Name: tooluniverse-codex-plugin
Rating: 75.2 (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

94%

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

The canonical home for this skill is tooluniverse-codex-plugin in mims-harvard/ToolUniverse

Quality

Content

88%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 body: copy-paste commands, a verification step, and ordered diagnostic feedback loops. The main weaknesses are minor redundancy between the two troubleshooting sections and a maintainer section that arguably belongs in a separate reference file.

Suggestions

Collapse the Troubleshooting table and the "Automated diagnosis & repair" block into a single source of truth to remove the duplicated fixes (e.g. uv cache clean, uv tool uninstall, marketplace upgrade).

Move the "For plugin maintainers" section into a separate reference file (e.g. MAINTAINERS.md) and link to it, keeping SKILL.md focused on the user-facing install flow.

Tighten the prose explaining Git-marketplace mechanics — the auto-upgrade behavior is already demonstrated by the upgrade commands and the troubleshooting "Update never arrived" row.

Dimension	Reasoning	Score
Conciseness	Mostly lean with tables and code blocks earning their place, but there is noticeable redundancy between the Troubleshooting symptom/fix table and the later "Automated diagnosis & repair" section, plus some prose (e.g. the Git-marketplace mechanism) that could be trimmed — efficient with minor over-explanation, a 4 not a 5.	4 / 5
Actionability	Every step is copy-paste ready: concrete bash commands for install, verify, update, pin, uninstall, and diagnosis, with a worked pin example ("args": ["tooluniverse@1.3.0"]) and specific recovery commands covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced flow (Prerequisites → Install → Verify → Updates → Uninstall) with explicit validation (codex plugin list / --json, uvx tu --version) and feedback loops in both the Troubleshooting table and the ordered "Automated diagnosis & repair" steps that say to apply the FIX for whatever fails then restart.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with a one-level-deep pointer to the bundled setup-tooluniverse skill's API_KEYS_REFERENCE.md, but all content lives in a single ~160-line file with the maintainer-oriented section inlined rather than split out — good structure with minor organization gaps, a 4.	4 / 5
	Total	18 / 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: specific actions, comprehensive natural trigger phrases with synonyms and error scenarios, explicit what/when, and a clear boundary against the sibling Claude Code skill. Every dimension lands on the top anchor.

Dimension	Reasoning	Score
Specificity	"Install, set up, verify, update, pin, uninstall, or troubleshoot the ToolUniverse plugin on OpenAI Codex" lists seven distinct concrete actions with comprehensive coverage of the plugin lifecycle, matching the 5-anchor.	5 / 5
Completeness	Clearly answers "what" (the seven lifecycle actions) and "when" ("Use it whenever someone wants to get ToolUniverse...won't load, hits a uvx...error...wants to pin or remove it"), both explicit and concrete. Uses third person throughout with no first/second-person voice.	5 / 5
Trigger Term Quality	Includes natural user phrases ("get ToolUniverse working on Codex", "the 1000+ scientific tools", "the harvard tools", "uvx or MCP-server startup error", "running an old tool version") plus the "even if they never say the word 'plugin'" hedge, giving comprehensive coverage of natural terms and synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (ToolUniverse on OpenAI Codex) with an explicit exclusion clause — "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 conflict risk.	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: plugins/tooluniverse/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.