CtrlK
BlogDocsLog inGet started
Tessl Logo

impeccable

Frontend design guidance, upstream-maintained (impeccable).

44

Quality

46%

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 ./optional-skills/creative/impeccable/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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-structured catalog stub that gives a clear entry point and points to upstream documentation, but it is light on actionable, executable guidance — most real instruction lives in the external bundle rather than here.

Suggestions

Add one or two short executable examples (e.g. a sample '/impeccable critique' invocation and the 'npx impeccable detect' output format) so the body is useful without the external docs.

Replace the inlined list of all 23 sub-command names with a grouped summary plus a pointer to the bundled command reference, reducing inline bulk.

Clarify the post-init workflow with a brief 2-3 step sequence (init -> critique/detect -> apply fixes) so users know the expected path before consulting the external URL.

DimensionReasoningScore

Conciseness

The body is short and lean with no padding of concepts Claude already knows; the only slightly non-essential part is the catalog-stub blockquote justifying the upstream-maintenance model, keeping it in the 'efficient; minor instances of over-explanation that could be trimmed' band rather than a clean 5.

4 / 5

Actionability

It gives concrete commands ('/impeccable init', 'npx impeccable detect') and lists the 23 sub-commands, but provides no executable examples for the actual design work and delegates everything else to an external URL, matching 'some concrete guidance but incomplete; missing key details'.

3 / 5

Workflow Clarity

There is a single unambiguous entry point ('After install, start with: /impeccable init') — appropriate for a stub/overview where the simple-skill exception applies — with only minor gaps because everything beyond init is handed off to external docs.

4 / 5

Progressive Disclosure

It is a well-organized overview with a clear one-level pointer to full documentation (https://impeccable.style) and the install command; it is not a 5 because the inlined 23-sub-command list is bulk that lives in the real bundle, and navigation targets an external URL rather than local reference files (none exist in this catalog stub).

4 / 5

Total

15

/

20

Passed

Description

25%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 is concise but underspecified: it names the frontend-design domain yet gives no concrete actions, no natural trigger phrases, and no explicit 'use when' guidance, leaving it vague and prone to overlapping with other design skills.

Suggestions

Replace the generic noun 'guidance' with concrete actions, e.g. 'Apply design heuristics, audit UIs for anti-patterns, and run a deterministic design detector on frontend code.'

Add an explicit 'Use when...' trigger clause naming natural user phrases such as 'design this UI', 'make this look better', 'audit my frontend', or 'polish this layout'.

Narrow the niche and include distinguishing terms (e.g. the 61-rule detector, anti-pattern fixes) to reduce overlap with generic design skills like claude-design.

DimensionReasoningScore

Specificity

The description names the domain ('Frontend design guidance') but offers no concrete actions — 'guidance' is a generic noun, not a specific capability, matching the anchor 'Names the domain but actions are minimal or generic' and falling below anchor 3 which requires concrete actions.

2 / 5

Completeness

It provides only a vague 'what' ('Frontend design guidance') and no 'when'/trigger clause at all, matching the anchor 'Has a vague what and no when'; the judging guideline's missing-trigger cap would allow at most 3, but the absent when pushes it to 2.

2 / 5

Trigger Term Quality

'Frontend design' is a relevant keyword but no natural user trigger phrases (e.g. 'make this look better', 'design this UI'), synonyms, or file extensions appear, so it sits noticeably below the midpoint at 'one or two generic keywords; missing the natural phrases users say'.

2 / 5

Distinctiveness Conflict Risk

'Frontend design guidance' is very broad with high overlap risk against general design/frontend skills (the metadata even names related_skills claude-design and popular-web-designs), matching 'Very broad; high overlap risk with many similar skills'.

2 / 5

Total

8

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
NousResearch/hermes-agent
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.