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.

69

Quality

86%

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

72%

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

The skill body is highly actionable with concrete commands, LaTeX environments, and well-organized one-level-deep references. Its main weaknesses are redundant page-overflow guidance and missing validation/feedback loops in the fragile LaTeX-compilation workflow.

Suggestions

Collapse the three repeated page-overflow / \newpage sections ('Page Break Strategy', 'Critical Overflow Prevention', 'Page Overflow Prevention') into a single concise block to remove ~30 lines of repetition.

Add an explicit validation/feedback loop to the LaTeX compilation step (e.g., 'if xelatex errors on overflow, move content to Appendix A and recompile') to satisfy the feedback-loops requirement for document-generation workflows.

Trim the repeated 4-page-limit / box-size reminders (lines 201-206, 252-255) to a single statement since the same constraints are stated multiple times.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept filler, but the page-overflow / \newpage guidance is repeated verbatim across 'Page Break Strategy', 'Critical Overflow Prevention', and 'Page Overflow Prevention' (e.g., lines 173-183, 208-212, 236-265), which is unnecessary tightening.

2 / 3

Actionability

Provides executable commands (generate_schematic.py, the xelatex/bibtex/xelatex/xelatex sequence), concrete LaTeX environments (hypothesisbox1-5, predictionbox), and specific budgets (≤0.6 pages, 6-10 sentences, 10-15 citations) — copy-paste ready.

3 / 3

Workflow Clarity

The 8-step workflow is clearly sequenced, but validation/feedback checkpoints are absent: the fragile LaTeX compilation step lists commands without an 'if the PDF fails, fix and recompile' recovery loop, which caps workflow clarity at 2 per the feedback-loops scoring note.

2 / 3

Progressive Disclosure

The body is a concise overview pointing one level deep to real, verified bundle files (references/*.md, assets/*.{sty,tex,md}, scripts/generate_schematic.py), each clearly signaled inline and listed in a Resources section with descriptions.

3 / 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.

The description is specific, complete, and well-triggered, clearly stating both capabilities and the conditions under which to invoke the skill. It occupies a distinct scientific-inquiry niche with natural trigger terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Structured hypothesis formulation from observations', 'formulate testable hypotheses with predictions', 'propose mechanisms', 'design experiments to test them' — matching the score-3 anchor for listing several specific actions.

3 / 3

Completeness

Explicitly answers both 'what' (formulate hypotheses, propose mechanisms, design experiments, predictions) and 'when' via a clear 'Use when you have experimental observations or data' trigger clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Includes natural terms a researcher would actually say — 'experimental observations or data', 'testable hypotheses', 'propose mechanisms', 'design experiments' — giving good coverage rather than only jargon.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear scientific-method niche with distinctive triggers ('testable hypotheses with predictions', 'scientific method framework') unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

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