omc-doctor

Diagnose and fix oh-my-claudecode installation issues

Quality

62%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/omc-doctor/SKILL.md

Quality

Content

71%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 a strong operational document: fully executable diagnostics with per-step verdict criteria, a defined report format, and safely gated auto-fixes. Its weaknesses are redundancy (repeated version-check snippets, inlined name catalogs) and a monolithic structure with no reference files, plus no verification loop after fixes are applied.

Suggestions

Extract the repeated node version/cache-sniffer script into a single shared snippet (or a scripts/ file) and reuse it in Steps 1, 4, 6 and the fix section instead of restating it.

Move the plugin agent/skill/command name catalogs and the fix procedures into one-level-deep reference files (e.g. references/legacy-names.md, references/fixes.md) and link them from the body.

Add a post-fix verification step that re-runs the diagnostics and confirms the issue is resolved before telling the user to restart Claude Code.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but it is noticeably redundant: the same ~600-character node version-snippet is repeated across Steps 1, 4, 6 and the fixes section, and two long plugin-name lists are fully inlined, matching the 'mostly efficient but could be tightened' anchor rather than the efficient one at 4.	3 / 5
Actionability	Every step ships copy-paste-ready bash/node commands, each with an explicit diagnosis table, plus a concrete report template and complete fix commands (including a specific WebFetch call), matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	Seven clearly sequenced checks each end in an explicit diagnosis checkpoint, and destructive fixes are gated on user confirmation, name-matching validation against plugin-provided names, and optional backups — but there is no post-fix re-run of diagnostics to verify resolution, so it sits at the 'clear sequence with minor validation gaps' anchor rather than 5.	4 / 5
Progressive Disclosure	Sections are well-labeled (Steps 1-7, Report Format, Auto-Fix, Post-Fix) but the skill is entirely monolithic with no bundle files; the long plugin-name lists and fix procedures are prime candidates for one-level-deep reference files, matching the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	15 / 20 Passed

Description

53%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.

The description is clear, in third person, and distinct thanks to naming the target plugin, but it is minimal: it states only a generic diagnose-and-fix action with no trigger guidance and no enumeration of what kinds of installation issues are covered. Adding a 'Use when...' clause and a few specifics (hooks, plugin cache, CLAUDE.md) would raise most dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user reports oh-my-claudecode/omc is broken, outdated, misconfigured, or not working after installation.'

Enumerate the concrete checks performed, e.g. 'Checks plugin version and cache, legacy hooks and curl-installed files, CLAUDE.md freshness, and Node/runtime prerequisites.'

Include natural user phrasings and synonyms ('troubleshoot', 'omc not working', 'setup broken') to broaden trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('oh-my-claudecode installation issues') and two concrete actions ('Diagnose and fix'), but gives no specifics on what is checked (hooks, plugin cache, CLAUDE.md, versions), so it matches the 'domain and 1-2 concrete actions, not comprehensive' anchor rather than the several-action anchor at 4.	3 / 5
Completeness	The 'what' is clear (diagnose and fix installation issues), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Relevant natural keywords are present ('diagnose', 'fix', 'installation issues', 'oh-my-claudecode'), but common user variations like 'broken', 'not working', 'troubleshoot', or 'omc' are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming the specific plugin 'oh-my-claudecode' gives a narrow trigger niche; only minor overlap risk exists with the closely related omc-setup skill, matching the 'mostly distinct' anchor.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/omc-doctor/SKILL.md
Commit: dc7ba1d

Reviewed: 3 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.