auto-review-loop-minimax

Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex/auto-review-loop-minimax/SKILL.md

Quality

Content

67%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 body is actionable and well-structured with a clear multi-phase workflow and validation checkpoints. Its main weakness is conciseness: the MCP/curl invocation and prompt body are repeated across three sections rather than factored into a single referenced template.

Suggestions

Factor the repeated MCP/curl invocation and full review prompt into a single template section, then reference it from Phase A and the Round 2+ section to remove triplicated content.

Replace bracketed placeholders like "[Review prompt content]" with explicit pointers to the canonical prompt template so the guidance is fully copy-paste-ready.

Tighten the duplicated STOP CONDITION / POSITIVE_THRESHOLD definition (currently stated in both Constants and Phase B) into one authoritative location.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete prompts and commands, but the full MCP/curl invocation and prompt body are repeated three times (API Configuration, Phase A, Round 2+ template), adding noticeable verbosity that could be tightened via a shared template reference.	3 / 5
Actionability	Provides concrete, mostly copy-paste-ready guidance: exact curl commands, JSON state schema, MCP tool invocations with verbatim system prompts, and file paths, with only minor placeholder gaps like "[Review prompt content]".	4 / 5
Workflow Clarity	Clear sequence (Initialization → Phases A–E → Termination) with an explicit STOP CONDITION, a 24-hour staleness validation checkpoint, and a review→fix→re-review feedback loop; minor validation gaps prevent a top score.	4 / 5
Progressive Disclosure	Well-sectioned body with clearly signaled one-level-deep references to shared-references/*.md (output-versioning, output-manifest, output-language) and no nested references; minor organization gaps from repeated inline templates.	4 / 5
	Total	15 / 20 Passed

Description

87%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 clear, specific, and distinct, with explicit trigger guidance and concrete differentiation from the Codex MCP alternative. Minor specificity gaps keep it just below a perfect specificity score, but it strongly answers both what and when.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("multi-round research review loop using MiniMax API", review→implement→re-review), with only minor gaps in enumerated actions versus a fully comprehensive list.	4 / 5
Completeness	Explicitly answers both what (autonomous multi-round research review loop) and when ("Use when you want to use MiniMax instead of Codex MCP", with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ("auto review loop minimax", "minimax review") and an explicit "Use when" clause, with only a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (MiniMax-based external review) explicitly differentiated from Codex MCP, with distinct triggers minimizing conflict risk.	5 / 5
	Total	18 / 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/skills-codex/auto-review-loop-minimax/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.