omc
oh-my-claudecode — Teams-first multi-agent orchestration layer for Claude Code. 32 specialized agents, smart model routing, persistent execution loops, and real-time HUD visibility. Zero learning curve.
64
45%
Does it follow best practices?
Impact
98%
7.53xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/omc/SKILL.mdQuality
Discovery
17%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description reads more like marketing copy than a functional skill description. It lists features and buzzwords ('Teams-first', 'Zero learning curve') but fails to describe concrete actions Claude would perform or when this skill should be selected. The technical jargon and lack of natural trigger terms make it difficult for Claude to match user requests to this skill.
Suggestions
Add a 'Use when...' clause specifying explicit triggers, such as 'Use when the user mentions multi-agent workflows, team coordination, agent orchestration, or needs to run multiple Claude agents together'
Replace marketing language with concrete action verbs describing what the skill does, e.g., 'Coordinates multiple specialized agents to complete complex tasks, routes requests to appropriate models, maintains persistent execution state'
Include natural user-facing keywords that someone would actually say, such as 'multiple agents', 'parallel tasks', 'team workflows', 'agent coordination'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (multi-agent orchestration) and mentions some features ('32 specialized agents, smart model routing, persistent execution loops, real-time HUD visibility'), but these are high-level feature claims rather than concrete actions Claude would perform. No specific verbs describing what actions the skill enables. | 2 / 3 |
Completeness | Describes what it is (an orchestration layer with features) but completely lacks any 'Use when...' clause or explicit trigger guidance. Does not answer when Claude should select this skill over others. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('multi-agent orchestration layer', 'HUD visibility', 'model routing') that users would not naturally say. Missing natural trigger terms users might use when needing this functionality. 'Zero learning curve' is marketing fluff, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The specific product name 'oh-my-claudecode' and '32 specialized agents' provide some distinctiveness, but 'multi-agent orchestration' could overlap with other agent-related skills. The lack of clear use-case triggers increases conflict risk. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid actionable guidance with clear commands and good organization. The main weaknesses are some marketing fluff that wastes tokens and missing validation/error recovery details for the orchestration workflows. The quick reference table and installation steps are particularly well done.
Suggestions
Remove the 'Why OMC?' section - it's marketing content that Claude doesn't need to execute the skill
Add explicit validation steps and error recovery guidance for Team mode pipeline failures (e.g., what to check if team-verify fails)
Trim descriptions in tables to essential information only (e.g., 'Coordinated agents on shared task list' could just be 'Multi-agent coordination')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary marketing language ('Zero learning curve', 'Why OMC?' section) and explanatory content that doesn't add actionable value. The tables are well-structured but some descriptions could be tighter. | 2 / 3 |
Actionability | Provides concrete, copy-paste ready commands throughout. Installation steps are explicit, command syntax is clear with examples, and the quick reference table gives immediately executable commands. | 3 / 3 |
Workflow Clarity | The Team mode pipeline is clearly sequenced (plan → prd → exec → verify → fix loop), but lacks explicit validation checkpoints or error recovery guidance. The update workflow mentions '/omc:omc-doctor' for issues but doesn't explain what to do with its output. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, numbered steps, and tables for quick scanning. Links to full documentation and GitHub for deeper content. Content is appropriately split without nested references. | 3 / 3 |
Total | 10 / 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
c033769
- 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.