data-report

Turns CSV, Excel, or JSON data into a polished visual report page.

Quality

68%

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-report/SKILL.md

Quality

Content

86%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 body is a lean, high-signal template spec with an unusually valuable concrete failure-mode warning about Chart.js container heights. Its only gaps are the absence of an inline code example for the container pattern and a validation checkpoint on the parsed data before rendering.

Suggestions

Include a 3-4 line inline HTML snippet showing the required wrapper pattern (<div style="position:relative;height:280px"><canvas>...</canvas></div>) so the critical rule is copy-paste ready.

Add a short validation step for the data pipeline, e.g., after parsing, confirm the row/column counts and date range match the user's input before rendering charts.

Replace the abstract color directive with a concrete palette recipe (e.g., specific hex primary + named neutral ramp) or a pointer to the chart palette to use.

Dimension	Reasoning	Score
Conciseness	Every bullet earns its place: the section spec is terse, and the chart-container warning carries genuinely non-obvious, high-value detail ("ResizeObserver 死循环", "KPI 迷你图 ~40px, 主图表 ~240–280px") with no padding or explanation of concepts Claude already knows — matching the lean anchor 5.	5 / 5
Actionability	Mostly executable: concrete px heights, library choices ("Chart.js 或 ECharts (jsdelivr CDN 引入)"), section counts, and styling specifics ("zebra stripe, hover, sticky header"). It falls short of anchor 5 only because there is no copy-paste code snippet for the container pattern and a few directives stay abstract ("配色克制专业: 主色 1 + 中性色阶").	4 / 5
Workflow Clarity	The page structure is presented as an unambiguous ordered sequence (header → KPI grid → charts → table → insights → footer) for a single-task skill, matching anchor 4. It misses anchor 5 because there is no validation checkpoint for the data-parsing step — e.g., confirming parsed row/column counts before rendering — though the task is not destructive/batch so the cap of 3 does not apply.	4 / 5
Progressive Disclosure	The body is under 50 lines, requires no external references (none exist in the bundle), and is organized into clearly labeled sections per area ("头部", "KPI 卡片网格", "主图表区", "数据表格", "洞察块", "方法论"), which per the scoring guidance merits a 5 for a short, self-contained skill.	5 / 5
	Total	18 / 20 Passed

Description

50%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 states a clear single capability with concrete input formats, but it omits any 'when to use' trigger guidance and lacks natural keyword variations (chart, dashboard, .csv, .xlsx), leaving it in the middling range on every dimension. It is serviceable but would benefit from an explicit use-when clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user provides CSV/Excel/JSON data and wants a report, dashboard, or visual summary page."

Include natural trigger terms and file extensions users would actually say: charts, dashboard, weekly report, data visualization, .csv, .xlsx.

Enumerate 2-3 concrete actions the report includes (KPI cards, charts, data table, insights) to raise specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	"Turns CSV, Excel, or JSON data into a polished visual report page" names the domain and one concrete action (convert data into a visual report page), but does not enumerate several specific actions — it matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than the level-4 anchor listing several actions.	3 / 5
Completeness	The 'what' is clear (turn data into a polished visual report page), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	It includes the format keywords "CSV, Excel, or JSON" but misses common natural variations users would say — "chart", "dashboard", "data visualization", "report", and file extensions like .csv or .xlsx — matching the anchor 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	"visual report page" with generic data inputs is somewhat specific, but it overlaps with chart, dashboard, and general dataviz skills and lacks any trigger phrase to disambiguate — fitting the anchor 'Somewhat specific but could still overlap with similar skills' better than the mostly-distinct anchor 4.	3 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: skills/data-report/SKILL.md
Commit: 1b47e60

Reviewed: 3 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.