ljg-qa

信息提问机。给一篇文章/论文/书，把核心观点抽成 Q-A 对——Question 切要害，不教科书；Answer 简洁清晰，有形式化收口，逻辑链完整。读者顺 Q 链走过，每个 A 砸下一枚钉子，复现作者整套推理。Use when user says '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa', or shares an article/paper/book and asks for Q-A extraction. Triggers when the user wants ideas extracted not as a summary but as a sequence of incisive questions with answered. NOT FOR FAQ generation, glossary creation, or comprehension quizzes — this is intellectual scaffolding, not study aids.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 is token-efficient and conveys a strong, specific answer template plus concrete output formatting, but its actual execution workflow and design patterns are delegated to two bundle files that are absent, leaving the procedure incomplete and navigation broken. Shipping the referenced Workflows/ and References/ files (or inlining the procedure) would lift actionability, workflow clarity, and progressive disclosure.

Suggestions

Provide the missing 'Workflows/Extract.md' so the extraction procedure steps are actually available, or inline a numbered, validated step sequence in the body.

Provide 'References/QuestionDesign.md' (or inline the Q-design patterns) so the '设计参考' pointer resolves to real content.

Add a validation checkpoint confirming the org-mode file was written to ~/Documents/notes/ and that each A satisfies the four-part (结论/形式化/论证步/边界) structure before finishing.

Dimension	Reasoning	Score
Conciseness	The body is lean — short declarative sections with no padding and no explanation of concepts Claude already knows; the 'Gotchas' capture skill-specific AI failure modes tersely, so every token earns its place per the 5 anchor.	5 / 5
Actionability	The four-part answer template (结论/形式化/论证步/边界) with a worked symbol example and the concrete output path/filename are actionable, but the core extraction procedure delegates to a 'Workflows/Extract.md' that is not present in the bundle, leaving key execution details missing per the 3 anchor.	3 / 5
Workflow Clarity	The workflow is a single delegation to a missing 'Workflows/Extract.md' with no visible sequenced steps or validation in the body, and the skill writes files to ~/Documents/notes/ without a verify checkpoint; the destructive/batch cap of 3 applies and takes precedence over the simple-skill exception.	3 / 5
Progressive Disclosure	The body is cleanly sectioned and references are clearly signaled, but the two referenced files ('Workflows/Extract.md', 'References/QuestionDesign.md') do not exist in the bundle, so the references dangle and navigation does not fully resolve — above 2 (not buried/inline) but below 4 (references must resolve).	3 / 5
	Total	14 / 20 Passed

Description

100%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 concise yet comprehensive: it states concrete capabilities, lists natural Chinese/English trigger terms with an explicit 'Use when' clause, and draws a clear boundary against adjacent study-aid skills. It fully satisfies the specificity, trigger, completeness, and distinctiveness criteria with no first/second-person voice issues.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions comprehensively — '把核心观点抽成 Q-A 对', 'Question 切要害', 'Answer 简洁清晰，有形式化收口，逻辑链完整', '复现作者整套推理' — matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.	5 / 5
Completeness	Explicitly answers both what (extract viewpoints into formalized Q-A chains) and when (a 'Use when...' clause with concrete trigger phrases plus a 'NOT FOR...' exclusion), matching the 5 anchor exactly.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage across Chinese and English variants — '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa' — plus the share-an-article scenario, fitting the synonyms-and-extensions anchor at 5 over the 'few terms missing' anchor at 4.	5 / 5
Distinctiveness Conflict Risk	Clear niche (intellectual Q-A scaffolding from articles/papers/books) with distinct triggers and an explicit 'NOT FOR FAQ generation, glossary creation, or comprehension quizzes' boundary, giving minimal conflict risk per the 5 anchor.	5 / 5
	Total	20 / 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-qa/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.