ljg-blind

盲区扫描——读昨天你与 AI 的全部对话，照出暴露的思维盲区（不是不懂的知识，是让某类真相一直看不见的思维习惯），再从微信读书挑一本书的一章精准补上，落成一篇完整分析笔记。Use when user says '扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/ljg-blind', or wants yesterday's AI conversations analyzed for cognitive blind spots plus a targeted weread chapter to fill them. 可选参数：传一个日期(YYYY-MM-DD)扫那天而非昨天。NOT FOR 纵向深钻一个观点（用 ljg-think）、一个领域降秩（用 ljg-rank）、陪读一篇文本（用 ljg-read）、找一个领域的约束（用 ljg-constraint）。

Quality

91%

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

88%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.

A well-engineered, highly actionable skill body with a clearly sequenced five-step workflow, executable code, feedback loops, and a self-check. Minor room to tighten prose and to split reference-style sections into bundle files.

Suggestions

Move the org 严格语法 reference and the 语气规则 rules into a references/ file (e.g. references/note-style.md) and link to it from the body, improving both conciseness and progressive_disclosure.

Tighten the 盲区是什么 framing section — the core definition is needed, but the elaboration paragraphs could be condensed to earn conciseness toward the score-5 anchor.

Consider extracting the 五种盲区信号 taxonomy into references/blind-spot-signals.md so the operational steps in the body stay lean while the conceptual model remains discoverable one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly lean and domain-specific (the 五种盲区信号 framework, f(x)取景框, 切痕风 rules are the skill's own model, not generic Claude knowledge), but the 语气规则 and org 严格语法 sections contain minor over-explanation that could be trimmed, matching the score-4 anchor.	4 / 5
Actionability	Fully executable copy-paste-ready guidance throughout: a complete jq filtering script, exact curl payloads with jq parsing for weread search/chapter APIs, a TypeScript tool invocation, and an org-mode note template, matching the score-5 anchor.	5 / 5
Workflow Clarity	Five explicitly sequenced steps with validation checkpoints and a feedback loop ('没有就退回第三步'), plus a dedicated 自检 checklist and fallbacks (数据稀薄兜底, weread 兜底); the operation is read-mostly with a single note write, so the destructive/batch cap does not apply, matching the score-5 anchor.	5 / 5
Progressive Disclosure	No bundle directories exist; the single SKILL.md is well-sectioned with clear headers and only one-level-deep external references (WeReadWebUrl.ts, sibling ljg-* skills), but reference-style material (语气规则, org 语法, Gotchas) is inlined rather than split into reference files, matching the score-4 anchor.	4 / 5
	Total	18 / 20 Passed

Description

95%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, specific description with comprehensive trigger terms, explicit when-guidance, and clear boundary demarcation against sibling skills. The only ding is the second-person voice, which the rubric penalizes on specificity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('读昨天你与 AI 的全部对话', '照出暴露的思维盲区', '从微信读书挑一本书的一章', '落成一篇完整分析笔记') matching the score-5 anchor, but the second-person voice ('你') triggers the required −1 specificity penalty per the rubric guidelines.	4 / 5
Completeness	Explicitly answers both what (read conversations → surface blind spots → weread chapter → analysis note) and when via a concrete 'Use when...' clause, plus an optional date parameter, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage including synonyms and the slash command ('扫盲区', '盲区', '照盲区', '看看我的思维盲区', '我昨天想漏了什么', 'blind spot', 'ljg-blind', '/ljg-blind'), matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (cognitive blind-spot scanning of yesterday's AI chats plus a weread chapter) with distinct triggers and explicit 'NOT FOR' boundary guidance distinguishing ljg-think/ljg-rank/ljg-read/ljg-constraint, matching the score-5 anchor.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: lijigang/ljg-skills
Path: skills/ljg-blind/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.