CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

golden-html-multi

Use when testing the multi-file html build

Quality

50%

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 ./tests/golden/phase2/html_multi/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 well-structured documentation index with genuine, clearly-signaled reference files, but it is padded with redundant statistics and a truncated filler code example and lacks sharp actionable guidance. Tightening the overview and removing wasted tokens would lift it materially.

Suggestions

Remove the truncated long Python example (x0…x37…) — it adds no executable value and wastes the token budget.

Consolidate the redundant statistics (Section Overview, Documentation Statistics, and Table Summary overlap) into a single concise summary.

Replace the generic 'When to Use This Skill' bullets with concrete guidance tying each user need to the specific reference file that answers it.

DimensionReasoningScore

Conciseness

The body carries padded metadata (statistics repeated across sections), generic 'When to Use This Skill' boilerplate, and a truncated giant code example (x0…x37 then '…') that burns tokens for no value, fitting the 'noticeably verbose; several padded sections' anchor.

2 / 5

Actionability

Concrete navigation to reference files is provided, but the inlined code examples are low-value extracts (one truncated mid-statement) and the 'When to Use' list is vague, leaving guidance incomplete per the 'some concrete guidance but incomplete' anchor.

3 / 5

Workflow Clarity

As a reference/lookup skill there is no multi-step process to sequence; the structure is navigable but no explicit sequence or checkpoints are given, matching the 'steps listed but validation gaps; sequence present but implicit' band.

3 / 5

Progressive Disclosure

Real one-level-deep reference files (golden_html_multi_s1-s2.md, golden_html_multi_s3-s4.md, index.md) are clearly signaled in the Navigation section with descriptions, giving good structure with only minor gaps from inlined extracted content.

4 / 5

Total

12

/

20

Passed

Description

28%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 thin: it gives a 'when' trigger but no concrete 'what' and only generic action language, leaving it indistinct and weakly specified. It reads more as a label than a capability statement.

Suggestions

State the concrete actions the skill performs (e.g., 'Builds, validates, and inspects multi-file HTML documentation') before the 'Use when' clause.

Add natural trigger phrases users would actually say, such as 'multi-file HTML', 'HTML documentation build', or 'HTML site assembly'.

Make the 'what' explicit so the description answers both what it does and when to use it, e.g. '…Use when assembling or testing a multi-file HTML documentation build.'

DimensionReasoningScore

Specificity

The description names a domain ("multi-file html build") but offers only the minimal, generic action "testing" — it lists no concrete capabilities, matching the 'names the domain but actions are minimal or generic' anchor rather than the fully vague (1) or multi-action (3) anchors.

2 / 5

Completeness

It supplies a 'when' clause ("Use when testing…") but the 'what' is absent or only weakly implied, mirroring the 'only when is present without what' example; the explicit 'Use when…' clause prevents it from dropping to 1.

2 / 5

Trigger Term Quality

Only "testing" and "multi-file html build" appear; the latter is jargon rather than a phrase a user would naturally say, and common synonyms/variations are missing, fitting the 'one or two generic keywords; missing the natural phrases' anchor.

2 / 5

Distinctiveness Conflict Risk

"multi-file html build" carves out a niche giving some distinctiveness, but the generic verb "testing" leaves overlap risk with other build/test skills, matching the 'somewhat specific but could still overlap' anchor.

3 / 5

Total

9

/

20

Passed

Validation

100%

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

yusufkaraaslan/Skill_Seekers

Path

tests/golden/phase2/html_multi/SKILL.md

Revision

5b5d8df

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill