statistical-method-design

Design statistical methods, baselines, diagnostics, variants, and ablations that directly address a formal problem formulation.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./external/agents/stat_research_agent/skills/statistical-method-design/SKILL.md

Quality

Content

80%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.

The skill body is lean and well-structured with concrete checklists and a useful YAML template, fitting a simple design-spec skill well. Its main weakness is workflow clarity: the material reads as a checklist rather than a sequenced, validated process.

Suggestions

Convert the implicit design sequence into an explicit ordered workflow with numbered steps and a validation checkpoint (e.g., verify each method maps to a claim before finalizing).

Add one fully worked example of a method proposal showing name, formula/algorithm, assumptions, and diagnostics filled in.

Optionally include a brief "before you start" trigger reminder so the body is self-contained without relying on the description.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanation of concepts Claude already knows; every section (overview, checklists, YAML example) earns its place.	5 / 5
Actionability	Concrete, specific checklists for method components and baseline types give actionable guidance, but there is no worked example of a complete method proposal (e.g., a sample formula or algorithm block).	4 / 5
Workflow Clarity	The sections imply a rough sequence (formulate, propose, define baselines, map to claims) but present a checklist rather than an explicit ordered workflow, with no validation checkpoints.	3 / 5
Progressive Disclosure	Under 50 lines, no bundle files needed, and content is well-organized into clearly labeled sections (Overview, Required Method Proposal, Baselines and Ablations, Method-to-Claim Map).	5 / 5
	Total	17 / 20 Passed

Description

58%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.

The description is concise and names a clear domain with several concrete deliverable types, but it lacks an explicit "Use when..." trigger clause, which caps its completeness and trigger-term quality. It is reasonably distinct from sibling skills.

Suggestions

Add an explicit trigger clause, e.g. "Use when proposing an estimator, baseline, ablation, or diagnostic for a formally specified statistical problem."

Replace the single generic verb "design" with more concrete action verbs or named method types (e.g., "construct estimators, specify baselines, derive diagnostics").

Include natural keyword variations a user might say (e.g., "method proposal", "ablation study", "baseline comparison") in the description body.

Dimension	Reasoning	Score
Specificity	Lists several concrete deliverable types ("methods, baselines, diagnostics, variants, and ablations") but applies one generic verb ("design") without naming concrete method types, leaving minor coverage gaps.	4 / 5
Completeness	Has a clear "what" (design statistical methods addressing a formal problem formulation) but no explicit "when/Use when" clause; the trigger is only weakly implied, which caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like "baselines" and "ablations" are domain-relevant but there are no natural trigger phrases (e.g., "Use when proposing an estimator"), missing common variations users would actually say.	3 / 5
Distinctiveness Conflict Risk	Tied specifically to formal problem formulation, giving it a clear niche with only minor overlap risk against general research or experimental-design skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: aiming-lab/AutoResearchClaw
Path: external/agents/stat_research_agent/skills/statistical-method-design/SKILL.md
Commit: be4ba47

Reviewed: 5 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.