ljg-structure

找出一段信息中母题级别的结构，把抽象关系展开回具体可见的现象，再用风洞检验关键因果与边界。USE WHEN user says '找结构', '母题是什么', '结构风洞', '背后的结构', '不要只做AB测试', or wants the generative mechanism beneath a problem. 仅当用户明确要求时展开跨域来源或多母题组合。NOT FOR 普通摘要、单个类比、事实查询或已有明确唯一解的执行题。

Quality

85%

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

Quality

Content

70%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured, conceptually rich instruction skill with a clear staged workflow and concrete output spec including a validation read-back. Its weaknesses are moderate verbosity in the Gotchas and a workflow-routing reference to a file that has no accompanying bundle directory.

Suggestions

Tighten the Gotchas section by merging near-duplicate bullets (e.g. the several '母题不是更抽象的标题'/'例子必须映射角色与因果' restatements) to reduce token load without losing guidance.

Either add the referenced Workflows/FindStructure.md as an actual bundle file under a references/ directory, or remove the Workflow Routing table if FindStructure.md is not part of this skill bundle.

Add one concrete, fully-worked example output (org-mode skeleton populated with the first-speaker case) so the output rules are copy-paste ready rather than inferred from prose.

Dimension	Reasoning	Score
Conciseness	The body is mostly earned because the conceptual machinery (母题/类比/结构 distinctions, the wind-tunnel method) is the skill's actual method rather than common knowledge Claude already has, but the long Gotchas list and some restated guidance ('主题是名字，母题是难题…') could be tightened, matching the 'Mostly efficient but includes some unnecessary explanation' anchor.	2 / 3
Actionability	It gives concrete output rules — exact headings, ASCII-only relation graphs, an org-mode template with a file path, and a read-back step — but as an instruction-only analysis skill it stops short of fully copy-paste-ready artifacts and some structural-card guidance stays at the 'describe rather than instruct' level, matching the 'Some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	The conceptual sequence (输入 → 母题 → 结构 → 内部风洞 → 结论) is clearly staged, the conclusion has an explicit two-paragraph structure with a 'force the model to change its mind' checkpoint, and the file workflow ends with a read-back validation step, matching the 'Clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	The file is one well-organized document with clear sections, but the Workflow Routing table points to a 'Workflows/FindStructure.md' path while no references/ scripts/ or assets/ bundle exists in the skill folder, so the signaled external reference is not actually present alongside the skill.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong: it names several concrete capabilities, supplies natural trigger phrases a user would actually say, and pairs an explicit USE WHEN clause with a NOT FOR exclusion list for clear routing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '找出一段信息中母题级别的结构', '把抽象关系展开回具体可见的现象', '再用风洞检验关键因果与边界' — which match the 'Lists multiple specific concrete actions' anchor.	3 / 3
Completeness	It explicitly answers both what (the first sentence of actions) and when (the 'USE WHEN' clause), and adds a 'NOT FOR' exclusion list, matching the 'Clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	The USE WHEN clause gives natural user phrases ('找结构', '母题是什么', '结构风洞', '背后的结构', '不要只做AB测试') plus a plain-language intent ('wants the generative mechanism beneath a problem'), giving good coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche is distinct ('母题结构风洞') with explicit trigger phrases and a NOT FOR boundary that rules out summaries, single analogies, and fact queries, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 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-structure/SKILL.md
Commit: 0e78094

Reviewed: 9 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.