ara-rigor-reviewer

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

77%

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

A well-structured, highly actionable review procedure with clear workflow sequencing and a real one-level-deep reference. The main weakness is conciseness/progressive-disclosure overlap: the six dimensions' scoring anchors and check inventories are duplicated between the body and the reference file instead of being split cleanly.

Suggestions

Move the per-dimension scoring-anchor tables and check inventories out of the body and into references/review-dimensions.md, keeping only a one-line summary plus the dimension table inline, to remove duplication and tighten the overview.

Replace the inlined D1-D6 anchor/check blocks with short pointers (e.g., "See references/review-dimensions.md#d1") so the body stays a lean procedure while detail lives one level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance and avoids explaining generic concepts Claude knows, but the six per-dimension sections each restate full scoring anchors and check lists that are duplicated in references/review-dimensions.md, so it could be tightened rather than earning the lean-and-efficient 3.	2 / 3
Actionability	Despite being instruction-only with no code, the guidance is highly concrete and executable: a fixed read order, exact entity-extraction rules (e.g., each `## C{NN}` section with named fields), explicit working maps, a precise findings schema, a grade-mapping table, and a copy-paste-ready JSON report template.	3 / 3
Workflow Clarity	A clearly sequenced seven-step procedure with explicit checkpoints (grade gates such as "no dimension < 3", severity-sorted findings, verbatim evidence_span requirements); the read-only review nature means the destructive/batch validation cap does not apply.	3 / 3
Progressive Disclosure	A single reference is clearly signaled ("See [references/review-dimensions.md]...for scoring anchor details and check inventories") and exists on disk, but the per-dimension anchor and check detail is also inlined in the body — content that should be separate is inline — matching the anchor-2 example rather than a clean split.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 clearly states capabilities and an explicit use-when trigger with a distinct niche. Its only weakness is trigger-term quality: the phrasing leans on domain jargon rather than the natural vocabulary a user would actually say.

Suggestions

Add layperson trigger terms (e.g., "peer review", "research rigor audit", "critique a research artifact") so users can surface the skill with everyday phrasing rather than only ARA-specific jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person ("Performs...review", "scoring six dimensions", "producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation"), matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers both what (performs the review, scores six dimensions, produces a report with a recommendation) and when ("Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release"), mirroring the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Contains some natural terms ("review", "epistemic critique", "publication or release") but is dominated by jargon ("ARA Seal Level 2 semantic epistemic review") and misses common user variations like "peer review" or "research rigor" that appear only in tags, so it is not a 3.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply defined (ARA Seal Level 2 epistemic review) with distinct triggers tied to Level 1 passing and pre-publication critique, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 22-agent-native-research-artifact/rigor-reviewer/SKILL.md
Commit: 773a529

Reviewed: about 12 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.