omc-doctor
Diagnose and fix oh-my-claudecode installation issues
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/omc-doctor/SKILL.mdQuality
Discovery
40%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 troubleshooting) which gives it strong distinctiveness, but it lacks explicit trigger guidance ('Use when...') and doesn't enumerate specific actions or common user phrasings. It reads more like a title than a full skill description.
Suggestions
Add a 'Use when...' clause with trigger terms like 'oh-my-claudecode not working', 'install error', 'setup failed', 'plugin not loading', 'configuration problem'.
List specific concrete actions such as 'check PATH configuration, resolve dependency conflicts, verify shell integration, fix permission errors, validate config files'.
Include common user phrasing variations like 'setup', 'install', 'broken', 'can't load', 'error' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (oh-my-claudecode installation) and two actions (diagnose and fix), but doesn't list specific concrete actions like checking PATH, resolving dependency conflicts, or verifying configuration files. | 2 / 3 |
Completeness | Describes what it does (diagnose and fix installation issues) but has no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also quite thin, bringing it to 1. | 1 / 3 |
Trigger Term Quality | Includes 'oh-my-claudecode' and 'installation issues' which are relevant keywords, but misses common variations users might say like 'setup', 'install error', 'not working', 'configuration', or 'plugin'. | 2 / 3 |
Distinctiveness Conflict Risk | The skill targets a very specific tool ('oh-my-claudecode') and a specific problem domain (installation issues), making it clearly distinguishable and unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured diagnostic skill with strong actionability and clear workflow sequencing. Each step has concrete commands, explicit diagnosis criteria, and corresponding fixes. The main weaknesses are the verbose inline Node.js one-liners that hurt readability and the long lists of known plugin names that could be externalized to improve conciseness and progressive disclosure.
Suggestions
Extract the long lists of known plugin agent/skill/command names into a separate reference file (e.g., KNOWN_PLUGIN_FILES.md) and reference it from the main skill.
Refactor the complex inline Node.js one-liners (especially the CLAUDE.md version check) into readable multi-line scripts or reference external script files for clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long with some verbose inline Node.js one-liners that are hard to read, and the extensive lists of known plugin names add bulk. However, most content is necessary diagnostic/fix instructions rather than explaining concepts Claude already knows. The CLAUDE.md version-check script is particularly bloated. | 2 / 3 |
Actionability | Every diagnostic step has concrete, executable bash/node commands, clear diagnosis criteria with severity levels (OK/WARN/CRITICAL), and specific fix commands. The auto-fix section provides copy-paste ready solutions for each identified issue. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced as numbered steps (1-7), each with explicit diagnosis criteria and severity classifications. The auto-fix section includes a confirmation checkpoint ('ask user'), backup suggestions before destructive operations, and a post-fix restart instruction. The report format provides a structured validation summary. | 3 / 3 |
Progressive Disclosure | The content is a single monolithic file with no references to supporting documents, which is acceptable for a diagnostic skill but the file is quite long (~200+ lines). The known plugin names lists and lengthy inline Node scripts could be extracted to reference files to keep the main skill leaner. | 2 / 3 |
Total | 10 / 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.