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)。

69

Quality

85%

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

70%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-sequenced, actionable methodology with strong validation feedback loops, but it is verbose in places and ships most of its material inline rather than splitting bulky sections into reference files.

Suggestions

Trim the philosophical '约束是什么' section and de-duplicate the '急着找出口,就会看不清墙' and '描述不是改造' refrains to tighten conciseness.

Move the three ASCII diagram templates (and optionally the 中文母语化 style guide) into a references file (e.g. references/diagrams.md) and link to it, improving progressive disclosure.

Keep the 7-step 工序 and 心内判据 checklist as-is — these are the strongest, most executable parts of the skill.

DimensionReasoningScore

Conciseness

Mostly efficient methodology content, but padded with philosophical exposition (the water/cup and light-speed analogies in '约束是什么') and repeated reinforcement ('急着找出口,就会看不清墙' and '描述不是改造' each appear multiple times) that could be tightened.

3 / 5

Actionability

Gives a concrete 7-step 工序 with specific probe questions, a 4-step 落地 sequence, three ASCII diagram templates, and literal output commands with a referenced frontmatter template — actionable for an instruction-only skill, with only minor abstraction in the analytical steps.

4 / 5

Workflow Clarity

A clear 7-step process is paired with a 7-item 心内判据 validation checklist and an explicit feedback loop ('过不了一条,回工序接着走'), giving sequenced steps with checkpoints and error-recovery guidance.

5 / 5

Progressive Disclosure

Section headers provide structure and the one bundle file (references/template.org) is clearly signaled, but the ~244-line monolithic body inlines bulky material — three diagram templates and the style guide — that could be split into one-level-deep references.

3 / 5

Total

15

/

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.

A precise, trigger-rich description that cleanly states capabilities, fires on natural user phrasings, and draws explicit boundaries against neighboring skills. It is among the strongest description examples.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — find framing constraints, classify them as world/rule/explanation (hard/soft/self-imposed), see how they define identity and frame the solution space, distinguish same-goal/different-constraint divergences, and identify old explanations mistaken for hard facts — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (find/classify/frame constraints and explain behavior) and when (USE WHEN with concrete trigger phrases), and adds a NOT FOR clause bounding scope.

5 / 5

Trigger Term Quality

The USE WHEN clause packs natural phrases a user would actually say ('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', '这行为为什么这么做', 'constraint', '/ljg-constraint') including synonyms and variations.

5 / 5

Distinctiveness Conflict Risk

Clear niche (constraint/solution-space analysis) with distinct triggers, and the NOT FOR clause explicitly separates it from sibling skills ljg-rank, ljg-think, ljg-book, and ljg-learn, minimizing conflict risk.

5 / 5

Total

20

/

20

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.