CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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)。

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

73%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 instruction-only skill: the process is precisely sequenced with explicit validation gates and feedback loops, output is concretely specified, and the reference file is real and clearly signaled. Its weaknesses are repetition of the same 'don't rush to loosen constraints' principle across many sections, a Markdown-vs-org inconsistency in the output-format guidance, and a long always-loaded body that could offload the diagram gallery and style guide to references.

Suggestions

State the 'description before modification, loosening comes second' principle once in Gotchas and once in 松动哪条, and cut its repetition from 约束是什么, step 3, 心内判据, and the diagram sections — this is the main source of avoidable tokens in the conciseness dimension.

Resolve the output-format inconsistency: the Workflow Routing table and Example 1 say "保存为 Markdown 文件" while the 输出 section writes a `.org` file with org-mode frontmatter from `references/template.org`; align all three on the org format.

Move the three ASCII diagram templates (or the 中文母语化 style guide) into a `references/` file and link it from a short in-body section, slimming the always-loaded SKILL.md body while keeping the skill's per-execution core inline.

DimensionReasoningScore

Conciseness

The core methodology (7-step 工序, 4-step 解空间落地, 7-gate 判据, 3 diagram forms) is dense and load-bearing, but the 'description first, loosening second' principle is repeated in roughly six places (Gotchas, 约束是什么, step 3, 心内判据, 松动哪条, and both diagram sections) and the 约束是什么 philosophical preamble is expansive — mostly efficient, but noticeably could be tightened.

3 / 5

Actionability

Guidance is largely executable: copy-paste commands (`date +%Y%m%dT%H%M%S`), a concrete output path (`~/Documents/notes/{时间戳}--{领域}的约束__constraint.org`) backed by the real `references/template.org`, three worked examples, and discriminating questions for each hardness layer — but the routing table and Example 1 say "保存为 Markdown 文件" while 输出 specifies a `.org` file with org-mode frontmatter, an output-format inconsistency that is a minor gap.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced (铺约束候选 → 分层归位 → 真伪定性 → 错配 → 矛盾对 → 身份约束 → 两把透镜, then 补全题面 → 列出约束组 → 框出解空间 → 解释实际操作) with an explicit 7-item post-hoc checklist and feedback loops ("过不了一条,回工序接着走"; "右边对不上左边...回去接着挖,别硬画"), matching the validation-with-error-recovery anchor.

5 / 5

Progressive Disclosure

The body is well-sectioned with clear headers and its single reference is clearly signaled and one level deep ("frontmatter 见 `references/template.org`", verified to exist with the frontmatter template). However, the ~240-line monolithic body inlines material that could live in reference files — the three ASCII diagram templates (~50 lines) and the 中文母语化 style guide — leaving minor organization gaps rather than a fully appropriate split.

4 / 5

Total

16

/

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.

An exemplary description: it names the skill's concrete capabilities, gives comprehensive natural trigger phrases in Chinese and English (including the slash command), answers both what and when explicitly, and carves out its niche against four sibling skills with a NOT FOR clause. Voice is third-person descriptive with no fluff despite its density.

DimensionReasoningScore

Specificity

The description lists multiple concrete, specific 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)", "定义身份、补全问题、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" — with no meaningful gaps in coverage, matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

It explicitly answers both 'what' (find and classify defining constraints, map the solution space, explain actual behavior) and 'when' ("USE WHEN 用户说 '约束'... or gives any domain/profession/role/product/debate"), plus a "NOT FOR" exclusion list, satisfying the concrete-trigger-phrases anchor; a missing when-clause cap does not apply.

5 / 5

Trigger Term Quality

Trigger terms are comprehensive and natural in both languages — '约束', '找约束', '本质约束', '什么框住了它', '边界在哪', '这行为什么这么做', 'constraint', '/ljg-constraint' — covering synonyms, question phrasings, the English keyword, and the slash command, which matches the top anchor including synonyms.

5 / 5

Distinctiveness Conflict Risk

Clear niche (constraint mapping and solution-space analysis) with distinct triggers and explicit disambiguation from sibling skills — "NOT FOR 往下挖生成器(用 ljg-rank)...(用 ljg-think)...(用 ljg-book)...(用 ljg-learn)" — so conflict risk is minimal.

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.

Validation — 15 / 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

Path

skills/ljg-constraint/SKILL.md

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.