hypothesis-formulation

Structured scientific hypothesis generation from observations. Use when formulating testable hypotheses, competing explanations, or experimental predictions.

Quality

80%

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 concise, well-structured procedural skill that gives concrete, actionable guidance for hypothesis formulation without over-explaining concepts Claude already knows; its main gap is the absence of a worked example and explicit validation/feedback loops.

Suggestions

Add one short worked example showing the If/then/because template applied to a real observation so the hypothesis format is unambiguous.

Insert an explicit validation checkpoint (e.g., verify each hypothesis is falsifiable and discriminated from alternatives before moving to experimental design) to strengthen the feedback loop.

Tighten or merge generic self-evident items like "State both explicitly" and "Propose at least 2-3 plausible explanations" to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is a lean numbered list that assumes Claude already knows what H0/H1, power analysis, and pre-registration are, with no concept padding; not 5 because a few items are self-evidently generic ("State both explicitly", "Propose at least 2-3 plausible explanations") and could be trimmed or tightened.	4 / 5
Actionability	Concrete directives and an explicit "If... then... because..." template plus specific methods (power analysis, pre-registration) give mostly executable guidance; not 5 because there is no worked example anchoring the template, and not 3 because guidance goes well beyond pseudocode.	4 / 5
Workflow Clarity	Five numbered sections form a clear observation-to-design sequence with embedded checks ("Ensure the hypothesis is falsifiable", "Ensure sample size is adequate"); not 5 because there are no explicit error-recovery feedback loops, and not 3 because checkpoints are present rather than missing.	4 / 5
Progressive Disclosure	A single ~35-line file with no need for external references, organized into five clearly headed sections, qualifies for the simple-skill exception allowing a 5 on well-organized structure alone.	5 / 5
	Total	17 / 20 Passed

Description

82%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 tight, well-formed description that clearly answers both what the skill does and when to use it, with natural trigger phrases and low conflict risk; its only weakness is that the 'what' names a single primary action rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	"Structured scientific hypothesis generation from observations" names the domain plus one concrete action (generation), but does not enumerate several specific capabilities, matching the 3 anchor (1-2 concrete actions, not comprehensive); not 4 because it lists only a single primary action, not several.	3 / 5
Completeness	It explicitly states the what ("Structured scientific hypothesis generation from observations") and an explicit when with concrete trigger phrases ("Use when formulating testable hypotheses, competing explanations, or experimental predictions"), matching the 5 anchor.	5 / 5
Trigger Term Quality	"Use when formulating testable hypotheses, competing explanations, or experimental predictions" surfaces several natural phrases a user would say; not 5 because coverage lacks synonyms/file-style variations and a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	"Scientific hypothesis generation" carves a clear niche with distinct triggers (hypotheses, competing explanations, predictions) and minimal overlap with other skills, matching the 5 anchor.	5 / 5
	Total	17 / 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: aiming-lab/AutoResearchClaw
Path: researchclaw/skills/builtin/experiment/hypothesis-formulation/SKILL.md
Commit: be4ba47

Reviewed: 4 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.