data-storytelling
Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.
76
47%
Does it follow best practices?
Impact
95%
1.06xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/business-analytics/skills/data-storytelling/SKILL.mdQuality
Discovery
67%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 has a solid structure with an explicit 'Use when' clause that clearly communicates both purpose and trigger conditions. However, the capability description leans toward abstract concepts ('compelling narratives', 'persuasive structure') rather than concrete actions, and the trigger terms could be broader to capture more natural user language. The skill could also be more distinctive to avoid overlap with general visualization or presentation skills.
Suggestions
Replace abstract phrases like 'compelling narratives' and 'persuasive structure' with concrete actions such as 'annotate charts with insights, write narrative summaries, structure data-driven slide decks'.
Expand trigger terms to include common user language like 'dashboard', 'charts', 'graphs', 'metrics', 'KPIs', 'data summary', or 'insights'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (data storytelling) and some actions ('visualization, context, and persuasive structure'), but these are somewhat abstract rather than concrete specific actions like 'create charts, write narrative summaries, build slide decks'. | 2 / 3 |
Completeness | Clearly answers both 'what' (transform data into compelling narratives using visualization, context, and persuasive structure) and 'when' (presenting analytics to stakeholders, creating data reports, building executive presentations) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'analytics', 'stakeholders', 'data reports', 'executive presentations', but misses common variations users might say such as 'dashboard', 'charts', 'graphs', 'insights', 'KPIs', 'metrics', or 'data summary'. | 2 / 3 |
Distinctiveness Conflict Risk | Could overlap with general data visualization skills, presentation creation skills, or report generation skills. The focus on 'narratives' and 'persuasive structure' provides some distinction, but 'data reports' and 'executive presentations' are broad enough to conflict with other skills. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive blog post or textbook chapter on data storytelling than a concise, actionable skill file for Claude. It contains substantial amounts of general communication advice (transition phrases, headline formulas, do's and don'ts) that Claude already knows, while lacking specific technical workflows, tool usage instructions, or validation steps. The content would benefit enormously from aggressive trimming and splitting into referenced sub-files.
Suggestions
Cut the content by 60-70%: remove transition phrases, headline formulas, do's/don'ts lists, and general storytelling concepts that Claude already knows. Focus on the unique structural templates and decision logic.
Split the three frameworks and presentation templates into separate referenced files (e.g., FRAMEWORKS.md, TEMPLATES.md) and keep SKILL.md as a concise overview with navigation links.
Add a concrete workflow with validation: e.g., 1) Identify audience and goal, 2) Select framework, 3) Draft narrative, 4) Verify all claims have supporting data, 5) Check that every slide/section has a 'so what', 6) Review for audience-appropriate language.
Make the matplotlib example more actionable by providing a complete, runnable script with sample data, or remove it in favor of guidance on when/how to generate visualizations programmatically.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Much of this is general storytelling advice, presentation templates, and writing tips that Claude already knows well (narrative arcs, transition phrases, headline formulas). The ASCII art templates and extensive frameworks add bulk without providing actionable technical guidance. | 1 / 3 |
Actionability | The matplotlib annotation example is concrete and executable, and the frameworks provide useful structural templates. However, most content is descriptive markdown templates and general advice rather than executable code or specific tool commands. The skill describes what good data stories look like rather than giving Claude precise instructions on how to produce them. | 2 / 3 |
Workflow Clarity | The frameworks provide a clear sequence (Hook → Context → Problem → Insight → Solution → Impact → CTA), and the progressive reveal technique shows step-by-step layering. However, there are no validation checkpoints, no feedback loops for iterating on the story, and no guidance on how to verify the narrative is effective before delivery. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no references to external files. All frameworks, templates, visualization techniques, and writing tips are inlined in a single massive document. Content like the three full framework examples, presentation templates, and writing techniques could easily be split into separate referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- wshobson/agents
- Commit
27a7ed9
- 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.