CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-word

Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to explain/master a specific English word.

65

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary lean instruction-only skill: it gives a precise, template-driven output structure with concrete micro-examples and zero padding, and its small size needs no external files. The only gap is that a couple of quality directives ('penetrating insight', 'philosophical height') are aspirational rather than operational, and a single complete sample output would make it copy-paste unambiguous.

DimensionReasoningScore

Conciseness

The body is ~35 lines with zero padding: a one-line goal statement ("目标不是翻译,而是让用户掌握这个词的深层含义和用法"), a casing rule, and a compact output spec. It assumes Claude's competence and never explains what a word or Markdown is, matching 'lean and efficient; every token earns its place'.

5 / 5

Actionability

The output structure is concrete and executable: an exact title-line template (`## {Word} /{音标}/ {中文翻译}`), worked micro-examples ("Incubate: 母鸡趴在蛋上", "温暖 + 时间 + 保护 = 孕育"), and a literal quote format. It falls short of 5 because directives like "要有穿透力,展现词源、多领域含义之间的内在联系" and "必须具有哲学高度" are aspirational rather than actionable, and there is no complete worked example of a full output.

4 / 5

Workflow Clarity

This is a simple single-purpose skill (under 50 lines, one task) and the single action is unambiguous: normalize the word ("转换为小写,首字母大写"), then emit a fully-specified three-part output in order. No destructive or batch operations are involved, so no validation checkpoints are required — the simple-skill exception applies and the sequence leaves no gaps.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and no references/ directory exists (verified — references/, scripts/, assets/ are all absent). Per the rubric's guideline, well-organized sections alone qualify: the body is cleanly split into Usage, Instructions, and a numbered 输出结构 with subsections.

5 / 5

Total

19

/

20

Passed

Description

66%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 short, third-person, and has an explicit 'Use when' clause with a clear niche, but the capability statement is abstract — 'core semantics and epiphany' doesn't tell the reader (or the model routing on it) what concrete outputs the skill produces. Trigger coverage lacks natural synonyms like 'what does this word really mean' or 'etymology'.

Suggestions

Replace the abstract 'core semantics and epiphany' with the skill's concrete deliverables, e.g. 'Deconstructs an English word into its root image, core-imagery formula, insightful explanation, and a bilingual aphorism'.

Broaden the trigger clause to include natural user phrasings: 'Use when the user asks to explain, deeply analyze, or master a specific English word, its etymology, or its nuanced meaning (e.g. "deeply explain serendipity")'.

Add 1-2 more concrete actions to the 'what' statement (e.g. 'derives the core-imagery formula' and 'produces a bilingual one-liner') to lift specificity from abstract to actionable.

DimensionReasoningScore

Specificity

The description names the domain ("a single English word") and one to two actions ("Deconstructs a single English word into core semantics and epiphany"), but 'core semantics and epiphany' is abstract rather than a list of concrete actions like 'etymology, imagery formula, bilingual aphorism'. It is not the vague 'helps with words' of a 1, nor does it list the several specific actions needed for a 4.

3 / 5

Completeness

Both parts are present: the 'what' ("Deconstructs a single English word into core semantics and epiphany") and an explicit 'Use when' clause ("Use when user asks to explain/master a specific English word"). It falls short of a 5 because the 'when' trigger phrase is generic ('asks to explain/master') and the 'what' leans on the abstract term 'epiphany' rather than concrete deliverables.

4 / 5

Trigger Term Quality

It includes relevant phrases users would say — "explain/master a specific English word" — but misses common variations like 'deeply explain this word', 'what does X really mean', 'etymology of', 'vocabulary', or 'definition'. Coverage exists but synonyms and variations are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Deep-dive English word mastery" and "a specific English word" carve out a clear niche with distinct triggers (single-word deep explanation), unlike generic writing or translation skills. Conflict risk with other skills is minimal; the anchor-5 example has similarly narrow, distinct triggers.

5 / 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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
lijigang/ljg-skills
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.