omc-setup

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

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

85%

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 well-structured, highly actionable orchestration skill with a clear multi-phase workflow, validation checkpoints, and clean progressive disclosure into phase files and scripts. Its main weakness is moderate verbosity from duplicated flag/usage content across the Help Text, Flag Parsing, and Keeping Up to Date sections.

Suggestions

De-duplicate flag/usage information: the Help Text block and 'Keeping Up to Date' repeat content already in 'Flag Parsing' — consider a single canonical flag table the Help Text references.

Trim the Help Text USAGE/EXAMPLES lines that restate the Flag Parsing bullets to reduce token cost without losing clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept explanations Claude already knows, but the large Help Text block and the 'Keeping Up to Date' section repeat flag/usage information already present in 'Flag Parsing', so it could be tightened.	2 / 3
Actionability	Provides fully executable bash commands with concrete env-var-expanded paths, jq-based config checks, exact AskUserQuestion prompts and options, and copy-paste-ready script invocations.	3 / 3
Workflow Clarity	Sequences the full flow (Pre-Setup Check -> Resume Detection -> Phases 1-4) with explicit validation checkpoints (coordinator response/exit-status validation, fail-closed protocol checks, resume detection) and feedback loops for interrupts.	3 / 3
Progressive Disclosure	Acts as a clear overview that delegates each phase to a separate one-level-deep phase file, offloads HUD setup to the 'hud' skill, and routes script work to setup scripts, with well-signaled navigation and no nested reference chains.	3 / 3
	Total	11 / 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 is specific to a named product and names concrete setup channels, but it lacks an explicit 'Use when' trigger clause and could cover more natural trigger terms like 'configure' or 'update'. It is solid but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. 'Use when installing, updating, repairing, or reconfiguring oh-my-claudecode via plugin, npm, or local-dev.'

Broaden trigger terms to include 'configure', 'update', and 'repair' so Claude matches more natural user phrasing.

Expand the action list beyond 'install or refresh' to reflect the full scope (e.g. configure, repair) the body supports.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Install or refresh') and three setup domains ('plugin, npm, and local-dev setups'), but the action set is limited to two verbs and 'canonical setup flow' is vague, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It states what the skill does ('Install or refresh oh-my-claudecode') but has no explicit 'Use when...' trigger clause, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Includes relevant terms a user might say ('oh-my-claudecode', 'plugin', 'npm', 'local-dev', 'setup') but omits common variations like 'configure', 'update', or 'repair' that the body itself mentions.	2 / 3
Distinctiveness Conflict Risk	Targets a specific named product ('oh-my-claudecode') across named distribution channels, giving it a clear niche unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/omc-setup/SKILL.md
Commit: 590fb98

Reviewed: 1 day 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.