x-omo

Use when user asks for non-Claude model dispatch (GPT-5, Gemini, Codex, o3) or invokes OMO agents (oracle, explore, librarian, multimodal-looker) — bridges Claude Code to OpenCode CLI, handles agent catalog, model routing flags, and prompt-block construction

Quality

83%

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

78%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 highly actionable and lean, with concrete commands, error feedback loops, and clear routing. The main defect is progressive disclosure: the skill points to seven detail files but only one exists, leaving most reference links dangling.

Suggestions

Add the missing referenced files (agents/oracle.md, agents/explore.md, agents/librarian.md, agents/multimodal-looker.md, models-routing.md, gotchas.md) or remove/inline the dangling links so every referenced path resolves.

Consolidate the three overlapping routing tables (Agent Catalog, When to Use Which Agent, User Intent Routing) into one or two to tighten conciseness.

Lay out the dispatch lifecycle as a single numbered checklist with explicit validation checkpoints (invoke → set timeout → collect all results → verify any file changes → synthesize) rather than distributing it across sections.

Dimension	Reasoning	Score
Conciseness	Information-dense with tables and executable commands and no padding about concepts Claude already knows, but the Agent Catalog, When-to-Use, and User Intent Routing tables overlap noticeably and could be consolidated. Not 5 because the redundant routing tables are more than trivially trimmable; not 3 because the body is genuinely lean and never explains basics.	4 / 5
Actionability	Fully executable, copy-paste-ready commands ("omo-agent oracle \"prompt\"", "--model <alias>", "--file /path", timeout 600000, run_in_background) cover role agents, model routing, file/skill attach, and parallel dispatch, plus an error-string→resolution map. Matches the anchor for copy-paste-ready commands covering common cases; not 4 because coverage is comprehensive rather than having minor gaps.	5 / 5
Workflow Clarity	A clear dispatch lifecycle (quick-dispatch rule → invoke → set timeout → choose execution mode → collect → synthesize) with an exit-code feedback loop (non-zero → diagnose → retry with correct agent) and a verify-after-modification step. Not 5 because the sequence is distributed across sections rather than one explicit numbered checklist with checkpoints; not 3 because validation and feedback loops are present.	4 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and signals one-level-deep references clearly, but scoring against the actual bundle, 6 of 7 referenced files (agents/oracle.md, agents/explore.md, agents/librarian.md, agents/multimodal-looker.md, models-routing.md, gotchas.md) do not exist — only references/prompt-blocks.md is present, so the disclosure path breaks for most routes. Not 4 because broken/dangling references mean navigation does not actually work; not 2 because the in-skill structure and signaling are good, not minimal.	3 / 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.

A strong description that explicitly covers what the skill does and when to use it, with concrete model/agent triggers and a distinct niche. The only weaknesses are slightly abstract action phrasing and a few natural trigger variations living only in the triggers list rather than the description itself.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("bridges Claude Code to OpenCode CLI, handles agent catalog, model routing flags, and prompt-block construction") plus named models and agents, but the actions are system-level/meta rather than discrete artifact operations, leaving minor coverage gaps. Not 5 because the actions are slightly more abstract than the fully comprehensive concrete-action anchor; not 3 because multiple specific capabilities are clearly named.	4 / 5
Completeness	Explicitly answers both: "Use when user asks for non-Claude model dispatch... or invokes OMO agents" (when, with concrete triggers) and "bridges Claude Code to OpenCode CLI, handles agent catalog, model routing flags, and prompt-block construction" (what). Matches the anchor for clearly and explicitly answering both what AND when with concrete trigger phrases; not 4 because the when clause is fully explicit, not merely adequate.	5 / 5
Trigger Term Quality	Covers natural model names ("GPT-5, Gemini, Codex, o3") and agent names ("oracle, explore, librarian, multimodal-looker") users would say, but is missing some common phrasings like "ask gpt"/"use gemini"/"multi-model" that only appear in the triggers list. Not 5 because synonyms and variations are not comprehensively exhaustive within the description itself; not 3 because keyword coverage is genuinely good.	4 / 5
Distinctiveness Conflict Risk	The non-Claude/OpenCode-CLI niche with named external models and OMO agents is highly specific and distinct from other skills, with minimal conflict risk. Matches the clear-niche anchor; not 4 because the trigger surface is tightly scoped to non-Claude dispatch with no real overlap with generic skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 missing	Warning

	Total	14 / 16 Passed

Repository: quangtran88/x-skills
Path: skills/x-omo/SKILL.md
Commit: f17a69e

Reviewed: 6 days 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.