Name: tooluniverse-codex-plugin
Rating: 73.6 (1 reviews)
Author: mims-harvard

tooluniverse-codex-plugin

Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex. ALWAYS consult this skill for any of those — don't answer from memory, because the exact marketplace name (mims-harvard/ToolUniverse), the "codex plugin marketplace add" then "codex plugin add -m tooluniverse" flow, Codex's startup auto-upgrade behavior, the uvx tooluniverse MCP server, and the API-key env vars are easy to get wrong. Use it whenever someone wants to get ToolUniverse (or "the 1000+ scientific tools" / "the harvard tools") working on Codex, says the Codex plugin or its tools/skills won't load, hits a uvx or MCP-server startup error, asks how Codex updates it, wants to pin or remove it, or finds it running an old tool version — even if they never say the word "plugin". Not for the Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills.

Quality

91%

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

82%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.

A strong, highly actionable install/operational guide with excellent executable commands, a dedicated verify step, and a feedback-loop diagnosis section. The main weaknesses are minor: a few trimmable explanatory asides and a long single-file structure that could offload maintainer notes or the full key list to separate references.

Suggestions

Trim the explanatory parentheticals (e.g. the Git-marketplace rationale after the install block) into a single concise note so only the action and its one-line 'why' remain.

Move the 'For plugin maintainers' section — a different audience — into a separate reference file (e.g. MAINTAINERS.md) and link to it from the body, tightening the user-facing overview.

Collapse the env-var keys into a one-line pointer to API_KEYS_REFERENCE.md rather than inlining three export examples plus the cache-edit caveat.

Dimension	Reasoning	Score
Conciseness	Mostly lean and information-dense — copy-paste command blocks and compact tables — but a handful of parenthetical asides (e.g. the owner/repo Git-marketplace rationale) could be trimmed without losing actionability.	4 / 5
Actionability	Fully executable throughout: exact 'codex plugin marketplace add' / 'codex plugin add -m tooluniverse' commands, env-var exports, a JSON pin snippet, and a numbered automated-diagnosis block with explicit FIX actions covering the common failure cases.	5 / 5
Workflow Clarity	Clear install sequence (Prerequisites → two-command install → Restart → 'Verify it worked') plus a troubleshooting table and a feedback-loop diagnosis section, but the validation checkpoints are spread across sections rather than one unified validated flow, leaving minor gaps.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with one clearly signaled one-level reference ('the bundled setup-tooluniverse skill → API_KEYS_REFERENCE.md'), but the body is a long single file with no actual bundle split and the maintainer section addresses a different audience than the user flow.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

An exemplary description: third-person voice, comprehensive concrete actions, dense natural trigger coverage, and explicit disambiguation against the sibling Claude Code skill. It is long but information-dense rather than padded, so verbosity does not pull it below the top anchors.

Dimension	Reasoning	Score
Specificity	Lists seven concrete plugin-lifecycle actions — 'Install, set up, verify, update, pin, uninstall, or troubleshoot' — giving comprehensive, non-generic coverage with no real gaps.	5 / 5
Completeness	Explicitly states both what (the seven lifecycle actions on the ToolUniverse Codex plugin) and when ('Use it whenever someone wants to get ToolUniverse ... working on Codex'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural phrases and synonyms users actually say ('1000+ scientific tools', 'the harvard tools', 'won't load', 'uvx startup error', 'running an old tool version'), including the 'even if they never say the word plugin' case.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche and adds explicit negative boundaries — 'Not for the Claude Code plugin (use tooluniverse-claude-code-plugin), for running research with the tools, or for authoring new tools or skills' — minimizing overlap with the sibling skill.	5 / 5
	Total	20 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: skills/tooluniverse-codex-plugin/SKILL.md
Commit: 1b02920

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.