data-analytics

Use this skill for quantitative product or business analysis: data quality checks, metric diagnostics, KPI design and reporting, dashboards, analytical reports, charts, notebooks, market sizing, semantic layers, and evidence-backed recommendations. Also use it whenever Data Analytics is explicitly invoked.

Quality

63%

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 ./packages/opencode/src/skill/builtin/.bundle/data-analytics/SKILL.md

Quality

Content

46%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 well-organized, concise policy writing, but it functions as a routing stub for a `workflows/` tree that is not present in this bundle, leaving its primary action unexecutable and its references dangling. The one bundled asset (sample CSV) is never referenced by name.

Suggestions

Bundle the referenced `workflows/index/SKILL.md` and focused workflow files, or rewrite the body to be self-contained so the routing step does not depend on files missing from the bundle.

Name the bundled sample data explicitly (e.g., `assets/demo-product-growth.csv`) so the instruction to "prefer bundled scripts and sample data" points to a real file.

Add a concrete example of the default deliverable (e.g., a minimal matplotlib snippet or a report skeleton) so the delivery-override rules are executable rather than purely conditional.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and rule-dense with no explanation of concepts Claude already knows; minor tightening is possible in the "Safety and fidelity" section and the somewhat repetitive delivery-override caveats.	4 / 5
Actionability	The core instruction — "Read `workflows/index/SKILL.md` completely. Treat it as the authoritative plugin-level eligibility and analytical routing policy" — points to files absent from the bundle (no `workflows/` directory exists), and no commands or code appear anywhere, so execution is delegated to missing files and only high-level conditional rules remain.	2 / 5
Workflow Clarity	Routing steps 1–5 are clearly sequenced and one completion checkpoint exists ("A requested report remains incomplete until its chosen portable file exists or a concrete blocker is reported"), but the sequence's second step depends on a nonexistent file and there are no validation feedback loops.	3 / 5
Progressive Disclosure	Scored against the actual bundle: the only bundled file is `assets/demo-product-growth.csv`, which the body never names, while all references (`workflows/index/SKILL.md`, focused workflows, bundled scripts/sample data) point to nonexistent paths — the disclosure structure is broken despite the body's own clean section organization.	2 / 5
	Total	11 / 20 Passed

Description

80%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 description: comprehensive and specific about capabilities, in third person, with an explicit invocation trigger. Its main weaknesses are a narrow 'when' clause limited to explicit invocation and missing natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete capabilities — "data quality checks, metric diagnostics, KPI design and reporting, dashboards, analytical reports, charts, notebooks, market sizing, semantic layers, and evidence-backed recommendations" — giving comprehensive, specific coverage of the domain with no gaps.	5 / 5
Completeness	The 'what' is explicit and concrete, and an explicit 'when' clause exists ("Also use it whenever Data Analytics is explicitly invoked"), but the when-clause only covers explicit invocation and omits concrete natural trigger phrases like 'use when the user asks to analyze data or build a dashboard', so it falls short of the 5 anchor.	4 / 5
Trigger Term Quality	Good natural keyword coverage ("data quality checks", "KPI", "dashboards", "charts", "market sizing", "notebooks"), but common phrasings users would naturally say — "analyze data", "data analysis", "metrics", file-type triggers — are absent; keywords are implicit in the capability list rather than stated as trigger variations.	4 / 5
Distinctiveness Conflict Risk	A clear niche (quantitative product/business analysis) with distinctive terms like "metric diagnostics", "semantic layers", and "market sizing"; minor overlap risk remains with general visualization/charting skills via "dashboards" and "charts", keeping it below the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: XiaomiMiMo/MiMo-Code
Path: packages/opencode/src/skill/builtin/.bundle/data-analytics/SKILL.md
Commit: f0293bf

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.