toolhive-cli-user

Guide for using ToolHive CLI (thv) to run and manage MCP servers and skills. Use when running, listing, stopping, building, or configuring MCP servers locally. Covers server lifecycle, registry browsing, secrets management, client registration, groups, container builds, exports, permissions, network isolation, authentication, and skill management (install, uninstall, list, info, build, push, validate). NOT for Kubernetes operator usage or ToolHive development/contributing.

Quality

89%

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

86%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 well-structured CLI reference with executable commands, clear guardrails for destructive operations, and disciplined offloading of exhaustive flag/example detail to verified companion files. Adding an explicit validate-and-retry loop for build/skill workflows would push workflow clarity to the top level.

Dimension	Reasoning	Score
Conciseness	Mostly lean: command blocks carry brief inline comments and there is little explanation of concepts Claude already knows. Some inline command enumeration duplicates COMMANDS.md and could be trimmed, placing it above the score-3 'mostly efficient' anchor but short of fully lean.	4 / 5
Actionability	Fully executable, copy-paste-ready `thv` commands throughout — e.g. 'thv run filesystem', 'thv secret set MY_API_KEY', 'thv skill install my-skill --scope project' — covering the common cases with concrete flags. Matches the score-5 anchor.	5 / 5
Workflow Clarity	Quick Start gives a clear run/list/status/logs/stop/rm sequence, and the Guardrails section mandates confirming destructive batch ops ('thv rm --all', 'thv stop --all', 'thv group rm --with-workloads') with validation steps ('thv skill validate', 'thv runtime check') and an error-recovery table present. Above 3 because validation/confirmation checkpoints exist; below 5 because there is no explicit validate→fix→retry feedback loop for the primary workflows.	4 / 5
Progressive Disclosure	SKILL.md is a well-organized overview that defers detail to one-level-deep, verified references — '[COMMANDS.md](references/COMMANDS.md#thv-run)' and '[EXAMPLES.md](references/EXAMPLES.md)' — with a 'See Also' section and anchor links. Both referenced files exist, matching the score-5 anchor for clear navigation and appropriate splitting.	5 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong, specific description that clearly states capabilities, when to invoke the skill, and where its boundaries lie. Minor room to broaden trigger-term synonyms, but it is comprehensive and well-scoped.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full surface area — 'server lifecycle, registry browsing, secrets management, client registration, groups, container builds, exports, permissions, network isolation, authentication' plus skill subcommands 'install, uninstall, list, info, build, push, validate'. Comprehensive coverage matching the score-5 anchor; not below since it is not merely 'several specific actions with minor gaps'.	5 / 5
Completeness	Explicitly answers both 'what' ('Guide for using ToolHive CLI (thv) to run and manage MCP servers and skills') and 'when' ('Use when running, listing, stopping, building, or configuring MCP servers locally') with concrete trigger phrases, plus a boundary clause. Matches the score-5 anchor directly.	5 / 5
Trigger Term Quality	'Use when running, listing, stopping, building, or configuring MCP servers locally' supplies natural action verbs a user would say, but lacks synonyms or alternate phrasings (e.g. 'start', 'deploy', 'MCP'). Above 3 because coverage is genuinely good; below 5 because common variations are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (ToolHive CLI for MCP servers/skills) with an explicit exclusion — 'NOT for Kubernetes operator usage or ToolHive development/contributing' — minimizing conflict risk. Distinct triggers; matches the score-5 anchor.	5 / 5
	Total	19 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: stacklok/toolhive
Path: skills/toolhive-cli-user/SKILL.md
Commit: ccabad6

Reviewed: about 13 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.