CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-scientific-skills

Scientific research and analysis skills

31

Quality

25%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/claude-scientific-skills/SKILL.md

The canonical home for this skill is claude-scientific-skills in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

26%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 lean and sectioned but almost entirely vacuous — it offers no executable guidance, no workflow steps, and deflects substantive content to an external repo. Adding concrete, actionable instructions is the primary gap.

Suggestions

Add concrete, executable guidance — specific commands, code snippets, or named tools/methods — instead of the abstract 'provides guidance and patterns' phrasing.

Provide a clear step sequence for the skill's workflow (with validation checkpoints for any batch or data-mutating operations) rather than leaving the Instructions section empty of steps.

Replace the tautological 'when to use' sentence and the triple repetition of the skill name with substantive, tightened content that earns its tokens.

DimensionReasoningScore

Conciseness

The body is short and free of concept over-explanation, but it repeats 'scientific research and analysis skills' three times and uses a tautological when-to-use sentence that could be tightened.

3 / 5

Actionability

The Instructions section is entirely abstract ('provides guidance and patterns for...') with no code, commands, or specific steps — it describes rather than instructs.

1 / 5

Workflow Clarity

No multi-step process is given and the single intended action is vague and not unambiguous, so the workflow is effectively absent.

1 / 5

Progressive Disclosure

The body is brief and organized into clear sections (Overview, When to Use, Instructions) with no nested references, though it deflects detail to an external repo link rather than bundle files.

4 / 5

Total

9

/

20

Passed

Description

25%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 is a generic domain label that names no concrete actions, lacks a 'Use when' trigger, and overlaps broadly with many analysis/research skills. It needs specific capabilities and explicit trigger guidance to become distinguishable and actionable.

Suggestions

Replace the generic label with concrete capabilities (e.g., 'run statistical analyses, fit regression models, summarize experimental data') so users know what the skill actually does.

Add an explicit 'Use when...' trigger clause naming natural phrases users say (e.g., 'Use when the user asks to analyze experimental data, run statistical tests, or summarize research results').

Narrow the domain and add distinctive terms (specific tools, file types, or methods) to reduce overlap with general data-analysis and research skills.

DimensionReasoningScore

Specificity

The description only names the domain ('Scientific research and analysis skills') and lists no concrete actions, matching the anchor that names a domain with minimal/generic actions.

2 / 5

Completeness

It gives only a vague 'what' and entirely omits a 'when / Use when' clause, matching the anchor for a vague what with no when (and below the missing-trigger cap of 3).

2 / 5

Trigger Term Quality

It offers generic activity keywords ('research', 'analysis') but none of the specific natural phrases a user would say (e.g., 'analyze data', 'run tests', 'literature review'), fitting the generic-keywords anchor.

2 / 5

Distinctiveness Conflict Risk

'Scientific research and analysis' is very broad and would overlap heavily with general data-analysis, statistics, and research skills, matching the high-overlap-risk anchor.

2 / 5

Total

8

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.