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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and clearly sequenced for a read-only SQL analysis tool, but the body is longer than necessary: it teaches generic SQL Claude already knows and keeps all detail inline in one file rather than splitting reference material out. Trimming the SQL tutorial and externalizing examples would improve token efficiency and structure.

Suggestions

Cut or heavily trim the 'Analysis Patterns' section — Claude already knows GROUP BY, window functions, CTEs, and CASE-based pivots; keep only patterns specific to this skill's table-naming rules or DuckDB quirks.

Consolidate the repeated script-invocation examples: the Complete Example and Multi-file Example restate the same parameter pattern, so one worked example plus the parameters table suffices.

Move the detailed SQL pattern library and full worked examples into a separate reference file (e.g. references/examples.md) linked from SKILL.md, keeping the main file a lean overview plus parameter reference.

Dimension	Reasoning	Score
Conciseness	Script-usage guidance is lean, but the 'Analysis Patterns' section (~60 lines) teaches SQL Claude already knows (GROUP BY, window functions, CTEs, CASE pivots) and the Complete/Multi-file examples restate the same invocation pattern — matching the score-2 anchor for mostly efficient but padded.	2 / 3
Actionability	Provides fully executable bash commands with exact flags, a precise parameters table, copy-paste SQL, and output paths, matching the score-3 anchor for copy-paste-ready executable guidance.	3 / 3
Workflow Clarity	Clearly numbered steps (understand -> inspect -> analyze) plus a full Steps 1-4 worked example, with inspect-before-query acting as the schema-discovery checkpoint; operations are read-only so the destructive/batch validation cap does not apply.	3 / 3
Progressive Disclosure	A single ~240-line monolithic file holds everything inline (overview, SQL pattern library, full worked examples); the only bundle file (analyze.py) is an opaque executable ('Do NOT read the Python file') rather than a navigable reference, matching the score-2 anchor where split-able content stays inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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: it states a concrete, broad capability set, uses natural trigger terms with file extensions, and gives an explicit 'Use this skill when...' clause covering both what and when. Voice is third person and free of over-claims.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('generate statistics, create summaries, pivot tables, SQL queries... aggregation, filtering, joins, and exporting results'), matching the score-3 anchor for multiple specific actions rather than just naming a domain.	3 / 3
Completeness	Explicitly answers both when ('Use this skill when the user uploads Excel... or CSV files and wants to perform data analysis') and what (the capability list), matching the score-3 anchor with an explicit 'Use when...' trigger.	3 / 3
Trigger Term Quality	Covers natural terms users actually say — 'Excel (.xlsx/.xls)', 'CSV files', 'data analysis', 'statistics', 'pivot tables' — including file extensions, matching the score-3 anchor for good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	A clear niche (tabular-file analysis via SQL/DuckDB) gated on an explicit file-type trigger (Excel/CSV uploads) makes it unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	12 / 12 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: bytedance/deer-flow
Path: skills/public/data-analysis/SKILL.md
Commit: cd9432b

Reviewed: about 13 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.