CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

specificity-management

Use when reviewing stylesheets, component styles, and responsive behavior related to Keep CSS specificity low and flat. Check the rendered layout across breakpoints and interaction states before proposing a fix.

Quality

71%

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/specificity-management/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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, token-efficient overview body that delegates detail to a real one-level reference. The weaknesses are an actionability gap (no inline code or before/after selector examples), a missing post-fix validation step in the workflow, and a slightly inaccurate reference pointer.

Suggestions

Inline one minimal before/after selector example in the Fix section (e.g. "#main-navigation .nav-list .nav-link" → ".nav-link") so the core guidance is executable without opening rule.md.

Add a Verify step after Fix that references rule.md's Verification section — e.g. "Verify computed styles in DevTools and check the rendered UI at affected breakpoints before considering the fix done."

Trim the opening escalation paragraph (it repeats rule.md's 'Why It Matters' verbatim) and correct the reference pointer to describe what rule.md actually contains.

DimensionReasoningScore

Conciseness

The body is lean (~45 lines): a Quick Reference of four one-line rules plus four terse task sections, with all code deferred to the reference. The one trimmable part is the opening escalation paragraph — "High specificity creates an escalation problem — once you use an ID selector, you need another ID to override it..." — which explains a concept Claude already knows and duplicates rule.md's 'Why It Matters' verbatim. That is a minor instance of over-explanation, matching level 4 rather than the leaner level 5.

4 / 5

Actionability

Guidance is specific in intent — "Flatten high-specificity selectors to use classes instead of IDs, reduce nesting depth, and remove unnecessary !important" and "Use :where() to apply styles with zero specificity" — but the body contains no code examples, commands, or before/after selectors; everything executable lives one file away in rule.md. This sits at 'some concrete guidance but incomplete; missing key details' rather than level 4, which requires concrete code or commands with only minor gaps.

3 / 5

Workflow Clarity

The Check → Fix → Explain → Code Review sections give a recognizable sequence, but no validation checkpoint follows the Fix step — there is no "verify computed styles / rendered layout after fixing" step in the body, even though the skill's own description mandates checking rendered layout and rule.md contains a Verification section that the workflow never points to. Sequence present, checkpoints missing, which is exactly level 3.

3 / 5

Progressive Disclosure

SKILL.md acts as an overview with a single clearly signaled, one-level-deep reference ("For full implementation details, code examples, and framework-specific guidance, see references/rule.md"), and the referenced file exists and contains the details. Minor organization gaps keep it below level 5: the pointer promises "framework-specific guidance" that rule.md does not actually contain, and the escalation paragraph is duplicated between the two files rather than living in one place.

4 / 5

Total

14

/

20

Passed

Description

70%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 solid description with an explicit 'Use when...' trigger, domain-appropriate natural terms, and a concrete verification action. Its main weakness is that the 'what' undersells the skill's actual capabilities — selector analysis, flattening, and !important removal are never named.

Suggestions

Enumerate the skill's concrete capabilities in the 'what' clause, e.g. "Analyzes selectors for ID usage, deep nesting, and unnecessary !important; flattens them to class-based, low-specificity rules."

Add missing natural trigger terms such as ".css", "!important", and "specificity wars" to broaden keyword coverage.

Tighten the trigger scope — 'reviewing stylesheets, component styles, and responsive behavior' is broader than the specificity-focused niche and risks firing on general layout/responsive review requests.

DimensionReasoningScore

Specificity

The description names the domain ("stylesheets, component styles, and responsive behavior" for CSS specificity) and one concrete action — "Check the rendered layout across breakpoints and interaction states before proposing a fix" — but the skill's actual capabilities (analyzing selectors for ID usage, flattening nested selectors, removing !important) are not enumerated. It matches 'Names domain and 1-2 concrete actions, but not comprehensive' rather than level 4, which requires several listed specific actions.

3 / 5

Completeness

Both parts are explicitly present: "Use when reviewing stylesheets, component styles, and responsive behavior related to..." answers 'when', and "Check the rendered layout across breakpoints and interaction states before proposing a fix" answers 'what'. The 'what' is thin — it describes verification behavior but not the specificity analysis/fixing the skill performs — so it does not reach level 5's 'clearly and explicitly answers both with concrete trigger phrases', while level 3 is ruled out because the 'when' clause is explicit.

4 / 5

Trigger Term Quality

Natural terms a frontend developer would say are present: "stylesheets", "component styles", "responsive behavior", "breakpoints", "interaction states", and "CSS specificity". Common variations and file extensions are missing (e.g. ".css", "!important", "cascade"), so it falls short of the comprehensive synonym/extension coverage of level 5 but is well above the sparse keyword coverage of level 3.

4 / 5

Distinctiveness Conflict Risk

The CSS-specificity niche ("Keep CSS specificity low and flat", selectors, breakpoints) is fairly distinct with clear triggers. There is minor overlap risk with generic CSS review, lint, or responsive-layout skills — "reviewing stylesheets... and responsive behavior" is somewhat broad — which keeps it at 'mostly distinct; minor overlap risk' rather than level 5's clear-niche bar.

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/specificity-management/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.