CtrlK
BlogDocsLog inGet started
Tessl Logo

hypothesis-generation

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

78

1.67x
Quality

67%

Does it follow best practices?

Impact

99%

1.67x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/hypothesis-generation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

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.

This is an excellent skill description that clearly articulates specific capabilities (hypothesis formulation, mechanism proposal, experiment design), provides explicit trigger conditions, and proactively disambiguates from related skills. The inclusion of cross-references to similar skills (scientific-brainstorming, hypogenic) is a strong differentiator that reduces conflict risk. Minor note: the phrase 'Use when you have' uses second person, but the rest of the description is appropriately structured.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'formulate testable hypotheses with predictions', 'propose mechanisms', and 'design experiments to test them'. These are clear, actionable capabilities.

3 / 3

Completeness

Clearly answers both 'what' (structured hypothesis formulation, propose mechanisms, design experiments) and 'when' (explicit 'Use when you have experimental observations or data and need to formulate testable hypotheses'). Also includes disambiguation guidance for related skills.

3 / 3

Trigger Term Quality

Includes strong natural keywords users would say: 'observations', 'data', 'testable hypotheses', 'predictions', 'mechanisms', 'design experiments', 'scientific method'. Also differentiates from related skills with terms like 'open-ended ideation' and 'automated LLM-driven hypothesis testing'.

3 / 3

Distinctiveness Conflict Risk

Explicitly distinguishes itself from two related skills ('scientific-brainstorming' for open-ended ideation and 'hypogenic' for automated LLM-driven hypothesis testing), creating a very clear niche for structured hypothesis formulation from observations.

3 / 3

Total

12

/

12

Passed

Implementation

35%

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

This skill is significantly over-verbose, spending most of its token budget explaining scientific method fundamentals Claude already knows and repeating LaTeX formatting advice multiple times. The workflow is logically structured but lacks validation checkpoints, and massive amounts of formatting detail are inlined that should be delegated to the referenced FORMATTING_GUIDE.md. The skill would benefit enormously from aggressive trimming to focus on what's truly novel: the specific template structure, the mandatory schematics requirement, and the reference file ecosystem.

Suggestions

Cut the content by 60-70%: remove explanations of basic scientific concepts (what testability means, what literature search is, what hypothesis generation involves) and trust Claude's existing knowledge. Focus only on project-specific conventions and templates.

Move all LaTeX formatting details (page overflow prevention, box usage, compilation) to the referenced FORMATTING_GUIDE.md and assets/ files, keeping only a 2-3 line summary with a pointer in the main skill.

Add explicit validation checkpoints between workflow steps, e.g., 'Before proceeding to Step 4, verify you have identified at least 3 distinct evidence themes from the literature' or 'Validate hypothesis quality against criteria before designing experiments.'

Include a concrete worked example showing a brief observation → hypothesis → prediction → experimental design cycle to make the workflow actionable rather than abstract.

DimensionReasoningScore

Conciseness

Extremely verbose at ~250+ lines. Extensively explains concepts Claude already knows (what hypothesis generation is, what testability means, what literature search is). The LaTeX formatting section alone is massively over-detailed with repeated instructions about page overflow prevention stated 3+ times. Much of this content explains basic scientific method concepts that Claude inherently understands.

1 / 3

Actionability

Provides some concrete guidance like the xelatex compilation commands and the generate_schematic.py script, but most content is procedural description rather than executable examples. The workflow steps are largely abstract instructions ('identify the core observation', 'search for recent reviews') rather than concrete, copy-paste-ready commands or code. References external files (templates, .sty files) which helps but the skill itself lacks concrete worked examples.

2 / 3

Workflow Clarity

The 8-step workflow is clearly sequenced and logically ordered, but lacks explicit validation checkpoints or feedback loops. There's no 'verify your hypotheses meet criteria X before proceeding' gate between steps. The LaTeX compilation section has a clear sequence, but the core scientific workflow has no error recovery or validation steps between stages.

2 / 3

Progressive Disclosure

References external files well (references/, assets/, related skills) with clear descriptions, which is good. However, the main SKILL.md is monolithic with enormous inline content that should be in separate files — particularly the extensive LaTeX formatting instructions and page overflow prevention guidelines, which could easily live in the referenced FORMATTING_GUIDE.md instead of being duplicated here.

2 / 3

Total

7

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

10

/

11

Passed

Repository
K-Dense-AI/claude-scientific-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.