CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

story-short-analyze

短篇网文拆文。拆解爆款短篇小说(番茄短篇 / 故事会 / 知乎盐言 / 追妻 / 世情 / 重生 / 虐渣等通俗题材)的故事核、结构、情感线、反转设计、写作手法、共鸣层次。单一全量拆解管道:跑完 Stage 2-6 产出完整拆文报告,落盘到 拆文库/{书名}/,下游 story-short-write 同时读拆文报告 + 情节节点 + 写作手法 + 原文 + _meta.json 写下一篇。触发方式:/story-short-analyze、/短篇拆文、「拆短篇」「拆这篇短文」「短篇拆文」「精细拆解短篇」「8000 字短篇拆解」「番茄短篇拆文」「故事会拆解」「盐言故事拆解」「分析这篇短篇」——均进入同一管道。

Quality

95%

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

92%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 pipeline skill: concrete thresholds, immutable file contracts, staged execution with write-ahead crash recovery, and a gated three-check acceptance loop with explicit remediation. Its only weakness is minor repetition of the observation-scale and boundary caveats, which keeps conciseness at 4 while everything else sits at the top anchor.

DimensionReasoningScore

Conciseness

The body is dense and operational — routing thresholds, file names, stage tables, message templates — with essentially no explanation of concepts Claude already knows. It falls short of the lean anchor only through minor redundancy, e.g. the observation-scale caveat stated twice (「题材作为观察标尺——…不调用长篇阶段、卷级循环或黄金三章模型」 in Step 3 and 「标尺都是**观察标尺**:…也不从长篇 Skill 加载题材、节奏或质量资料」 in the reading table) and a few long parentheticals that could be trimmed.

4 / 5

Actionability

For an instruction-only skill the guidance is fully executable: exact numeric routing (「≤ 20,000 / 20,000 - 30,000 / > 30,000」), exact output files and immutable names (「三个 markdown…不可改名」), enumerated _meta.json fields, per-stage output specs (「写作手法(≥5项维度…)」「开头分析(前50/100字)」「共鸣分析(≥3层)」), and verbatim author-facing message templates. Common cases (no text provided, gray-zone word count, resume-after-interrupt, already-completed) are each covered with literal scripts.

5 / 5

Workflow Clarity

The pipeline is explicitly sequenced with dependencies (「2 → 3 → 4 → 5 → 6(严格串行,每阶段依赖前一阶段数据)」), each stage has a completion flag, and write-ahead progress tracking (「每个 Stage 开始前写入 _meta.json.last_stage_in_progress…确认非空且长度合理后,才清空它」) makes interruption recoverable. The acceptance gate is a three-check validation (表达自检 / structure_counts 校验 / BLOCK 项扫描) with an explicit feedback loop (「任一阻断 → 回到对应 Stage 补写」), matching the top anchor's validation-plus-error-recovery pattern.

5 / 5

Progressive Disclosure

The body is a lean overview that delegates detail via a reading-schedule table specifying exactly which reference files to read at each phase, with conditional additions clearly signaled (「源文靠证据链或信息差推进:analysis-short-suspense.md」). All 15 referenced files exist in references/ and cross-reference each other only at peer level — one level deep, easy to navigate, matching the well-signaled one-level-deep anchor.

5 / 5

Total

19

/

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.

A model description: it states concrete capabilities (six analysis dimensions, a staged pipeline, exact output artifacts and their downstream consumer) and pairs them with an explicit, exhaustive trigger list covering commands, colloquial verbs, and platform names. All four dimensions sit at the top anchor with no fluff or over-claiming.

DimensionReasoningScore

Specificity

The description enumerates six concrete analysis targets (「拆解爆款短篇小说…的故事核、结构、情感线、反转设计、写作手法、共鸣层次」), specifies the pipeline and output location (「跑完 Stage 2-6 产出完整拆文报告,落盘到 拆文库/{书名}/」), and names the downstream contract files. This matches the comprehensive-coverage anchor; nothing is generic or padded, and it stays below the 5 anchor's only failure mode by covering what, where, and how output is consumed.

5 / 5

Completeness

Both halves are explicit: the 「what」 is the full teardown scope with named deliverables (拆文报告 + 情节节点 + 写作手法 + _meta.json) and the downstream read by story-short-write, and the 「when」 is a dedicated 「触发方式」 clause listing concrete trigger phrases. This is the anchor-5 pattern (what AND when with concrete triggers), not anchor 4 where the when is only broadly stated.

5 / 5

Trigger Term Quality

「触发方式:/story-short-analyze、/短篇拆文、「拆短篇」「拆这篇短文」「短篇拆文」「精细拆解短篇」「8000 字短篇拆解」「番茄短篇拆文」「故事会拆解」「盐言故事拆解」「分析这篇短篇」」 covers slash commands, verb variants (拆/分析/精细拆解), and platform synonyms (番茄/故事会/盐言). These are exactly the phrases a Chinese web-fiction author would naturally say, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is sharply delimited to short-form teardown (「单一全量拆解管道」), and every trigger phrase carries a short-form marker (短篇/短文), so it will not fire for the sibling long-form analysis or writing skills. Conflict risk is minimal, fitting the clear-niche-distinct-triggers anchor rather than anchor 4's 「minor overlap risk with closely related skills」.

5 / 5

Total

20

/

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-short-analyze/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.