oh-my-codex
Multi-agent orchestration layer for OpenAI Codex CLI. Provides 30 specialized agents, 40+ workflow skills, team orchestration in tmux, persistent MCP servers, and staged pipeline execution.
67
48%
Does it follow best practices?
Impact
100%
1.38xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/oh-my-codex/SKILL.mdQuality
Discovery
32%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 provides a feature inventory with impressive-sounding numbers (30 agents, 40+ workflows) but lacks concrete action verbs describing what users can actually do. The critical 'Use when...' clause is entirely absent, making it difficult for Claude to know when to select this skill. The technical jargon may not match how users naturally request these capabilities.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'coordinate multiple agents', 'run Codex workflows', 'manage AI team in terminal', or 'orchestrate coding tasks'
Replace feature counts with concrete actions: instead of '30 specialized agents', describe what users can do like 'spawn coding agents, coordinate parallel tasks, manage agent communication'
Include simpler trigger terms users might naturally say: 'AI team', 'parallel coding', 'agent coordination', 'automated workflows'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (OpenAI Codex CLI orchestration) and lists some capabilities (30 agents, 40+ workflows, tmux orchestration, MCP servers, pipeline execution), but these are high-level feature counts rather than concrete user-facing actions like 'create agent', 'run pipeline', or 'coordinate team tasks'. | 2 / 3 |
Completeness | Describes what the skill provides (agents, workflows, orchestration features) but completely lacks any 'Use when...' clause or explicit guidance on when Claude should select this skill. The 'when' is entirely missing. | 1 / 3 |
Trigger Term Quality | Includes some relevant technical terms like 'Codex CLI', 'tmux', 'MCP servers', and 'multi-agent', but these are fairly technical. Missing natural user phrases like 'coordinate agents', 'run workflows', 'manage AI team', or simpler trigger terms users might actually say. | 2 / 3 |
Distinctiveness Conflict Risk | The specific mention of 'OpenAI Codex CLI' and 'tmux' provides some distinctiveness, but terms like 'multi-agent orchestration', 'workflow skills', and 'pipeline execution' could overlap with other automation or orchestration skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides comprehensive, actionable reference documentation for the OMX multi-agent orchestration system with good use of tables and concrete commands. However, it lacks validation checkpoints in workflows, could benefit from splitting advanced content into separate files, and includes some unnecessary boilerplate (License, Resources sections that don't add instructional value).
Suggestions
Add validation/verification steps to the staged pipeline section (e.g., 'After team-exec, verify with `omx team status` before proceeding to team-verify')
Remove or minimize License and Resources sections - these don't help Claude execute tasks
Split hook extensions and configuration into separate reference files, keeping only essential quick-start info in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient with good use of tables, but includes some unnecessary sections (License, Resources) and could be tighter. The 'When to use this skill' section restates what's obvious from the title. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout: installation steps, CLI commands, workflow triggers, and team management commands are all copy-paste ready with specific syntax. | 3 / 3 |
Workflow Clarity | The staged pipeline section shows a clear sequence but lacks validation checkpoints or error recovery guidance. Team mode commands are listed but there's no guidance on what to do if team workers fail or how to verify successful completion. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline in one large file. Advanced topics like hook extensions and configuration could be split into separate reference files. External links are provided but no internal file references for deeper documentation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- supercent-io/skills-template
- Commit
fd18296
- Reviewed
Table of Contents
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.