omc-setup
Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow
53
60%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/omc-setup/SKILL.mdQuality
Discovery
57%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 identifies a clear niche (oh-my-claudecode installation/refresh) and is unlikely to conflict with other skills, but it lacks an explicit 'Use when...' clause and relies on somewhat jargon-heavy language like 'canonical setup flow'. The specificity of actions could be improved by listing what the setup flow actually does beyond install/refresh.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to install, set up, update, or refresh oh-my-claudecode.'
Replace jargon like 'canonical setup flow' with more natural language describing what the process entails, such as 'following the standard installation steps'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (oh-my-claudecode) and some actions (install, refresh), and mentions setup types (plugin, npm, local-dev), but doesn't list specific concrete actions beyond install/refresh. | 2 / 3 |
Completeness | The 'what' is partially addressed (install or refresh oh-my-claudecode for various setup types), but there is no explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'install', 'oh-my-claudecode', 'plugin', 'npm', 'local-dev', but these are somewhat niche. Users might say 'setup oh-my-claudecode' or 'install oh-my-claudecode' which are partially covered, but 'canonical setup flow' is jargon rather than a natural user phrase. | 2 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to 'oh-my-claudecode' which is a distinct tool/project, making it very unlikely to conflict with other skills. The niche is clear and well-defined. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent workflow clarity—clear phases, decision trees, resume detection, and interrupt handling make it robust for a complex setup process. However, it is significantly over-verbose: the full help text is reproduced inline, explanations are repeated across sections (Best-Fit Use, Help Text, Keeping Up to Date), and prose descriptions duplicate what the code already shows. Trimming redundancy could cut this by 30-40% without losing any information.
Suggestions
Remove or drastically shorten the inline help text block—Claude can generate help output dynamically from the flag definitions already provided, or reference it from a separate file.
Eliminate the 'Keeping Up to Date' section, which repeats information already covered in the Pre-Setup Check and flag parsing sections.
Consolidate the 'Best-Fit Use' section into the flag parsing section since they describe the same scenarios from different angles.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose. The full help text block is reproduced inline (which Claude could generate dynamically), the pre-setup check logic is explained in both prose and code redundantly, and there's significant repetition between the help text, the 'Best-Fit Use' section, and the 'Keeping Up to Date' section. The options for the already-configured prompt are described in exhaustive detail that could be much more compact. | 1 / 3 |
Actionability | The skill provides concrete, executable bash commands, specific file paths, exact flag parsing behavior, and clear decision trees for each scenario. The code snippets are copy-paste ready and the phase references point to specific file paths. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with explicit phases (1-4), pre-setup checks, resume detection, flag parsing as a decision tree, and graceful interrupt handling. Validation checkpoints exist (checking config file, prompting user at decision points) and there's a clear feedback loop for resume vs. start fresh. | 3 / 3 |
Progressive Disclosure | The skill correctly delegates detailed phase instructions to separate files (phases/01-04), which is good progressive disclosure. However, the inline help text block and the verbose pre-setup check explanation bloat the main file with content that could be more concise or referenced. Without bundle files provided, the phase file references cannot be verified, but the structure is sound. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
679b418
- 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.