CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

Quality

67%

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

65%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 clean, well-disclosed overview that correctly pushes implementation detail into references/rule.md, but the inline guidance stops at directives — a single before/after selector example or a verification step after fixing would make the body directly actionable. The duplication between the intro paragraph, the description, and rule.md is the main token waste.

Suggestions

Add one compact before/after selector example inline (e.g., `#sidebar .nav-item { ... }` → `.sidebar__nav-item { ... }`) so the Check and Fix sections are executable without opening rule.md.

Add a verification step to the workflow (e.g., "After flattening, re-check the rendered layout at each breakpoint to confirm overrides still apply") to close the checkpoint gap.

Delete the duplicated escalation intro paragraph (it is verbatim in rule.md's 'Why It Matters') and trim the Code Review section, which restates the frontmatter description.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: short Quick Reference bullets, four brief task sections, and a pointer to references/rule.md. Minor over-explanation remains — the two-sentence escalation intro is background Claude already knows and duplicates rule.md verbatim, and the Code Review section restates the frontmatter description.

4 / 5

Actionability

Some concrete guidance exists ("Avoid nesting selectors more than 3 levels deep", "Use :where() to apply styles with zero specificity"), but the Check and Fix sections are directives without inline specifics — no before/after selector examples, commands, or executable illustration of the common cases, with all examples deferred to rule.md. That matches level 3 (incomplete concrete guidance, missing key details) rather than level 4's mostly-executable bar.

3 / 5

Workflow Clarity

Check → Fix → Explain → Code Review implies a loose order, but the sections read as task variants rather than a sequenced process, and there is no validation checkpoint (e.g., re-check the rendered layout after applying a fix to confirm the override works). Sequence present, checkpoints absent — level 3, not level 4.

3 / 5

Progressive Disclosure

A clear, well-organized overview under 50 lines with a clearly signaled, one-level-deep reference: "see `references/rule.md`" points to a real 115-line file holding the specificity table, escalation examples, and framework guidance. The body duplicates only two sentences of it, and navigation is trivial.

5 / 5

Total

15

/

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 serviceable description with an explicit trigger clause and good domain keywords, but the 'what' is under-specified: it reads as a trigger condition plus one checking action rather than a statement of the skill's review/fix/explain capabilities. Rewriting to lead with concrete actions would lift it to the good-example tier.

Suggestions

Lead with a third-person statement of what the skill does (e.g., "Reviews CSS selectors for high specificity, flattens ID selectors and deep nesting, and removes unnecessary !important"), followed by the 'Use when' trigger.

Add natural trigger synonyms users would say: "!important", "selector specificity", "can't override styles", and the ".css" file extension.

Fix the garbled phrasing "related to Keep CSS specificity low and flat" — integrate the rule as a proper capability statement instead of a title splice.

DimensionReasoningScore

Specificity

The description names the domain ("reviewing stylesheets, component styles, and responsive behavior") and one to two concrete actions ("Check the rendered layout across breakpoints and interaction states before proposing a fix"), but never states the skill's core capabilities the body actually contains (fixing/flattening selectors, removing !important, explaining specificity scoring). Coverage gaps are larger than the minor gaps of level 4, but the actions go beyond the minimal/generic level 2.

3 / 5

Completeness

Has an explicit "Use when..." trigger clause plus a stated action ("Check the rendered layout across breakpoints and interaction states before proposing a fix"), so both 'what' and 'when' are present. The 'what' is thin and awkwardly phrased ("related to Keep CSS specificity low and flat" reads as a garbled insert), keeping it below level 5.

4 / 5

Trigger Term Quality

Good natural keyword coverage: "stylesheets", "component styles", "responsive behavior", "breakpoints", "interaction states", "CSS specificity" are phrases users would naturally say. A few natural terms are missing ("!important", "override styles", ".css" file extension).

4 / 5

Distinctiveness Conflict Risk

The CSS-specificity focus is a clear niche with distinct triggers, but "reviewing stylesheets, component styles, and responsive behavior" is broad enough to overlap with general CSS review or responsive-layout skills. Not level 5 because of that overlap; clearly above the generic overlap of level 3.

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
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.