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.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ljg-word/SKILL.md

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.

The body is a compact, well-structured instruction template for a single-purpose word-mastery skill that respects Claude's intelligence and avoids concept over-explanation. Its main weaknesses are interpretive (non-executable) directives in the explanation section and an absence of any validation or self-check step on the produced output.

Suggestions

Replace interpretive directives ('用充满洞见的语言', '要有穿透力') with concrete, checkable criteria for the 解释 section, e.g. required elements like etymology linkage and at least one cross-domain usage.

Add a brief validation/self-check step at the end (e.g. 'verify the title line contains phonetic + translation, the 金句 is bilingual, and all key terms are bolded') to catch missing output before delivering.

Make the 标题行 template fully concrete by showing the expected phonetic/translation placeholders inline rather than relying on {音标}/{中文翻译} tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean for a single-purpose skill — it states the goal, the output structure, and per-section instructions without padding Claude's existing knowledge, with only minor phrasing that could be trimmed, matching the score-4 anchor of 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	It gives concrete, structured guidance (explicit output template, required bold formatting, the title-line format with phonetic and translation) but no executable code or copy-paste-ready command, and some directives are interpretive ('用充满洞见的语言', '要有穿透力') rather than fully specified, fitting the score-3 anchor of 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	The four output sections are clearly sequenced (标题行 → 核心语义 → 一语道破) and the single action is unambiguous, but there are no validation checkpoints verifying the generated output (e.g. that the bilingual quote or bold keywords are present), so it sits at the score-3 anchor of 'steps listed but validation gaps'.	3 / 5
Progressive Disclosure	Content is well-organized under clear headers with no bundle files present and everything appropriately inlined for a short single-purpose skill, with the only minor gap being that section numbering is split across header levels, matching the score-4 anchor of 'good structure; most content appropriately placed'.	4 / 5
	Total	14 / 20 Passed

Description

62%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 cleanly states both what the skill does and when to use it with a clearly distinct single-word-mastery niche. It loses points for listing only one concrete action and for limited coverage of the natural trigger terms users would actually say.

Suggestions

Add 1-2 more concrete actions to broaden coverage (e.g. 'analyzes etymology, usage, and connotation') so it reads as comprehensive rather than a single deconstruct operation.

Expand trigger terms with synonyms users naturally say, such as 'define', 'meaning of', 'etymology of', or 'how to use the word'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('English word mastery') and one concrete action ('Deconstructs a single English word into core semantics and epiphany') but is not comprehensive — it lists only the deconstruct action rather than several specific operations, matching the score-3 anchor of naming a domain plus 1–2 concrete actions.	3 / 5
Completeness	It gives a clear 'what' ('Deconstructs a single English word into core semantics and epiphany') and an explicit 'when' ('Use when user asks to explain/master a specific English word'), with both present though the 'when' is slightly generic — fitting the score-4 anchor of having both what and when with the 'when' somewhat explicit but not maximally specific.	4 / 5
Trigger Term Quality	It includes relevant keywords ('English word', 'explain/master a specific English word'), but misses common natural variations and synonyms a user might say (e.g. 'define', 'meaning of', 'etymology', 'usage'), aligning with the score-3 anchor of 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The trigger is a fairly distinct niche (deep-dive mastery of a single English word) that would not collide with most skills, with only minor overlap risk against generic dictionary/explanation capabilities, matching the score-4 anchor of 'mostly distinct; minor overlap risk'.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: lijigang/ljg-skills
Path: skills/ljg-word/SKILL.md
Commit: 44f4105

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.