger-focused description with specific, natural when-clauses anchored in a distinct security niche. Its main weakness is that the skill's actual capability is never explicitly stated — the "what" must be inferred from the "when" — and it lacks common synonyms like JWT or localStorage that users might naturally say.

Suggestions

Prepend an explicit statement of what the skill does, e.g., "Reviews and hardens token storage by moving session tokens and JWTs to httpOnly cookies with CSRF defenses. Use when..."

Add natural synonyms users would say to the trigger list: "JWT", "localStorage", "session tokens", or "httpOnly cookies"

DimensionReasoningScore

Specificity

Names three concrete actions ("reviewing authentication implementation", "setting up a new auth system", "evaluating whether the current token storage approach exposes the application to XSS-based token theft") in a concrete security domain, but never states what the skill actually does (e.g., httpOnly cookie guidance) — a minor coverage gap that keeps it below the comprehensive anchor.

4 / 5

Completeness

An explicit, detailed "Use when..." clause is present, but the "what" is only implied through the when-clauses and never stated as a capability — mirroring anchor 3's structure of one clear half with the other only weakly implied. It is above anchor 2 because the rich when-clauses strongly imply the skill's purpose, but below anchor 4 because no explicit "what" statement exists.

3 / 5

Trigger Term Quality

Includes natural phrases users would say ("authentication", "auth system", "token storage", "XSS-based token theft"), but misses common synonyms like "JWT", "localStorage", "cookies", or "session tokens" that would round out coverage.

4 / 5

Distinctiveness Conflict Risk

The "token storage approach exposes the application to XSS-based token theft" phrase carves a clear niche with minimal conflict risk, though the broader "reviewing authentication implementation" trigger could overlap with closely related auth skills.

4 / 5

Total

15

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/token-storage-security/SKILL.md

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.