CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

story-long-write

长篇网文规划与写作。支持只讨论结构、只写大纲或指定细纲,明确要求正文后再写章节。触发方式:/story-long-write、/写长篇、「帮我开书」「定设定」「出卷纲」「规划剧情」「写大纲」「补细纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An unusually well-engineered orchestration skill: the body is a lean router with explicit sequencing, hard stop points, validation before delivery of batch prose output, and conditional one-level-deep references that all exist in the bundle. The only meaningful improvement is consolidating the repeatedly-stated prose-authorization guardrail.

DimensionReasoningScore

Conciseness

The body is extremely dense, assumes competence, and spends no tokens explaining known concepts — nearly every line is skill-specific routing or rules. It falls short of 5 only because the don't-auto-write-prose guardrail is repeated across the scenario table, 对象优先, 规划续接, and the 裸调用 section, which could be tightened into one place.

4 / 5

Actionability

Guidance is concrete and executable: exact commands (`{PYTHON} {skill 根}/scripts/outline_view.py --chapter {章号} {卷纲路径}`), a per-moment mandatory reading table, a three-tier decision list for new story elements with specific categories, and explicit numeric defaults (单章默认 1 章,日更默认 2-3 章,单轮最多 3 章). Minor gaps remain — e.g., the 申报表 and report formats are delegated to references rather than shown.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced with explicit validation checkpoints: the scenario table maps each trigger to a phase flow with stop points ("每个确认点作者说继续才往下"), the 写前必读 table is a per-stage checklist with hard-fail rules ("缺文件或没读完就停…不得先写正文再补读"), and batch prose work has pre-delivery verification ("交付前逐项复核:字数出了范围…交作者处置") plus error-recovery routing (tracking errors → tracking-transaction.md).

5 / 5

Progressive Disclosure

The SKILL.md is a pure router: a moment-based reading table sends the model to conditionally-required reference files (all verified to exist in references/) at file-or-section granularity, scripts are invoked by exact command, and references stay one level deep. This is a well-signaled, conditionally-loaded structure that keeps the overview lean.

5 / 5

Total

18

/

20

Passed

Description

91%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 description: it states concrete capability modes and pairs them with an explicit, natural-language trigger list including slash commands and a dozen colloquial phrases. Distinctiveness is good, with only minor overlap risk on generic outlining terms.

DimensionReasoningScore

Specificity

The description names the domain ("长篇网文规划与写作") and lists several concrete capability modes ("只讨论结构、只写大纲或指定细纲,明确要求正文后再写章节") rather than generic actions. It stops short of the comprehensive 5-anchor because revision/rework actions are only implied via triggers, not stated as capabilities.

4 / 5

Completeness

Both 'what' and 'when' are answered explicitly and concretely: what it does ("长篇网文规划与写作。支持只讨论结构、只写大纲或指定细纲…") and when to trigger it ("触发方式:…" followed by concrete trigger phrases). This matches the top anchor exactly.

5 / 5

Trigger Term Quality

Trigger coverage is comprehensive and natural: the slash commands plus 12 colloquial phrases a Chinese web-novel author would actually say (「帮我开书」「定设定」「出卷纲」「写大纲」「补细纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」), including synonyms for the same intent (续写/继续写, 修改/重写, 写大纲/规划剧情).

5 / 5

Distinctiveness Conflict Risk

The 长篇网文/开书/日更/回炉 vocabulary carves a clear niche with minimal conflict risk, but broadly applicable phrases like 「写大纲」「规划剧情」「续写」 could also fire for short-story or generic outlining requests from sibling skills, giving minor overlap risk.

4 / 5

Total

18

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

zenstory-ai/oh-story-claudecode

Path

skills/story-long-write/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.