data-storytelling

数据科学家与产品经理在向高管汇报或制作投资者演示时，当面临数据枯燥难懂的痛点，使用此技能可套用“Setup-Conflict-Resolution”叙事框架，自动生成结合可视化与业务上下文的洞察报告，让非技术受众秒懂结论并驱动决策。

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/data-storytelling/data-storytelling/SKILL.md

Quality

Content

42%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.

The content offers useful concrete templates and one real code example, but it is markedly verbose—re-explaining general storytelling knowledge Claude already has and inlining large mockups that inflate the token budget. It also lacks the validation/feedback-loop structure and file-based progressive disclosure that would make it tighter and easier to navigate.

Suggestions

Trim conceptual padding (narrative arc, rule of three, do's/don'ts, ASCII slide mockups) that Claude already knows, keeping only the distinctive SCR framework and executable templates to raise conciseness.

Move the three full story-framework templates and the visualization/presentation templates into separate reference files under ./references/ and signal them with one-level-deep links so the SKILL.md body stays a lean overview.

Make the matplotlib example copy-paste ready by either defining the variables (dates, revenue, launch_date) or explicitly noting it is a fragment requiring caller-supplied data, and add a brief validation/review checkpoint to the story-production workflow.

Dimension	Reasoning	Score
Conciseness	The ~450-line body extensively elaborates storytelling concepts Claude already knows (narrative arc, rule of three, do's/don'ts) and pads with large ASCII slide mockups, making it noticeably verbose with several unnecessary explanatory sections.	2 / 5
Actionability	Provides concrete filled-in story templates, a headline formula, and a real matplotlib annotation snippet, but the matplotlib code references undefined variables (dates, revenue, launch_date) and the bulk is example narrative rather than directly executable guidance.	3 / 5
Workflow Clarity	Lists clear sequences (6-step narrative arc, 7-slide template flow) but these are conceptual creative steps with no validation checkpoints or error-recovery feedback loops.	3 / 5
Progressive Disclosure	The single monolithic file is well-organized into clear sections, but substantial content (three full framework templates, visualization techniques, presentation templates) that could live in separate reference files is fully inlined, and no bundle references exist.	3 / 5
	Total	11 / 20 Passed

Description

83%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.

The description is strong: it clearly and explicitly states both what the skill does and when to use it, with concrete trigger scenarios and a named framework. Its main limitation is that the described actions stay somewhat high-level rather than enumerating multiple distinct concrete operations.

Dimension	Reasoning	Score
Specificity	Names the SCR narrative framework and a concrete action ('自动生成结合可视化与业务上下文的洞察报告'), which goes beyond a single generic action, though it does not enumerate multiple distinct concrete operations.	4 / 5
Completeness	Explicitly answers both 'what' (apply SCR framework, generate insight reports with visualization + business context) and 'when' (向高管汇报或制作投资者演示时，当面临数据枯燥难懂的痛点) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural scenario phrases users would say ('向高管汇报', '制作投资者演示', '数据枯燥难懂', '非技术受众'), with good coverage though missing some synonyms like 'deck' or 'dashboard'.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (executive/investor data storytelling via the SCR framework) that is mostly distinct, with only minor overlap risk against general data-analysis or reporting skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anbeime/skill
Path: skills/data-storytelling/data-storytelling/SKILL.md
Commit: d9e888d

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.