calculation-skill

A skill for mathematical calculations

Quality

50%

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-core/src/test/resources/test-skills/calculation-skill/SKILL.md

Quality

Content

41%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 commendably lean but provides no executable guidance, concrete examples, or workflow — it is a capability list rather than a usable skill. A simple skill can score well on workflow clarity only when its single action is unambiguous, which this is not.

Suggestions

Add a concrete, executable example for each capability (e.g. a Python snippet or a formula-evaluation pattern) so Claude knows exactly what to do.

Turn the bullet list into a short "When to use / How to use" structure so the intended action and any inputs/outputs are unambiguous.

If real operations exist, specify them concretely (e.g. supported functions, statistics available) rather than the generic category names.

Dimension	Reasoning	Score
Conciseness	The body is only ~8 lines with no padding or over-explanation of concepts Claude already knows; every token is lean and assumes competence, matching score 5's "lean and efficient; every token earns its place".	5 / 5
Actionability	The body only describes capability categories ("Basic arithmetic operations", "Advanced mathematical functions", "Statistical analysis") with no code, commands, or concrete steps — it describes rather than instructs, matching score 1's "entirely vague or abstract; only describes rather than instructs".	1 / 5
Workflow Clarity	There is no sequence or steps at all, only a flat capability list; the simple-skill exception (score 5 when the single action is unambiguous) does not apply because "computational tasks" is ambiguous, so it falls to score 1's "steps missing or incoherent; no sequence".	1 / 5
Progressive Disclosure	For an under-50-line skill with no need for external references, the heading-plus-bullets layout is reasonably well organized with no nested or buried references, fitting score 4's "good structure; most content appropriately placed; minor organization gaps"; it stops short of 5 only because the flat list lacks clear sectioning.	4 / 5
	Total	11 / 20 Passed

Description

33%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.

The description correctly names its domain in third person but is generic and lacks concrete actions, natural trigger terms, and any "Use when..." guidance. It reads as a placeholder rather than a discoverable, well-scoped skill description.

Suggestions

Replace the generic phrasing with concrete actions, e.g. "Evaluates arithmetic expressions, computes statistics, and solves equations."

Add an explicit trigger clause: "Use when the user asks to calculate, compute, sum, average, or perform mathematical/statistical operations."

Narrow the niche to reduce conflict risk by specifying the supported operation types or input formats (e.g. expressions, datasets, formulas).

Dimension	Reasoning	Score
Specificity	The phrase "A skill for mathematical calculations" names the domain (mathematical calculations) but states no concrete actions at all — it does not rise to the multi-action coverage of score 3, yet it is not entirely vague like score 1's "Helps with documents" since the domain itself is concrete.	2 / 5
Completeness	It offers a clear domain-level 'what' (mathematical calculations) but contains no 'when' / "Use when..." clause, so per the missing-trigger-guidance cap it cannot exceed 3; it is not score 2 because the 'what' is not vague, and not score 4 because no trigger guidance is present.	3 / 5
Trigger Term Quality	"mathematical calculations" is one or two generic keywords; it omits the natural phrases users actually say (e.g. "do math", "calculate", "compute a sum", "average"), matching score 2's "one or two generic keywords; missing the natural phrases".	2 / 5
Distinctiveness Conflict Risk	"mathematical calculations" is very broad and would overlap with virtually any skill that performs computation, fitting score 2's "very broad; high overlap risk"; it is somewhat more bounded than the entirely-generic score 1 but less niche than score 3.	2 / 5
	Total	9 / 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-core/src/test/resources/test-skills/calculation-skill/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.