devtools-unicode-escaping

Guidelines for escaping strings and handling user-controlled data in DevTools to prevent layout bleed-through, XSS, and security issues.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/devtools-unicode-escaping/SKILL.md

Quality

Content

100%

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

The content is an exemplary lean, actionable skill body: concrete executable examples, unambiguous decision guidance, and clean section organization with no unnecessary padding or external reference nesting. No changes needed.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's knowledge of DevTools/Lit without padding; every section directly earns its place with tight, purposeful guidance.	3 / 3
Actionability	Provides concrete, copy-paste-ready TypeScript examples with exact function names (escapeUnicodeAsText, safeEscapeUnicode) and clear when-to-use decision rules.	3 / 3
Workflow Clarity	As a single-decision skill the action is unambiguous: two helpers with explicit use-cases plus clearly separated Lit-wrapper and manual-DOM sections, satisfying the simple-skill allowance.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed, organized into four clear numbered sections; per the rubric a well-organized short skill with no required bundle scores 3.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 clearly communicates a distinct DevTools niche and concrete security/escaping outcomes, but it lacks an explicit "Use when..." trigger and could include more natural trigger-term variations. It is solid but not fully trigger-complete.

Suggestions

Add an explicit "Use when..." clause, e.g. when rendering untrusted strings in the DevTools UI, console messages, object properties, or DOM tree nodes.

Broaden trigger terms with natural variations users would say: "unicode escaping", "RTL/bidi overrides", "zero-width characters", "invisible characters".

Enumerate the concrete actions more specifically (e.g. "escape unicode, neutralize bidi overrides, render hidden characters visibly") to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the DevTools domain and concrete outcomes like "escaping strings" and "prevent layout bleed-through, XSS, and security issues", but does not enumerate multiple specific concrete actions to reach the score-3 anchor.	2 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." trigger guidance; per the rubric a missing explicit when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms ("escaping strings", "user-controlled data", "DevTools", "XSS") are present but common natural variations a user might say (unicode, RTL/bidi, zero-width) are missing, matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The DevTools-specific unicode/security escaping niche is clearly distinguishable and unlikely to trigger for the wrong skill, matching the score-3 anchor.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ChromeDevTools/devtools-frontend
Path: .agents/skills/devtools-unicode-escaping/SKILL.md
Commit: 184a74d

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.