best-practices

Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".

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 ./src/resources/skills/best-practices/SKILL.md

Quality

Content

65%

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

A highly actionable, well-organized reference of web best-practice patterns with concrete examples throughout. It is hampered by length and lack of progressive disclosure, and by the absence of a sequenced audit workflow with validation checkpoints.

Suggestions

Move the bulk of the inline pattern catalog into a reference file (e.g., references/patterns.md) and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure and conciseness.

Add a short, sequenced audit workflow with explicit validation steps (run npm audit, validate headers, check Lighthouse) and a fix-and-retry loop, raising workflow clarity for the implied audit process.

Trim well-known basics (doctype, charset placement, duplicate IDs) that Claude already knows to recover token budget.

Dimension	Reasoning	Score
Conciseness	Prose is lean and mostly actionable patterns, but at ~575 lines much of the inline reference (charset placement, doctype, duplicate IDs, passive listeners) covers knowledge Claude already has, inflating the token budget.	2 / 3
Actionability	Dense with executable, copy-paste-ready code and commands (npm audit, concrete HTTP headers, HTML/JS/CSS snippets, React error boundary), with clear bad/good contrasts throughout.	3 / 3
Workflow Clarity	An audit checklist is provided, but there is no sequenced audit workflow with explicit validation checkpoints or a fix-and-retry feedback loop, which the rubric expects for batch/destructive operations.	2 / 3
Progressive Disclosure	Sections are well organized, but all reference material is inline in SKILL.md with no bundle files; the large catalog of patterns is not offloaded to one-level-deep reference files.	2 / 3
	Total	9 / 12 Passed

Description

92%

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, third-person description that clearly states both what it does and when to use it with natural trigger terms. Its main weakness is the broad domain, which risks overlap with general code-review or security-audit skills.

Suggestions

Narrow the description's niche (e.g., "front-end/web best practices audits") to reduce overlap with general code-review and security-audit skills and boost distinctiveness.

Consider adding a distinguishing scope cue such as "for web/front-end projects" so it is less likely to trigger for non-web code quality requests.

Dimension	Reasoning	Score
Specificity	Names three concrete domains ("security, compatibility, and code quality") and enumerates specific operations (apply, audit, modernize, review, check), going beyond naming a domain and a few actions.	3 / 3
Completeness	Explicitly answers what ("Apply modern web development best practices for security, compatibility, and code quality") and when ("Use when asked to...") with explicit trigger guidance.	3 / 3
Trigger Term Quality	Triggers ("apply best practices", "security audit", "modernize code", "code quality review", "check for vulnerabilities") are natural phrases a user would actually say, with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	"Best practices" is broad and overlaps with related quality/security skills; the body itself cross-references a web-quality-audit skill, indicating overlap risk despite reasonably distinct triggers.	2 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (584 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: gsd-build/gsd-2
Path: src/resources/skills/best-practices/SKILL.md
Commit: 33c00aa

Reviewed: about 14 hours 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.