statistical-method-design

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

Quality

66%

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

72%Weight 40%Scale 1-3

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

The body is a compact, well-organized instruction-only skill that assumes Claude's competence and needs no external references. Its main weakness is actionability and workflow clarity: it provides a template and an implied ordering rather than a worked example or an explicit validate-the-method-against-the-target checkpoint.

Suggestions

Add one short worked example showing a populated method proposal (a named estimator with its formula, assumptions, diagnostics, and baseline) so the checklist is concrete rather than abstract.

Make the workflow explicit and ordered (e.g. 1. derive method from the formal target, 2. define baselines/ablations, 3. build the method-to-claim map, 4. verify each method addresses the stated assumptions) with a validation checkpoint at the end.

Specify how to check that a method 'directly addresses' the formal problem formulation — a concrete sanity check the model can run before finalizing the proposal.

Dimension	Reasoning	Score
Conciseness	The body is lean — a short overview, two bulleted checklists, and a compact YAML template — with no padding or explanation of concepts Claude already knows; every line earns its place.	3 / 3
Actionability	It gives a concrete per-method checklist (Name, Problem it solves, Formula, Inputs/outputs, etc.) and a fill-in YAML schema, but stays at the template level with no worked example, so key instantiation detail is missing.	2 / 3
Workflow Clarity	The sections imply an ordered progression (propose method → define baselines/ablations → map to claims), but the sequence is implicit and there are no validation checkpoints confirming the method actually addresses the formal target.	2 / 3
Progressive Disclosure	At ~44 lines with no bundle files and no need for external references, the well-organized sections satisfy the simple-skill allowance for a top score on progressive disclosure.	3 / 3
	Total	10 / 12 Passed

Description

60%Weight 40%Scale 1-3

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 about capabilities but reads as a capability statement rather than a triggered instruction: it states what the skill does without an explicit "Use when..." clause or natural trigger terms. Adding trigger guidance and more natural user phrasings would lift the completeness and trigger-term dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when proposing an estimator or algorithm, defining baselines, running ablations, or designing diagnostics for a formal problem statement').

Reword capability verbs into phrasings users actually say, such as 'design a baseline', 'run an ablation study', or 'add diagnostics', to improve trigger-term quality.

Tie the 'when' to concrete workflow moments (after problem formulation, before empirical evaluation) to sharpen distinctiveness from general methodology skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in one clause — "Design statistical methods, baselines, diagnostics, variants, and ablations" — matching the anchor for enumerating several specific capabilities.	3 / 3
Completeness	It clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger; "that directly address a formal problem formulation" only implies the when, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Domain terms like "baselines", "ablations", and "diagnostics" are words a research user might say, but the phrasing is capability-style rather than natural triggers and common variations (e.g. "design a baseline", "run an ablation") are missing.	2 / 3
Distinctiveness Conflict Risk	The statistical-method-design niche is fairly specific, but the description lacks explicit triggers to disambiguate it from adjacent methodology skills, so overlap risk remains.	2 / 3
	Total	9 / 12 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: e2e23c9

Reviewed: 6 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.