CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

story

网络小说工具箱主入口。根据用户需求自动路由到对应 skill,并可启动本地 Dashboard。触发方式:/story、$story、/story dashboard、/网文、「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」。

Quality

83%

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

88%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 actionable router skill: concrete commands, exact prompt templates, and explicitly sequenced workflows with fallbacks for nearly every failure mode (missing agents, version mismatches, multiple books, no book directory). The only real costs are a few over-dense inline sections that could be trimmed or moved to reference files.

DimensionReasoningScore

Conciseness

The body is dense and operational with essentially no padding — it never explains concepts Claude already knows, and lines like the routing table and prompt templates earn their tokens. Minor over-explanation could be trimmed, e.g., the single-paragraph spawn version notice ("先读取项目根 .story-deployed 的 agents_version ... 大于 44 时额外提示...") is convoluted enough that it reads as over-long, and host invocation variants are restated across sections.

4 / 5

Actionability

Guidance is copy-paste executable throughout: exact commands (`node "<story-skill-dir>/scripts/dashboard-server.mjs" --root "<workspace>" --open`, `gh release view --json tagName,name,url -R zenstory-ai/oh-story-claudecode`, `curl -fsS --max-time 5 ...`), complete three-line prompt templates with placeholders for story-explorer/story-researcher, and concrete detection markers (`.active-book`, `.story-deployed`, `正文/`, `设定/题材定位.md`).

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation and error recovery: dashboard startup checks node availability, requires the directory to exist, and waits for the "本机地址" output before returning the URL; version check handles gh→curl fallback, unknown current version, and fetch failure ("查不到 → 告知...不报错"); agent spawn defines explicit degraded paths ("story-explorer 不可用 → 主会话直接用 Read/Grep"); updates require explicit user consent before acting.

5 / 5

Progressive Disclosure

Structure is good: a scannable routing table with in-page pointers ("见下方「Dashboard 工作台」") and the heavy implementation properly externalized in real bundle files (scripts/dashboard-server.mjs, 991 lines, plus assets/), referenced by exact path. Some detail that is only needed at execution time — the spawn version-notice rules and the full per-host update paths — is inlined in the always-loaded entry file and could live in one-level-deep reference files, keeping it short of the anchor-5 split.

4 / 5

Total

18

/

20

Passed

Description

73%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 well-formed router description with an explicit trigger clause and natural user phrasing, giving it strong 'when' coverage and low conflict risk. Its main weakness is the thin 'what': it names routing and the Dashboard but never previews the concrete capabilities being routed to.

Suggestions

Enumerate 3-4 concrete routed capabilities in the description (e.g., 长篇/短篇写作、拆文、扫榜、去 AI 味、审稿) to lift specificity from '1-2 actions' toward comprehensive coverage.

Add a few high-frequency trigger synonyms for the sub-intents currently only discoverable in the body (e.g., 拆书、扫榜、选题、去AI味) so the description-level trigger coverage matches the body's routing table.

Keep the description in the same third-person register it already uses while expanding it — avoid turning the trigger list into first/second-person usage guidance.

DimensionReasoningScore

Specificity

The description names the domain ("网络小说工具箱主入口") and exactly two concrete actions — "根据用户需求自动路由到对应 skill" and "并可启动本地 Dashboard" — matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not list the toolbox's specific capabilities (long-form writing, 拆文, 扫榜, 去 AI 味, 审稿, 封面) that would justify a 4.

3 / 5

Completeness

Both parts are present: a clear 'what' ("自动路由到对应 skill,并可启动本地 Dashboard") and an explicit 'when' clause ("触发方式:...") with concrete trigger phrases. The 'what' stays abstract — routing is named but the routed-to capabilities are not enumerated — so it sits at 'both present, one could be more specific' rather than the fully explicit anchor of 5.

4 / 5

Trigger Term Quality

It includes natural phrases users would actually say — 「我想写小说」「记住我的写作习惯」「打开工作台」「检查更新」— plus concrete invocation forms (/story, $story, /story dashboard, /网文), which is good keyword coverage. Common variations for several sub-intents (拆文, 扫榜, 去AI味, 审稿, 封面) are absent, so it falls short of the comprehensive-synonyms anchor of 5.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (web-novel writing toolbox main entry, /网文) with distinctive trigger phrases like 「记住我的写作习惯」 that would not naturally fire unrelated skills. Conflict risk with generic document or writing tools is minimal.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 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

Total

14

/

16

Passed

Repository

zenstory-ai/oh-story-claudecode

Path

skills/story/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.