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.
Overall
score
72%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 94%
↑ 1.01xAgent success when using this skill
Validation for skill structure
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with good completeness and trigger term coverage. The explicit 'Use when...' clause with specific scenarios is a strength. The main weakness is that the capabilities described are somewhat abstract ('compelling narratives', 'persuasive structure') rather than concrete actions, and there's moderate overlap risk with related visualization or presentation skills.
Suggestions
Add more concrete actions to improve specificity, e.g., 'create annotated charts, write insight summaries, structure findings hierarchically'
Include distinguishing terms to reduce conflict risk, such as specific output formats or unique methodologies that differentiate this from general visualization or presentation skills
| 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' or 'generate summary statistics'. | 2 / 3 |
Completeness | Clearly answers both what ('Transform data into compelling narratives using visualization, context, and persuasive structure') and when ('Use when presenting analytics to stakeholders, creating data reports, or building executive presentations') with explicit triggers. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'analytics', 'stakeholders', 'data reports', 'executive presentations'. These are terms users naturally use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Could overlap with general data visualization skills or presentation creation skills. The focus on 'narratives' and 'stakeholders' provides some distinction, but 'data reports' and 'presentations' are broad enough to potentially conflict with other skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability with rich, concrete templates and examples that Claude can directly apply to data storytelling tasks. However, it suffers from verbosity (explaining basic narrative concepts) and poor progressive disclosure (everything inline in one massive file). The workflow guidance shows story structure but lacks validation/iteration checkpoints for ensuring the story lands with its audience.
Suggestions
Split the three detailed frameworks (Problem-Solution, Trend, Comparison) into a separate FRAMEWORKS.md file, keeping only brief summaries in the main skill
Remove or drastically condense the 'Core Concepts' section - Claude understands narrative arcs and story structure without detailed explanation
Add a validation workflow: 'Before presenting: 1. Test key insight with one stakeholder, 2. Verify data accuracy, 3. Check that call-to-action is achievable'
Move visualization templates and presentation templates to separate reference files (VISUALIZATIONS.md, TEMPLATES.md) with clear navigation links
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful frameworks and examples but is verbose at ~400 lines. Many sections explain concepts Claude already knows (narrative arcs, story structure basics) and could be condensed significantly while preserving actionable value. | 2 / 3 |
Actionability | Provides highly concrete, copy-paste ready templates with specific examples (churn analysis, Q4 performance, market comparison). Includes executable Python code for visualization and detailed markdown templates that can be directly adapted. | 3 / 3 |
Workflow Clarity | The frameworks show clear story structures (Setup→Conflict→Resolution, slide sequences), but lacks explicit validation checkpoints. No guidance on how to verify the story resonates, test with stakeholders, or iterate based on feedback before final presentation. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files. All frameworks, templates, and techniques are inline. The Resources section links to external books but the skill itself would benefit from splitting templates into separate reference files. | 1 / 3 |
Total | 8 / 12 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
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 13 / 16 Passed | |
- 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.