omc-doctor

Diagnose and fix oh-my-claudecode installation issues

Quality

66%

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

75%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 content is highly actionable with fully executable diagnostic and fix commands, a clear sequenced workflow, and proper validation/confirmation around destructive operations. Its main weakness is token efficiency from repeated version-check scripts and a few explanatory sentences that could be tightened.

Suggestions

De-duplicate the cross-platform version-check node script (Steps 1, 4, 6) by defining it once and reusing, or move the shared snippet to a bundled script under scripts/.

Add an explicit post-fix re-verification step (re-run the diagnostics and confirm all checks return OK before telling the user to restart) to close the workflow feedback loop.

Trim explanatory prose such as the Ralph rationale in Step 5 to the bare actionable instruction, keeping only what Claude would not already infer.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bash/node commands and diagnosis bullets without explaining concepts Claude already knows, but the cross-platform version-check node one-liner is repeated across Steps 1, 4, and 6 and a few explanatory sentences could be trimmed, fitting 'mostly efficient but could be tightened' rather than the lean 4.	3 / 5
Actionability	Every step provides copy-paste-ready executable commands (bash, node -e one-liners, WebFetch) with concrete diagnosis logic and specific auto-fix commands, fully covering the common diagnostic and repair cases.	5 / 5
Workflow Clarity	Seven steps are clearly sequenced with per-step OK/WARN/CRITICAL diagnosis checkpoints and user-confirmed, backup-offered destructive fixes, satisfying the destructive-operation validation requirement; it sits at 4 rather than 5 because there is no explicit re-run/re-verify loop after fixes are applied.	4 / 5
Progressive Disclosure	The skill is self-contained with no bundle files and is well-organized into clear sections (Task, Steps 1-7, Report Format, Auto-Fix, Post-Fix); at over 50 lines with long inline lists of known plugin names it is well-structured but not the ideal 'overview pointing to one-level-deep references' of a 5.	4 / 5
	Total	16 / 20 Passed

Description

57%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 specific to a named plugin and clearly states what the skill does, but it omits any explicit 'when to use' trigger guidance and lacks synonym coverage of natural user phrasing. Adding a 'Use when...' clause would lift completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when oh-my-claudecode is not working, broken, or showing installation/setup errors.'

Include natural synonyms users would say ('installation problems', 'setup issues', 'not working', 'broken') to broaden trigger-term coverage.

Optionally name a concrete fix action beyond 'fix' (e.g. 'remove legacy hooks, clear stale cache') to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('oh-my-claudecode installation issues') and two concrete actions ('Diagnose and fix'), matching the anchor for 1-2 concrete actions without comprehensive coverage; it is below 4 because only two high-level verbs are given rather than several specific actions.	3 / 5
Completeness	A clear 'what' is present ('Diagnose and fix ... installation issues') but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3; it cannot reach 4 without an explicit 'when'.	3 / 5
Trigger Term Quality	Relevant keywords exist ('diagnose', 'fix', 'installation issues', 'oh-my-claudecode') but common user variations like 'not working', 'broken', 'problems', or 'errors' are missing, fitting the 'some relevant keywords but missing synonyms' anchor rather than the fuller coverage of 4.	3 / 5
Distinctiveness Conflict Risk	The description is tied to a specific named plugin ('oh-my-claudecode') and a narrow task (installation issues), giving it a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	14 / 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: 5aa678c

Reviewed: 8 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.