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.
60
41%
Does it follow best practices?
Impact
94%
1.06xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/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 good structural completeness with a clear 'what' and 'when' clause, which is its strongest aspect. However, it leans toward abstract language ('compelling narratives', 'persuasive structure') rather than listing concrete, specific actions. The trigger terms cover some key scenarios but miss common user vocabulary variations.
Suggestions
Replace abstract phrases like 'compelling narratives' and 'persuasive structure' with concrete actions such as 'generate charts, write narrative summaries, highlight key metrics, structure findings for decision-makers'.
Expand trigger terms to include common user vocabulary like 'dashboard', 'charts', 'graphs', 'KPIs', 'metrics', 'insights', 'data summary', or 'quarterly review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (data storytelling) and some actions ('visualization, context, and persuasive structure'), but these are somewhat abstract rather than concrete specific actions. It doesn't list specific capabilities like 'create charts', 'write narrative summaries', or '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 useful trigger terms like 'analytics', 'stakeholders', 'data reports', 'executive presentations', but misses common variations users might say such as 'dashboard', 'charts', 'graphs', 'KPIs', 'metrics', 'insights', or 'data summary'. | 2 / 3 |
Distinctiveness Conflict Risk | The skill occupies a recognizable niche (data storytelling/narrative), but could overlap with general data visualization skills, report generation skills, or presentation creation skills. The combination of 'narrative' + 'data' helps somewhat, but the boundaries aren't sharply defined. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
14%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 an actionable skill for Claude. It is extremely verbose, filled with general communication advice Claude already knows (headline formulas, transition phrases, do's/don'ts), and lacks a clear operational workflow for transforming data into narratives. The example frameworks are illustrative but the skill would benefit enormously from being condensed to core decision logic and split across referenced files.
Suggestions
Reduce content by 60-70%: Remove writing tips, transition phrases, do's/don'ts, and book recommendations that Claude already knows. Focus on the decision framework for choosing a story structure based on data type.
Add a clear operational workflow: e.g., '1. Identify the key insight from the data, 2. Select framework (Problem-Solution for gaps, Trend for time-series, Comparison for decisions), 3. Draft the narrative arc, 4. Validate: does every data point support the insight? Remove those that don't.'
Split content into referenced files: Keep SKILL.md as a concise overview with framework selection guidance, then reference separate files like FRAMEWORKS.md, VISUALIZATION.md, and TEMPLATES.md for detailed examples.
Add validation checkpoints: Include steps to verify data accuracy, check that insights are statistically supported, and confirm the narrative matches the audience's decision-making needs.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Much of this is general communication advice (headline formulas, transition phrases, do's/don'ts) that Claude already knows. The frameworks are essentially example business documents rather than actionable instructions. The content could be reduced by 70%+ without losing value. | 1 / 3 |
Actionability | The frameworks provide concrete examples of data story structures, and there's one executable matplotlib code snippet. However, most content is template markdown rather than executable guidance—it shows what a finished product looks like but doesn't give Claude specific steps for transforming arbitrary data into these formats. The templates are illustrative but not directly actionable for novel data. | 2 / 3 |
Workflow Clarity | There is no clear workflow for how to actually perform data storytelling step-by-step. The 'narrative arc' and 'story structure' sections list conceptual stages but lack operational steps like 'first analyze the data for outliers, then identify the top 3 insights, then select a framework.' No validation checkpoints exist for verifying story quality or data accuracy. | 1 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no references to supporting files. The content includes extensive templates, writing techniques, visualization code, and presentation layouts all inline. The frameworks, visualization techniques, and writing tips could each be separate referenced files, dramatically improving organization. | 1 / 3 |
Total | 5 / 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
- Dicklesworthstone/pi_agent_rust
- Commit
895269a
- 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.