aris-research-review

Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.

Quality

83%

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

The canonical home for this skill is research-review in wanshuiyin/Auto-claude-code-research-in-sleep

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 highly actionable, clearly sequenced review workflow with concrete MCP calls and ready prompt templates. The main gaps are token efficiency (duplicated prompt content and a pinned model version) and progressive disclosure (no external references and inline content that could be separated).

Suggestions

Remove the duplicated Prompt Templates section or fold its unique phrasings into the relevant workflow steps so each prompt appears once.

Move the pinned REVIEWER_MODEL = gpt-5.4 into a versioned/Constants note or a deprecated-patterns style section so the time-sensitive value does not bloat the core instructions.

If the prompt templates grow further, extract them into a references/ file linked one level deep from the workflow steps rather than inlining all variants.

Dimension	Reasoning	Score
Conciseness	Sections are mostly efficient and skip basic concept explanation, but the Prompt Templates block largely restates the Step 2-3 prompts and the pinned REVIEWER_MODEL = gpt-5.4 is a time-sensitive version number not placed in a deprecated section, so it does not reach the lean/efficient anchor.	2 / 3
Actionability	Provides executable tool invocations (mcp__codex__codex with config {"model_reasoning_effort": "xhigh"}), a concrete setup command (claude mcp add codex -s user -- codex mcp-server), and copy-paste-ready prompt templates, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	A clear five-step sequence (Gather, Initial Review, Iterative Dialogue, Convergence, Document) with an explicit feedback loop and concrete stopping criteria; the operation is non-destructive so the missing-validation cap does not apply.	3 / 3
Progressive Disclosure	Well-headed sections but the body is over 50 lines with no external one-level references, and the duplicated Prompt Templates content is inline material that could be split out, so it sits at 'some structure but could be better organized' rather than the clear-overview-with-references anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 description that pairs an explicit what-and-when structure with natural, copy-ready trigger phrases and a distinct external-review niche. Its only weakness is specificity, since it frames essentially one capability rather than enumerating several concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and core action ("Get a deep critical review of research", "critical feedback on research ideas, papers, or experimental results") but does not list multiple distinct concrete actions, so it stops at 'names domain and some actions' rather than reaching the multi-action anchor.	2 / 3
Completeness	Explicitly answers both what ("Get a deep critical review of research from GPT via Codex MCP") and when ("Use when user says ... or wants critical feedback ..."), matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Quotes natural phrases users would actually say — "review my research", "help me review", "get external review" — plus "critical feedback on research ideas, papers, or experimental results", giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The external-review-via-Codex-MCP mechanism and research-scoped triggers carve a clear niche unlikely to fire for unrelated skills, fitting the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-research-review/SKILL.md
Commit: 6da7f7c

Reviewed: about 7 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.