CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

referrer-policy

Use when reviewing HTTP response headers for privacy hardening on any website that handles authentication, session state, or sensitive URL parameters.

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 ./skills/referrer-policy/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 body is a lean, well-sectioned overview with exact policy values, a clear check-fix-verify workflow, and a properly disclosed single reference file. Its weaknesses are minor: some duplicated bullets in Quick Reference and no inline executable check command or config snippet, both of which live in the reference file.

DimensionReasoningScore

Conciseness

The ~35-line body is lean with no explanation of basic concepts, but the token-leak point is stated twice (intro example and again in Quick Reference: 'Sensitive URLs (reset tokens, private IDs) in query strings can be exposed via the Referer header') and the strict-origin-when-cross-origin behavior is described in two adjacent bullets, which could be merged.

4 / 5

Actionability

Concrete, exact guidance is given ('Referrer-Policy: strict-origin-when-cross-origin', 'Never use unsafe-url', 'HTTP header, <meta> tag, or the referrerpolicy attribute'), and as an instruction-only skill the missing code is acceptable since the guidance is actionable — though a curl one-liner for the Check step and one config snippet inline would close the gap to fully executable.

4 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review flow is clearly sequenced for a simple, single-purpose skill, and the Code Review section closes the loop with explicit verification ('verify them against the effective production-like response'). The action is unambiguous and the operation is neither destructive nor batch, so the simple-skill exception applies.

5 / 5

Progressive Disclosure

The body is a well-organized under-50-line overview that points to a single real one-level-deep reference (references/rule.md, confirmed present in the bundle) at the bottom: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md.'

5 / 5

Total

18

/

20

Passed

Description

58%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 has a clear and explicit trigger clause with a well-scoped context, but it never names the Referrer-Policy header — the skill's entire subject — leaving both the 'what' and the natural trigger terms incomplete. It also risks conflicting with other security-header skills sharing the same broad privacy-hardening trigger.

Suggestions

State the actual subject in the description, e.g. 'Check and set the Referrer-Policy header...' so the 'what' is explicit and specific rather than a generic privacy-hardening action.

Add natural trigger terms users would say, such as 'Referrer-Policy', 'Referer header', and 'security headers', so the skill surfaces when those words are mentioned.

Narrow the 'when' clause to referer leakage specifically (e.g. 'when a site's Referer header could leak sensitive URL parameters') to reduce overlap with other header-hardening skills.

DimensionReasoningScore

Specificity

The description names the domain ('reviewing HTTP response headers for privacy hardening') and one concrete action, but never mentions the Referrer-Policy header itself or enumerates the skill's actions (check, fix, configure), so it is not comprehensive.

3 / 5

Completeness

An explicit 'Use when reviewing... on any website that handles authentication, session state, or sensitive URL parameters' clause answers 'when' clearly and specifically, and 'what' is present ('reviewing HTTP response headers for privacy hardening'), but the 'what' side never states the skill's actual purpose — setting/checking the Referrer-Policy header — so it falls short of the top anchor.

4 / 5

Trigger Term Quality

Relevant keywords are present ('HTTP response headers', 'privacy hardening', 'authentication', 'session state', 'sensitive URL parameters'), but the most natural trigger terms — 'Referrer-Policy', 'Referer', 'security headers' — are missing entirely.

3 / 5

Distinctiveness Conflict Risk

The trigger 'any website that handles authentication, session state, or sensitive URL parameters' is broad and would also fire for sibling security-header skills (CSP, HSTS, X-Frame-Options), so overlap risk with closely related skills remains.

3 / 5

Total

13

/

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/referrer-policy/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.