CtrlK
BlogDocsLog inGet started
Tessl Logo

story-long-write

长篇网文写作。从大纲到正文,辅助长篇网络小说的创作,包括世界观、人物、情节线管理。触发方式:/story-long-write、/写长篇、「帮我开书」「写大纲」「日更」「续写」「继续写」「修改第X章」「回炉」「重写第X章」。

68

Quality

83%

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 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A comprehensive, well-architected long-form writing skill with excellent workflow sequencing, validation gates, and a clean progressive-disclosure structure backed by real bundle files. Its main weakness is conciseness: several gating/version/adapter caveats are repeated and could be tightened or moved into references.

Suggestions

Consolidate the repeated fail-fast / repair-action rules (缺失文件处理 6 items, Reference Gate, and version-mismatch notes) into a single references/workflow-gates.md and keep only the routing trigger in SKILL.md to reduce token load.

Move the multi-IDE agent adapter and agents_version (29) compatibility caveats into a short references/runtime-adapters.md, leaving a one-line pointer in the body.

Trim restatements of the same constraint across 核心方法, 写作流程, and the Reference Gate (e.g. '停在细纲交付,不自动写正文' appears multiple times) to a single canonical statement.

DimensionReasoningScore

Conciseness

The body is dense and information-rich but noticeably padded in places: long caveats on multi-IDE agent adapters, version-mismatch notices, and repeated fail-fast/repair-action prose restate the same gating concept multiple times, which could be tightened and pushed into references.

3 / 5

Actionability

Concrete executable guidance is present: explicit commands (scripts/tracking_commit.py check, scripts/author_memory_commit.py query --kind prose_style --kind story_design), a full file-structure tree, a detailed 产物映射表, and named reference files per scenario. Minor gaps: the Phase 1-5 steps themselves are deferred to references rather than shown inline.

4 / 5

Workflow Clarity

Multi-step processes are clearly sequenced (Phase 1→2→3→4→5) with a routing table by trigger condition, explicit matching-priority ordering, batch limits, a Reference Gate with fail-fast validation (必需路径不存在…立即停止,不得先写正文再补读), Constraint Lock delivery checklist, and feedback loops (tracking_commit.py check → repair → retry) for batch/destructive writing operations.

5 / 5

Progressive Disclosure

Clear overview routing to well-signaled one-level-deep references; all cited reference files and scripts (42 reference .md files, 32 genre-prose-cards, 9 scripts) exist and are organized by phase/场景, with a 按主题快速定位 cross-cutting index giving authoritative-vs-supporting file guidance. Content is appropriately split rather than inlined.

5 / 5

Total

17

/

20

Passed

Description

90%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, trigger-rich description that clearly states a long-form web-novel writing domain and enumerates concrete natural-language triggers users would actually say. Minor distinctiveness overlap risk with sibling story skills and slightly high-level action wording keep it just below perfect.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions (世界观、人物、情节线管理, 从大纲到正文) plus a clear deliverable scope, but the actions are high-level genre-craft categories rather than multiple distinct concrete operations, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (长篇网文写作:从大纲到正文,辅助世界观/人物/情节线管理) and 'when' with concrete trigger phrases prefixed by 触发方式, matching the anchor for explicit what-and-when with concrete triggers.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including the slash command (/story-long-write), the Chinese alias (写长篇), and multiple natural phrases users would actually say (帮我开书、写大纲、日更、续写、修改第X章、回炉、重写第X章).

5 / 5

Distinctiveness Conflict Risk

The 长篇网络小说 niche with these specific Chinese triggers is mostly distinct from sibling skills (story-short-write, story-deslop), though natural phrases like 写大纲/续写 could overlap with adjacent story skills in the pipeline.

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.

Validation13 / 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
worldwonderer/oh-story-claudecode
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.