data-analysis

Statistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets.

Quality

73%

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 ./agentscope-examples/documentation/src/main/resources/skills/data-analysis/SKILL.md

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 lean, well-scoped body for a simple skill: two clear steps naming specific tools with their outputs, and no padding beyond two short filler lines. The main gap is actionability — no example invocations, parameters, or output format for the two named tools.

Suggestions

Add a minimal example call for 'analyze_data' and 'write_summary' (parameters or expected output shape) to lift actionability from 3 toward 4-5.

Remove or make concrete the two filler lines — 'You are a data analysis assistant' and 'Always present results in a clear, structured format' — or replace the latter with an actual output template.

Clarify the conditional in step 2: specify where 'write_summary' writes and what the file should contain.

Dimension	Reasoning	Score
Conciseness	The body is very lean with no concept explanations — 13 lines total. Two minor instances of trimmable filler remain: 'You are a data analysis assistant' (role-play line Claude does not need) and 'Always present results in a clear, structured format' (vague directive with no actionable content). Fits anchor 4 (efficient, minor over-explanation) rather than 5 where every token earns its place.	4 / 5
Actionability	It names concrete tools ('analyze_data' with its outputs 'count, sum, min, max, average'; 'write_summary' to save results) but provides no invocation syntax, parameters, or example calls — it is instruction-shaped rather than executable guidance. Fits anchor 3 (some concrete guidance but incomplete, missing key details); not 4 because there is no example of how to actually call either tool.	3 / 5
Workflow Clarity	As a simple two-step skill the sequence is clear and unambiguous: compute statistics first, then conditionally save results. Minor ambiguity remains in the conditional 'if the user asks' and the vague 'clear, structured format' directive, which keep it below the unambiguous-single-action bar of 5; no validation is needed since neither step is destructive or batch-oriented.	4 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained, and needs no external references — no references/, scripts/, or assets/ directories exist and the body references no other files. Per the simple-skill exception, well-organized short content with no reference indirection scores 5.	5 / 5
	Total	16 / 20 Passed

Description

62%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 well-formed description with an explicit 'use when' trigger clause and natural trigger phrases, but it stays at the level of generic verbs. Naming concrete capabilities (e.g., specific statistics computed, supported formats) and broader trigger synonyms would strengthen it.

Suggestions

Replace generic verbs with concrete capabilities, e.g., 'Computes descriptive statistics (mean, median, min, max, standard deviation) and summarizes datasets' — this would raise specificity from 3 toward 4-5.

Broaden trigger coverage with common synonyms and formats users actually say: 'data analysis', 'stats', 'crunch the numbers', '.csv', 'summary statistics'.

Differentiate the 'what' from the 'when': the same three phrases serve both roles; state the capability list separately from the trigger conditions.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Statistical data analysis skill') and lists actions ('analyze numbers, compute statistics, or summarize datasets'), but these are generic verbs rather than concrete capabilities like naming the actual statistical operations or tools. It matches anchor 3 (domain and 1-2 concrete actions, not comprehensive) — not 4 because the actions lack the specificity of examples like 'extracts text and tables from PDF files'.	3 / 5
Completeness	Both parts are present: a 'what' ('Statistical data analysis skill' with its action list) and an explicit 'when' ('use when the user asks to analyze numbers, compute statistics, or summarize datasets'). Not 5 because the 'what' is a label that repeats the trigger phrases rather than a concrete capability list distinct from the triggers; not 3 because the 'when' clause is explicit, not merely implied.	4 / 5
Trigger Term Quality	Triggers 'analyze numbers, compute statistics, or summarize datasets' are natural phrases a user might say, but coverage is minimal — missing common variations and synonyms such as 'data', 'stats', 'trends', or file formats like '.csv'. Fits anchor 3 (some relevant keywords, missing common variations); not 4 because the keyword set is only three near-synonymous phrases.	3 / 5
Distinctiveness Conflict Risk	'Statistical data analysis' is a recognizable niche with distinct triggers around computing statistics, giving it mostly-distinct positioning with only minor overlap risk against closely related skills (e.g., data visualization or spreadsheet skills). Not 5 because 'analyze numbers' and 'summarize datasets' are broad enough that a user wanting charting or data cleaning could match this skill.	4 / 5
	Total	14 / 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: agentscope-ai/agentscope-java
Path: agentscope-examples/documentation/src/main/resources/skills/data-analysis/SKILL.md
Commit: 9e43ed8

Reviewed: 2 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.