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. Also owns explicit HypoGeniC-style or automated LLM-driven hypothesis generation/testing requests inside this single skill. For open-ended ideation use scientific-brainstorming.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A well-sequenced, actionable skill body with strong concrete LaTeX guidance and a real reference bundle. Its main weakness is verbosity: the page-overflow guidance is repeated several times and substantial formatting detail that should live in FORMATTING_GUIDE.md is inlined in SKILL.md.

Suggestions

Collapse the repeated \newpage / overflow-prevention guidance (Page Break Strategy, Critical Overflow Prevention, Page Overflow Prevention) into a single concise block; move the detailed worked examples into assets/FORMATTING_GUIDE.md.

Trim the inline LaTeX formatting detail (box color schemes, per-box content limits, page-boundary heuristics) to a brief pointer to assets/FORMATTING_GUIDE.md so SKILL.md reads as an overview.

Remove the restated '4-page main text limit' reminders that recur across the Document Structure, Citation Requirements, and Overflow sections.

DimensionReasoningScore

Conciseness

Mostly efficient but padded: the \newpage / page-overflow rule is restated across 'Page Break Strategy', 'Critical Overflow Prevention', and 'Page Overflow Prevention' (5+ times) and could be collapsed into one block.

2 / 3

Actionability

Provides an executable LaTeX compile block, named box environments (hypothesisbox1–5, predictionbox, comparisonbox), concrete citation/page targets, and specific reference files to consult — copy-paste ready for the deliverable.

3 / 3

Workflow Clarity

A clearly numbered 8-step workflow with sub-bullets, a closing 'Quality Standards' checklist, and a build feedback loop (xelatex → bibtex → xelatex → xelatex) for validating output.

3 / 3

Progressive Disclosure

References are real, one level deep, and listed in a '## Resources' section, but ~60 lines of detailed LaTeX formatting/overflow guidance are kept inline when they belong in the existing assets/FORMATTING_GUIDE.md.

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.

An excellent description: concrete actions, natural trigger terms, an explicit Use-when clause, and explicit conflict disambiguation against a sibling skill. Third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them' — plus 'HypoGeniC-style or automated LLM-driven hypothesis generation/testing'.

3 / 3

Completeness

Explicitly states what it does and provides an explicit 'Use when you have experimental observations or data and need to formulate testable hypotheses...' trigger clause covering both what and when.

3 / 3

Trigger Term Quality

Covers natural trigger terms users would say ('experimental observations or data', 'testable hypotheses', 'mechanisms', 'design experiments') and a named workflow trigger ('HypoGeniC-style').

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche and actively resolves overlap by routing elsewhere — 'For open-ended ideation use scientific-brainstorming' — making misfires unlikely.

3 / 3

Total

12

/

12

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

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-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.