story-long-scan

长篇网文扫榜。分析起点、番茄、晋江等平台排行榜数据，提炼市场趋势与热门题材。触发方式：/story-long-scan、/长篇扫榜、「长篇什么火」「起点排行」。

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A dense, highly actionable multi-phase workflow with strong validation checkpoints and real one-level-deep references. Its main weakness is mild verbosity from inlined detail and a conceptual philosophy section that could be trimmed or externalized.

Suggestions

Move the full Phase 4 report template and per-platform analysis-dimension tables into a reference file, keeping only a short summary inline, to improve progressive disclosure and conciseness.

Tighten the '核心哲学' section to a few bullet heuristics or relocate it to references to reduce token overhead.

Add a brief 'validation failed → recovery' sub-flow example for the 采集质量检查 to make the error path as concrete as the happy path.

Dimension	Reasoning	Score
Conciseness	The body is information-dense (URL/field tables, executable commands, output templates) and avoids explaining concepts Claude already knows; minor over-explanation remains in the '核心哲学' principles section and the inlined full report template, keeping it just below a lean 5.	4 / 5
Actionability	Fully executable copy-paste commands (e.g. 'node scripts/qidian-rank-scraper.js --type {榜单} --outdir {输出目录}') with concrete URLs, per-platform field definitions and output templates cover the common cases across four platforms.	5 / 5
Workflow Clarity	A clear 5-phase sequence with an explicit mandatory '采集质量检查' gate executed after each ranking, immediate-fix feedback loops ('发现问题当场修复') and hard feasibility-cap rules, satisfying the anchor for explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with a well-signaled '参考资料' table pointing one level deep to verified reference/script files; a fair amount of detail (full report template, per-platform analysis-dimension tables) is inlined rather than split out, so it does not fully reach the 'content appropriately split' anchor of 5.	4 / 5
	Total	18 / 20 Passed

Description

78%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 clear, well-triggered description in third person that answers both what and when with concrete invocation phrases. It is slightly held back by abstract action verbs and minor overlap risk with sibling story-long skills.

Suggestions

Sharpen the 'what' by listing 3-4 granular actions (e.g. 采集榜单数据、清洗字段、分析题材趋势、产出选题决策) instead of the abstract pair '分析/提炼'.

Add a one-line disambiguator clarifying this is the scan/采集 step versus the sibling analyze/write skills to reduce overlap risk.

Consider adding a common synonym or file extension (e.g. '.md 报告', '网文热度') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('长篇网文扫榜') and two concrete actions ('分析...平台排行榜数据', '提炼市场趋势与热门题材'), matching the anchor for 1-2 concrete actions but not comprehensive; the verbs are fairly abstract rather than a granular action list, so it does not reach the 'several specific actions' of a 4.	3 / 5
Completeness	Explicitly answers both what (analyze ranking data, distill trends/hot topics) and when via a dedicated '触发方式' clause listing concrete trigger phrases, matching the anchor that requires clear answers to both with concrete triggers.	5 / 5
Trigger Term Quality	Good keyword coverage including slash commands (/story-long-scan、/长篇扫榜), natural user phrases ('长篇什么火', '起点排行') and platform names (起点/番茄/晋江); falls short of a 5 because it lacks broader synonyms and file extensions rather than being exhaustively comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche (long-form web-novel ranking scanning) with distinct slash-command triggers, but it does not disambiguate from closely related sibling skills (story-long-analyze, story-long-write, story-short-scan) referenced in the body, leaving minor overlap risk.	4 / 5
	Total	16 / 20 Passed

Validation

81%

Warnings & errors only

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

Criteria	Description	Result
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
Path: skills/story-long-scan/SKILL.md
Commit: 5de060f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.