CtrlK
BlogDocsLog inGet started
Tessl Logo

data-analysis

Use this skill when the user uploads Excel (.xlsx/.xls) or CSV files and wants to perform data analysis, generate statistics, create summaries, pivot tables, SQL queries, or any form of structured data exploration. Supports multi-sheet Excel workbooks, aggregation, filtering, joins, and exporting results to CSV/JSON/Markdown.

74

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable, well-structured skill body built around concrete executable commands and SQL examples with a clear inspect→query→summary workflow. It is efficient and well-sectioned, with only minor redundancy between the example walkthroughs and the earlier reference material.

Suggestions

Trim redundancy: the 'Complete Example' and 'Multi-file Example' restate parameter usage already shown in 'Step 3'/'Parameters' — consider condensing them to just the differing SQL and the end-to-end narrative.

Add a brief validation/feedback note for query failures (e.g., unknown sheet name, type-mismatch, empty result) so Claude can recover without re-reading the script.

Optionally move the 'Analysis Patterns' SQL catalog into a references/ file linked from the body to tighten the core SKILL.md and give the patterns room to grow.

DimensionReasoningScore

Conciseness

Mostly lean — built from executable commands and SQL examples with no over-explanation of concepts Claude already knows — but the 'Complete Example' and 'Multi-file Example' re-cover the parameter usage already documented, and 'Core Capabilities' partly echoes the description.

4 / 5

Actionability

Fully executable, copy-paste-ready commands with exact paths, a clear parameter table, and concrete SQL examples covering common cases (inspect, query, summary, export, joins, window functions).

5 / 5

Workflow Clarity

Clear Step 1→2→3 sequence with the inspect step serving as a natural schema-checkpoint before querying; the destructive/batch cap does not apply (read-only analysis), but there are no explicit error-recovery or result-verification feedback loops.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with the single bundle (scripts/analyze.py) referenced by path and explicitly flagged ('Do NOT read the Python file'); no nested references, though SQL pattern examples are kept inline rather than split into a separate reference file.

4 / 5

Total

17

/

20

Passed

Description

100%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, specific description that clearly states capabilities, includes natural trigger terms with file extensions, and explicitly covers both what the skill does and when to use it. It is distinct from neighboring skills and uses appropriate third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'perform data analysis, generate statistics, create summaries, pivot tables, SQL queries... aggregation, filtering, joins, and exporting results to CSV/JSON/Markdown' — with comprehensive coverage and third-person voice ('Supports').

5 / 5

Completeness

Explicitly answers both what ('analyzes user-uploaded Excel/CSV files... generate statistics, create summaries, pivot tables, SQL queries') and when ('Use this skill when the user uploads Excel... and wants to perform data analysis').

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms and file extensions: 'Excel (.xlsx/.xls) or CSV files', 'statistics', 'pivot tables', 'SQL queries', 'summaries'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (Excel/CSV structured-data analysis via SQL) with distinct file-type and task triggers, minimal overlap with other skills.

5 / 5

Total

20

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bytedance/deer-flow
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.