aris-infra

ARIS (Auto-claude-code-research-in-sleep) infrastructure setup and configuration. Configures MCP servers for cross-model adversarial review, installs Python tools, and validates environment. Run this first before using any other ARIS skills. Use when: setting up ARIS, configuring review servers, "aris setup", "配置ARIS".

Quality

81%

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

Quality

Content

75%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 well-structured and highly actionable with copy-paste commands and a clear setup sequence, scoring solidly at 4 across all dimensions. The main gaps are a weak verification step, no integrated error-recovery feedback loop, and some inline content that could be offloaded to reference files.

Suggestions

Make Step 3 verification concrete and executable, e.g. a real tool invocation or `claude mcp list | grep <server>` check, instead of comment hints.

Add an explicit feedback loop: if `claude mcp list` does not show the expected server, re-run `claude mcp add ... -s user` and link to the relevant Troubleshooting item.

Move the per-MCP-server setup details (commands + env vars) into one-level-deep reference files under a bundled directory, keeping SKILL.md as an overview that points to them.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean commands, tables, and env-var blocks, but the Overview paragraph explaining the "self-play blind spot" rationale and the inline listing of five full MCP-server configs are minor instances of over-explanation that could be trimmed.	4 / 5
Actionability	Most guidance is copy-paste ready ("npm install -g @openai/codex", "claude mcp add ...", "pip install httpx arxiv requests"), but Step 3's verification is hint-level ("mcp__codex__codex should be available") rather than a concrete executable test command.	4 / 5
Workflow Clarity	A clear Step 1→2→3 sequence with a Verify Setup checkpoint is present, but there is no integrated feedback loop tying verification failure to a remediation step (the Troubleshooting section is separate, not wired into the flow).	4 / 5
Progressive Disclosure	Section structure is good (Quick Start, Steps, Workflows, Bundled Resources, Troubleshooting) and the Bundled Resources section lists one-level-deep file references, but the five MCP-server setups are inlined rather than split into per-server reference files, leaving a minor organization gap.	4 / 5
	Total	16 / 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 clearly and explicitly answers both what the skill does and when to use it, with concrete trigger phrases and a distinctive niche. Minor gaps in action specificity and trigger synonym coverage keep specificity and trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	"Configures MCP servers for cross-model adversarial review, installs Python tools, and validates environment" lists several concrete actions, though "installs Python tools" and "validates environment" are slightly generic, keeping it just below comprehensive (5).	4 / 5
Completeness	It explicitly states both what ("Configures MCP servers... installs Python tools, and validates environment") and when ("Run this first before using any other ARIS skills. Use when: ...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"setting up ARIS, configuring review servers, \"aris setup\", \"配置ARIS\"" provides good natural keyword coverage including a bilingual synonym, but misses common variations like "install" or "initialize" for a fully comprehensive set.	4 / 5
Distinctiveness Conflict Risk	The distinctive ARIS acronym and specific triggers ("aris setup", "配置ARIS") carve a clear niche with minimal risk of firing for unrelated skills.	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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-infra/SKILL.md
Commit: d51b64e

Reviewed: 5 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.