omc-setup

Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups from the canonical setup flow

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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, highly actionable setup orchestrator with excellent progressive disclosure into per-phase files. Its main weaknesses are redundancy (the Help Text and 'Keeping Up to Date' sections duplicate earlier flag/mode content) and the absence of visible validation for the destructive CLAUDE.md overwrites, which caps workflow clarity despite otherwise clear sequencing and checkpoints.

Suggestions

Add an explicit validation/verification checkpoint after the destructive CLAUDE.md write/backup (e.g. confirm the backup file exists and the new CLAUDE.md is non-empty before proceeding) to lift workflow_clarity above 2.

De-duplicate the Help Text block and 'Keeping Up to Date' section against the 'Flag Parsing' section, or collapse one into a pointer, to reduce redundancy and improve conciseness.

Consider moving the dense inline plugin-root node one-liner into a referenced script so the overview stays lean while keeping the resolution logic one level deep.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient orchestration guidance rather than basic-concept padding, but the ~48-line Help Text block and the 'Keeping Up to Date' section restate flag/mode information already covered in 'Flag Parsing', so it 'could be tightened' — matching score 2 rather than the lean every-token-earns-its-place score 3.	2 / 3
Actionability	It provides fully executable commands (the plugin-root node one-liner, repair-plugin-cache.mjs, jq-based pre-setup checks, setup-progress.sh, setup-claude-md.sh) with concrete env-var fallbacks and specific AskUserQuestion prompts with enumerated options, matching 'fully executable code/commands; copy-paste ready.'	3 / 3
Workflow Clarity	There is a clear sequence with explicit checkpoints (Pre-Setup Check, Resume Detection, Force Override) and decision feedback loops, but the workflow performs destructive writes (overwriting/backup of ~/.claude/CLAUDE.md) with no visible validation/verification step in this file — that validation is delegated to unseen phase files, so per the guideline missing validation in destructive operations caps this at 2.	2 / 3
Progressive Disclosure	The SKILL.md acts as a clear orchestrator overview pointing to well-signaled one-level-deep references (phases/01-install-claude-md.md through 04-welcome.md and several scripts/), with the multi-phase work appropriately split out rather than dumped inline, matching 'clear overview with well-signaled one-level-deep references; content appropriately split.'	3 / 3
	Total	10 / 12 Passed

Description

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 states a clear, distinct purpose around a specific product but stops short of a great trigger description: it lacks an explicit 'Use when...' clause and omits natural user terms like 'update' or 'configure' in favor of jargon. It is solid but improvable, with the weighted score pulled down by the high-weight completeness and trigger dimensions sitting at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to install, update, configure, or repair oh-my-claudecode (plugin, npm, or local-dev).'

Replace jargon/flavor ('canonical setup flow', 'local-dev') with natural user terms ('update', 'set up', 'configure', 'reinstall') to broaden trigger coverage.

Consider adding a third concrete action verb (e.g. 'configure' or 'repair') to move specificity from a two-verb list toward a comprehensive multi-action description.

Dimension	Reasoning	Score
Specificity	Quotes 'Install or refresh oh-my-claudecode for plugin, npm, and local-dev setups' — it names concrete actions (install, refresh) and a clear domain, but only two verbs rather than a comprehensive list of multiple specific actions, matching the score-2 anchor ('Processes PDF files and extracts content') and falling short of the score-3 multi-action example.	2 / 3
Completeness	Clearly states the 'what' (install/refresh OMC for the listed setups) but has no explicit 'Use when...' trigger clause, so the 'when' is only implied; per the guideline a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant keywords ('install', 'setup', 'plugin', 'npm') but misses common natural variations a user would say ('update', 'configure', 'set up', 'repair') and leans on jargon ('canonical setup flow', 'local-dev'), matching 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	It names a specific product (oh-my-claudecode) and a specific operation (install/refresh setup), giving it a clear niche unlikely to trigger for unrelated skills, matching 'clear niche with distinct triggers; unlikely to conflict.'	3 / 3
	Total	9 / 12 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
Commit: 6c59219

Reviewed: about 4 hours 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.