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

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 dense, well-structured procedural skill that splits detail appropriately into one-level-deep reference and asset files, all of which are present and clearly signaled. It is actionable and well-sequenced with validation tooling, with minor room to tighten prose and make validation feedback loops explicit.

Suggestions

Make the validate-fix-retry loop explicit in workflow steps that invoke a script (e.g. 'If exit code is 1, review the report, fix the record, and re-run until exit code 0').

Trim definitional asides Claude already knows (e.g. the full FINER mnemonic expansion, 'PICO is not a universal template') to tighten conciseness.

Consider a brief inline example of a filled prediction/rival matrix or evidence-ledger row to lift actionability from concrete-command to copy-paste-ready for the core scientific outputs.

Dimension	Reasoning	Score
Conciseness	Mostly lean and efficient for a complex domain, with specialized content (estimands, target-trial analogues, intercurrent-event handling) earning its place; a few explanatory disclaimers ('PICO is not a universal template', the FINER expansion) could be trimmed.	4 / 5
Actionability	Provides concrete executable commands (e.g. 'python3 scripts/check_operationalization.py local-operationalization.json'), a full tool-index table with copy-paste invocations, and specific templates/frameworks; minor gaps remain in the inherently procedural reasoning steps.	4 / 5
Workflow Clarity	A clearly sequenced 12-step workflow with per-step checklists and validation scripts referenced throughout; the validate-fix-retry feedback loop is implied via exit codes rather than spelled out explicitly in the steps.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview with one-level-deep references; the References and Local tool index sections clearly signal each bundled file (all referenced references/, assets/, and scripts/ paths exist on disk), making navigation easy.	5 / 5
	Total	17 / 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, third-person description that concretely enumerates capabilities and provides an explicit 'Use when' trigger tied to a recognizable scenario. It is comprehensive and distinctive, with only minor room to broaden plain-language trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what ('Formulate...') and when ('Use when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural terms a researcher would say (hypotheses, rival explanations, predictions, measurements, analysis plans, observations), though some phrasing is technical ('evidence-bounded', 'discriminating predictions') and a few plain synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (scientific hypothesis generation) with distinct, specialized triggers and minimal overlap risk with other skills.	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: 1e5eeff

Reviewed: ~17 hours 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.