statistical-problem-formulation

Formulate statistical research problems with formal notation, target parameters, assumptions, hypotheses, evaluation criteria, and theory targets.

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-problem-formulation/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 lean, well-structured, self-contained framework with a concrete handoff schema and a quality gate, but it would be more actionable with a worked example and clearer workflow sequencing. Adding a filled example and an explicit formulation procedure would raise the two mid-scoring dimensions.

Suggestions

Add one fully worked formulation example (filled handoff schema plus a short completed template) so the guidance is concrete and copy-paste ready rather than skeleton-only.

Provide an explicit ordered procedure for producing a formulation (e.g., 1. elicit observed data, 2. specify data model, 3. define target, …) with a review-against-quality-bar feedback step.

Keep the current lean structure; the only gap is moving from placeholders to a demonstrative filled instance.

Dimension	Reasoning	Score
Conciseness	The body is lean and purpose-built — an overview, an elements table, a typed handoff schema, a template, and a quality bar — with no padding explaining concepts Claude already knows, matching the "lean and efficient; every token earns its place" anchor.	3 / 3
Actionability	It provides concrete artifacts (a YAML schema with typed enums like "iid \| dependent \| clustered" and a sectioned template), but the template is skeleton-only with placeholders ("Let …", "Assume …", "…") and lacks a single worked example, leaving the guidance incomplete.	2 / 3
Workflow Clarity	A validation checkpoint exists via the Quality Bar ("passes only if another researcher could implement… without guessing"), but there is no explicit step sequence for performing the formulation and no feedback loop for review-fix-retry, matching the "steps present but checkpoints implicit" anchor.	2 / 3
Progressive Disclosure	The skill is self-contained with no bundle files and is organized into clearly delineated sections (Overview, Required Formulation Elements, Handoff Schema, Template, Quality Bar) with no nested or broken references, satisfying the well-organized self-contained anchor.	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 and names a clear, well-scoped domain, but it omits any explicit "Use when…" trigger guidance, which caps completeness and trigger-term quality. Adding natural trigger phrasing would lift the weaker dimensions.

Suggestions

Append a "Use when…" clause stating when to invoke the skill (e.g., before method design, theory derivation, experiments, or report writing) to satisfy the completeness "when" requirement.

Include natural trigger terms users would actually say (e.g., "define the estimand", "state assumptions", "formalize the hypothesis") to improve trigger-term quality and reduce conflict with generic research skills.

Keep the concrete element list, but ensure the trigger phrasing is explicit so the description both distinguishes the skill and signals when to use it.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete formulation elements — "formal notation, target parameters, assumptions, hypotheses, evaluation criteria, and theory targets" — matching the anchor for listing several specific concrete actions rather than vague language.	3 / 3
Completeness	It clearly answers "what" the skill does, but provides no explicit "when should Claude use it" guidance; per the guidelines a missing "Use when…" clause caps completeness at 2.	2 / 3
Trigger Term Quality	It contains relevant domain keywords ("statistical research problems", "assumptions", "hypotheses") but lacks the natural "Use when…" trigger phrasing and common user-facing variations a requester would naturally say, so it is not at full coverage.	2 / 3
Distinctiveness Conflict Risk	The statistical-formulation niche is fairly specific, but without explicit trigger terms in the description it could still overlap with broader research or analysis skills, matching the "somewhat specific but could overlap" anchor.	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-problem-formulation/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.