CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ljg-is

把一个名词或概念写成可使用的理解:先用普通话讲清它是什么、与相邻概念差在哪里,再说明它怎样运作、会改写什么判断,最后给出面对它时的行动抓手。USE WHEN 用户问 X 是什么、怎么理解、意味着什么、为什么重要、以后怎样判断或使用;尤其适合技术概念、制度、产品、角色、方法、规范与实践。NOT FOR 单纯查事实、公式证明、逐步操作教程、纵向因果深挖(用 ljg-think)或母题结构(用 ljg-structure)。

Quality

78%

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/ljg-is/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.

The body teaches a writing methodology effectively through concrete standards, sharp anti-pattern tests, and worked contrast examples, with no wasted tokens on known concepts. Its weaknesses are the missing production sequence and a Workflow Routing table that points to a nonexistent TraceCreation.md file.

Suggestions

Ship the referenced Workflows/TraceCreation.md in the bundle (or remove the Workflow Routing table and inline the creation steps), since the routing entry currently points to a file that does not exist.

Make the production sequence explicit — e.g. steps from the user's question through drafting to writing the Org file — and frame the 成品标准 as a validation checklist to run before saving, which would also supply the missing checkpoints.

Merge the three restatements of the four-part contract (the four-question block, 成品标准, and overlapping Gotchas such as the definition-boundary pair) to trim repeated content.

DimensionReasoningScore

Conciseness

The body is dense and skill-specific with no padding about concepts the model already knows; each Gotcha is a distinct, usable test (e.g. "删除概念名后仍然成立,说明它没有使用前文的理解"). It is not anchor 5 because the four-part contract is restated three times (four-question block, 成品标准, Gotchas) and could be tightened.

4 / 5

Actionability

For an instruction-only skill the guidance is concrete: an output path template "~/Context/{时间戳}--理解-{目标片段}__is.org", the "ljg-is-v5" schema, structural constraints ("两到四个随内容生出的标题和四到十个自然段"), and worked before/after examples plus boundary cases with routing decisions. It is not anchor 5 because there is no explicit step sequence from user query to finished file — that presumably lives in the routed workflow file, which is absent from the bundle.

4 / 5

Workflow Clarity

The four questions form an implicit path ("这四个问题是一条理解路径,不是四个正文栏目"), and the 成品标准 functions as a quality checklist, but neither is framed as a sequenced procedure with validation checkpoints. This fits anchor 3 — sequence present but implicit, checkpoints missing — rather than anchor 4, especially since the creation workflow is routed to a file that does not exist in the bundle.

3 / 5

Progressive Disclosure

The single-file body is well organized with clear sections, and its one external reference ("Workflows/TraceCreation.md") is clearly signaled in a routing table. However, that file is absent — the bundle contains no Workflows/, references/, scripts/, or assets/ directories — so the one-level-deep navigation dead-ends, matching anchor 3 rather than anchor 4's 'references mostly clear and usable'.

3 / 5

Total

14

/

20

Passed

Description

83%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 strong description: it states a concrete multi-step capability, gives explicit USE WHEN trigger phrases, and adds a NOT FOR clause that disambiguates sibling skills. The only weaknesses are minor — the output artifact is unmentioned and a few natural trigger synonyms are missing.

DimensionReasoningScore

Specificity

The description lists several concrete, ordered actions — "先用普通话讲清它是什么、与相邻概念差在哪里,再说明它怎样运作、会改写什么判断,最后给出面对它时的行动抓手" — covering the full pipeline of the skill. It falls short of anchor 5 only because it omits the concrete output artifact (the Org-mode file and ljg-is-v5 schema), a minor coverage gap.

4 / 5

Completeness

Both halves are explicit: the 'what' is the full transformation pipeline (plain-language definition and differentiation → mechanism → judgment rewrite → action guidance), and the 'when' is a concrete "USE WHEN" clause with specific trigger phrases plus a "NOT FOR" exclusion list. This clearly matches the anchor-5 example structure of explicit what AND when with concrete triggers.

5 / 5

Trigger Term Quality

"USE WHEN 用户问 X 是什么、怎么理解、意味着什么、为什么重要、以后怎样判断或使用" covers the natural phrasings a user would actually say, reinforced by domain triggers "技术概念、制度、产品、角色、方法、规范与实践". A few common variants (e.g. "解释一下 X", "介绍一下", "概念辨析") are missing, so it fits anchor 4 rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The "NOT FOR …(用 ljg-think)或母题结构(用 ljg-structure)" clause explicitly routes away from the two closest sibling skills, giving a clear niche. It is not anchor 5 because broad triggers like "怎么理解 X" could still overlap with other explanation-type skills not named in the routing; it is well above anchor 3's generic-overlap profile.

4 / 5

Total

17

/

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

Path

skills/ljg-is/SKILL.md

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.