CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-constraint

给一个领域、专业、角色、产品或争论找出真正框住它的几条约束,判明它们属于世界/规则/解释(硬/软/自设),看这组约束如何定义身份、补全问题、框出解空间并解释实际行为;尤其用于区分目标相同但约束不同导致的方案分歧,识别被误当硬事实的旧解释。USE WHEN 用户说 '约束', '找约束', '这个领域的约束是什么', '本质约束', '什么框住了它', '硬约束还是自设约束', '边界在哪', '这行为什么这么做', 'constraint', '/ljg-constraint', or gives any domain/profession/role/product/debate and wants its defining constraints and solution space mapped. NOT FOR 往下挖生成器(用 ljg-rank,找的是生成力不是边界)、纵向深钻一个观点到底(用 ljg-think)、拆一本书(用 ljg-book)、一个概念解剖(用 ljg-learn)。

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 a rich, well-sequenced method with concrete procedures, validation loops, precise diagram specs, and a defined output format — strong on actionability and workflow clarity. Its weaknesses are verbosity from philosophical framing and a monolithic single-file structure that underuses progressive disclosure despite having a clean one-level reference.

Suggestions

Tighten the '约束是什么' and '三层硬度' sections by trimming the water/cup, camel/desert, and '人不能飞' metaphors to one-line illustrations, keeping the procedural spine lean.

Move the three ASCII diagram templates and their character spec into a references/diagrams.md file, signaled from SKILL.md, so the main file reads as an overview pointing to detailed materials.

Consider extracting the extended conceptual framing (约束是什么 / 从约束到解空间到行为) into a reference file, leaving SKILL.md focused on the workflow, checklist, and output.

DimensionReasoningScore

Conciseness

The procedural core (7-step process, 心内判据 checklist, diagram specs, output format) is efficient, but extended philosophical exposition — the water/cup metaphor ("没有约束的东西没有形状..."), the camel/desert evolutionary metaphor, the "人不能飞" aside — pads the token budget with framing Claude largely does not need. It is mostly efficient but could be tightened, matching the score-2 anchor rather than the lean score-3 anchor.

2 / 3

Actionability

For an instruction-only skill the guidance is concrete and executable: a numbered 7-step process with specific probing questions, a 7-item verification checklist, three ASCII diagram templates with exact allowed/disallowed character lists, and an output section with exact commands (date +%Y%m%dT%H%M%S) and file path pattern. This matches the score-3 anchor of concrete, copy-ready guidance.

3 / 3

Workflow Clarity

A clearly sequenced 7-step process is paired with explicit validation checkpoints and a feedback loop: the 心内判据 section states "过不了一条,回工序接着走" and the diagram spec says "右边对不上左边,就是约束没找准,回去接着挖". This matches the score-3 anchor of a clear sequence with explicit validation and error-recovery loops.

3 / 3

Progressive Disclosure

The single reference (references/template.org) is one-level deep and clearly signaled ("frontmatter 见 references/template.org"), and the body is well-organized with section headers. But the SKILL.md is a ~240-line monolithic file where substantial conceptual sections and the diagram-template library are inline rather than split into reference files, fitting the score-2 anchor of content that could be better separated more than the score-3 anchor of content appropriately split across files.

2 / 3

Total

10

/

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 exemplary: it states concrete capabilities, supplies abundant natural trigger terms, answers both what and when explicitly, and sharply distinguishes itself from adjacent skills via a NOT FOR clause. No first/second-person voice is used, so no voice penalty applies.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "找出真正框住它的几条约束", "判明它们属于世界/规则/解释(硬/软/自设)", "框出解空间并解释实际行为", "区分目标相同但约束不同导致的方案分歧", "识别被误当硬事实的旧解释" — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (找出约束、判明硬度、框解空间、解释行为) and when (an explicit "USE WHEN" trigger clause plus a "NOT FOR" exclusion clause), matching the anchor for clearly answering both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

The USE WHEN clause packs natural phrases a Chinese user would actually say — '约束', '找约束', '这个领域的约束是什么', '本质约束', '边界在哪', '这行为什么这么做', 'constraint', '/ljg-constraint' — giving good coverage of natural terms rather than jargon.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche (constraint/solution-space analysis) and the "NOT FOR" clause explicitly distinguishes it from sibling skills (ljg-rank, ljg-think, ljg-book, ljg-learn) with reasons, making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

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.

Validation15 / 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
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.