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

70%

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

Fix and improve this skill with Tessl

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

Quality

Content

50%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 body is well-organized and teaches a clear, distinctive methodology with concrete structural rules, but it leans on two referenced files (Workflows/Extract.md, References/QuestionDesign.md) that are absent from the bundle, weakening actionability and progressive disclosure. Some boilerplate (voice-notification curl) also dilutes conciseness.

Suggestions

Either ship the referenced Workflows/Extract.md and References/QuestionDesign.md files, or inline the concrete extraction steps and question-design patterns directly so the skill is self-contained.

Trim the Voice Notification curl block and the restated '你不是' / chisel-and-nail metaphors to tighten the token budget.

Promote the implicit review step from Gotchas into an explicit validation checkpoint in the workflow (e.g., 'After drafting, scan every Q: if one answerable by a one-line definition, rewrite').

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and directive and assumes Claude's competence, but the Voice Notification curl block and repeated metaphor restatements ('Q 是凿子，A 是钉子', the four '你不是' bullets) add tokens that do not fully earn their place.	2 / 3
Actionability	Concrete guidance is present (the strict four-segment A structure, org-mode output format, denote filename pattern, and worked examples), but the core executable workflow is deferred to 'Workflows/Extract.md' which is not present in the bundle, leaving key details incomplete.	2 / 3
Workflow Clarity	A loose sequence is implied via the Examples (fetch → find skeleton → design Q chain → write A → output) and a review step is hinted in Gotchas, but the main step sequencing is offloaded to a missing Workflows/Extract.md rather than stated explicitly with checkpoints.	2 / 3
Progressive Disclosure	The body is well-sectioned and references are clearly signaled by named path ('Workflows/Extract.md', 'References/QuestionDesign.md'), but those referenced bundle files do not exist, so the one-level-deep navigation cannot actually resolve.	2 / 3
	Total	8 / 12 Passed

Description

90%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 states what the skill does, when to use it via natural trigger terms, and explicitly delineates its niche with a NOT-FOR boundary. Its only weakness is that the 'what' centers on a single operation with quality framing rather than enumerating multiple distinct actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('给一篇文章/论文/书') and the core action ('把核心观点抽成 Q-A 对') with quality constraints, but describes essentially one operation rather than listing multiple concrete actions, so it falls short of the top anchor.	2 / 3
Completeness	Clearly answers both what (extract Q-A pairs with formalized answers reproducing the author's reasoning) and when via an explicit 'Use when user says...' clause, with an additional 'NOT FOR...' boundary.	3 / 3
Trigger Term Quality	Lists natural terms users would say — '问答', 'Q&A', 'QA', '提问', '抽取问题', '/ljg-qa' — plus a scenario trigger ('shares an article/paper/book and asks for Q-A extraction'), giving good coverage of natural variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear intellectual-scaffolding niche with distinct triggers and an explicit 'NOT FOR FAQ generation, glossary creation, or comprehension quizzes' boundary, making conflict with other skills unlikely.	3 / 3
	Total	11 / 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-qa/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.