CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-writes

写作引擎。把一个观点写成可理解、可迁移、经得住反例的 1000-1500 字中文文章。USE WHEN 写文章 OR 优化思想内容 OR 展开观点 OR 改写成逻辑递进的中文。NOT FOR 普通摘要、事实查询或结构风洞(用 ljg-structure)。

68

Quality

84%

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

81%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-structured, substantive writing skill with an explicit workflow, validation checklist, feedback loops, and concrete output templates. The main weakness is mild cross-section repetition and a routed workflow file whose content isn't bundled to verify.

Suggestions

Consolidate the repeated 承重概念/从属机制 and 段首/切刀 guidance so each rule lives in one place; cross-reference instead of restating.

Either bundle Workflows/WriteEssay.md or inline its essential steps so the routed reference is verifiable and self-contained.

Tighten the 姿态与语言 bullet list by merging near-synonymous style rules (e.g., the verb/连词/形容词 items) to reduce token overhead.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's competence — no padding about what essays or writing are — but ideas like 承重概念/从属机制 and 段首/切刀 guidance recur across 成文契约, 姿态与语言, and Gotchas, leaving minor redundancy to trim.

4 / 5

Actionability

Gives copy-paste-ready output constraints (exact date commands, org file header block, filename pattern, ASCII-only) and two worked step traces; the core essay-construction method is procedural/descriptive rather than literal commands, so it is mostly rather than fully executable.

4 / 5

Workflow Clarity

The 讲解引擎 section lays out an explicit sequence (最小案例 → 零号模型 → 缺口 → 概念补位 → 同案重跑 → 整体回收 → 迁移与边界) with a validation checklist (四项成文契约) and feedback loops (rewrite-and-compare, save→readback→org-lint→report).

5 / 5

Progressive Disclosure

Well-organized into clear sections with one clearly signaled one-level reference (Workflows/WriteEssay.md via the routing table); no bundle files ship alongside to confirm that split is appropriately placed, keeping it just short of the top anchor.

4 / 5

Total

17

/

20

Passed

Description

87%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, tight description that states what it does, when to use it, and where not to use it. Trigger phrasing is natural and the negative boundary actively reduces conflict risk.

DimensionReasoningScore

Specificity

Lists several concrete writing actions — '写成...文章', '优化思想内容', '展开观点', '改写' — plus a concrete output spec (1000-1500 字中文); the verbs overlap as variations of writing rather than distinct capabilities, so it stops short of comprehensive.

4 / 5

Completeness

Explicitly answers both 'what' (写作引擎 that turns a viewpoint into a transferable, counterexample-resilient article) and 'when' (USE WHEN ... with concrete trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Natural user-facing triggers like '写文章', '优化思想内容', '展开观点' are present and would be said verbatim, but common synonyms ('写一篇', '帮我写') are not covered.

4 / 5

Distinctiveness Conflict Risk

Clear niche (Chinese viewpoint-to-essay) with distinct triggers and an explicit NOT FOR boundary that routes collisions to ljg-structure, minimizing wrong-skill activation.

5 / 5

Total

18

/

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.