hypothesis-generation

Formulate evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%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.

A well-structured, domain-rich skill body with clear sequencing, validation gates, and clean progressive disclosure into verified bundle files. The main lever for improvement is relocating time-sensitive version/date markers into a dedicated section.

Suggestions

Move time-sensitive markers (SPIRIT 2025, CONSORT 2025, the 'verified through 2026-07-23' source-ledger date) into a clearly labeled 'Currency / time-sensitive' or 'Deprecated' subsection so the main workflow stays evergreen.

Add a brief 'If validation reports errors: fix the declaration and re-run' loop note next to the CLI exit-code table to make the existing feedback loop explicit per command.

Consider trimming or tabulating the object-distinctions table and the rival-generation list into a reference file to further slim the core SKILL.md body.

Dimension	Reasoning	Score
Conciseness	Dense, information-rich prose that assumes Claude's competence and avoids explaining basics, but time-sensitive items ('SPIRIT 2025', 'CONSORT 2025', source ledger 'verified through 2026-07-23') are inline rather than in a deprecated/old-patterns section, incurring a minor penalty.	4 / 5
Actionability	Provides concrete executable commands in the tool index (e.g. 'python3 scripts/check_operationalization.py local-operationalization.json') and specific asset paths, though much of the workflow guidance is checklist-style rather than copy-paste code, which fits an instruction-heavy skill but leaves minor gaps.	4 / 5
Workflow Clarity	A 12-step workflow with explicit validation checkpoints (safety gate, dated evidence boundary, pre-outcome timestamping, human accountability verification), checklists throughout, and CLI exit-code feedback (0/1/2) that supports error recovery.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with a well-signaled one-level-deep References section listing each bundled file with a description; referenced assets/scripts/references all exist as real files, and content is appropriately split.	5 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong, specific description that clearly states capabilities and an explicit 'Use when' trigger with a useful boundary clause. Trigger-term naturalness is the only minor weakness, leaning slightly technical.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across the domain ('scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans'), giving comprehensive coverage rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Formulate ... analysis plans') and when ('Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural terms a researcher would say appear ('observations', 'preliminary findings', 'hypotheses', 'research plans'), but coverage leans technical and omits some common synonyms or looser phrasings users might actually say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (scientific hypothesis generation) with distinct triggers and a scoping clause ('without treating hypotheses as facts'), making overlap with unrelated skills unlikely.	5 / 5
	Total	19 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/hypothesis-generation/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.