data-storyteller

Use when building data-heavy screens, analytics dashboards, metric visualizations, or inline charts for Copilot. Creates bar/line charts, renders data tables, aggregates KPI metrics, builds filterable dashboard layouts, and generates HTML previews for concept validation. Triggers: 'dashboard', 'métricas', 'gráfico', 'chart', 'visualización', 'analytics', 'KPI', 'reporte', 'muestra los datos', 'cómo van los números'.

Quality

83%

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

Quality

Content

71%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.

A well-sequenced, action-oriented skill body with explicit gating checkpoints and copy-paste-ready routing tables. Its main weakness is progressive disclosure: one referenced file is missing from the bundle and one real bundle file is never referenced, creating navigation gaps.

Suggestions

Fix the broken reference on line 132: 'references/data-viz-conventions.md' does not exist in ./references/ — either add the file or correct the path so Claude's Read does not fail.

Surface the orphaned 'references/metrics-map.md' from the body (e.g., link it in Phase D4 — Validate Metrics) so the bundle file is discoverable, or remove it.

Consolidate the repeated 'Copilot inline → direct HTML, not VIZ-SPEC' note (present in both Edge Cases and Integration Notes) into one location to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly lean and table-driven with no padding of concepts Claude already knows, but the role block is slightly padded and the 'Copilot inline → direct HTML, not VIZ-SPEC' note repeats across Edge Cases and Integration Notes. Anchor 4 ('efficient; minor instances that could be trimmed') fits; not 5 because of that redundancy.	4 / 5
Actionability	Provides concrete executable commands — 'docker exec -t visionarias_client_dev npm ls ... \| grep ...', 'open /tmp/viz-preview-{timestamp}.html', and copy-paste MCP/WebSearch queries like 'resolve-library-id "Meta Marketing API" → query-docs "{metric_name}"'. Anchor 4 fits; not 5 because chart generation itself stays abstract and the preview timestamp/docker env are placeholders.	4 / 5
Workflow Clarity	Multi-step phases (D1→D4 / P1→P4 → Spec) are clearly sequenced with explicit per-phase Gates ('Do NOT proceed without...', 'Must produce a one-liner', 'User confirms'). Anchor 4 ('clear sequence with most checkpoints present') fits; not 5 because explicit validate→fix→retry error-recovery loops are only lightly sketched (Knowledge Routing Step 3 is the main fallback).	4 / 5
Progressive Disclosure	Structure is one-level-deep and mostly well signaled, but the body references 'references/data-viz-conventions.md' (line 132) which does NOT exist in the bundle, and 'references/metrics-map.md' exists but is never referenced — a broken link plus an orphaned file. Anchor 3 ('references present but not clearly signaled; organization gaps') fits; not 4 because a dead reference exceeds 'minor organization gaps', not 2 because real structure is present.	3 / 5
	Total	15 / 20 Passed

Description

96%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.

A strong, well-structured description that clearly states capabilities and trigger phrases with bilingual synonyms. The only soft spot is minor overlap risk with adjacent screen-building skills, which keeps distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Creates bar/line charts, renders data tables, aggregates KPI metrics, builds filterable dashboard layouts, and generates HTML previews for concept validation' — giving comprehensive coverage with no gaps. Anchor 5 fits; 4 requires 'minor gaps' which are absent.	5 / 5
Completeness	Explicitly answers both 'what' (the action list) and 'when' ('Use when building data-heavy screens, analytics dashboards...') plus a concrete 'Triggers:' block, matching anchor 5. Not 4, since both halves are explicit and specific rather than weakly implied.	5 / 5
Trigger Term Quality	The explicit 'Triggers:' list covers natural synonyms in two languages — 'dashboard', 'métricas', 'gráfico', 'chart', 'visualización', 'analytics', 'KPI', 'reporte', 'muestra los datos', 'cómo van los números' — matching the comprehensive-synonyms anchor 5. No common natural variant is obviously missing for this domain.	5 / 5
Distinctiveness Conflict Risk	Has a clear data-visualization niche with distinct triggers (KPI, métricas, gráfico, chart), but terms like 'analytics dashboards' create minor overlap risk with closely related screen/frontend skills (the body itself notes complementary overlap with ux-disruptivo and frontend-expert). Anchor 4 ('mostly distinct; minor overlap risk') fits better than 5.	4 / 5
	Total	19 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: alpacapurpura/luana-method
Path: claude/skills/data-storyteller/SKILL.md
Commit: caa08df

Reviewed: ~21 hours 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.