omc-setup

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

Quality

55%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/omc-setup/SKILL.md

Quality

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 specific tool (oh-my-claudecode) and high-level actions (install/refresh), giving it reasonable distinctiveness. However, it lacks a 'Use when...' clause, which significantly hurts completeness, and the actions described are not granular enough to fully convey the skill's capabilities.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to install, set up, update, or refresh oh-my-claudecode or mentions oh-my-claudecode configuration.'

Expand the specific actions beyond 'install or refresh' — describe what the canonical setup flow entails (e.g., 'configures plugins, sets up npm dependencies, initializes local development environment').

Include natural trigger term variations users might say, such as 'set up', 'configure', 'update', 'reinstall', or 'omc'.

Dimension	Reasoning	Score
Specificity	Names the domain (oh-my-claudecode) and some actions ('install or refresh'), mentions setup types ('plugin, npm, and local-dev setups'), but doesn't list concrete sub-actions beyond install/refresh.	2 / 3
Completeness	Describes what it does (install/refresh oh-my-claudecode) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric should cap completeness at 2, and the 'what' is also only partially described, placing this at 1.	1 / 3
Trigger Term Quality	Includes relevant terms like 'install', 'oh-my-claudecode', 'plugin', 'npm', 'local-dev', but misses common user variations like 'setup', 'configure', 'update', or abbreviations users might naturally say.	2 / 3
Distinctiveness Conflict Risk	Very specific to 'oh-my-claudecode' which is a distinct, named tool/project. Unlikely to conflict with other skills due to the unique product name and specific setup context.	3 / 3
	Total	8 / 12 Passed

Implementation

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability and workflow clarity with concrete commands, clear phase sequencing, and robust error recovery (resume detection, interrupt handling). Progressive disclosure is well-implemented by delegating to phase files. However, the content is significantly bloated — the help text block alone is ~30 lines of duplicated information, the plugin root resolution is an enormous inline script, and the 'Keeping Up to Date' section restates earlier content.

Suggestions

Remove or drastically shorten the Help Text block — it restates information already present in the Flag Parsing and Phase Execution sections; consider moving it to a separate HELP.md file

Move the large inline Node.js one-liner for Active Plugin Root Resolution into a referenced script file (e.g., scripts/resolve-plugin-root.sh) and just call it

Remove the 'Keeping Up to Date' section entirely — it repeats the flag descriptions and Pre-Setup Check behavior already documented above

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~180+ lines. The help text block is essentially duplicated information that restates what the workflow already describes. The 'Keeping Up to Date' section repeats flag explanations already covered. The inline Node.js one-liner for plugin root resolution is massive and could be referenced as a script. Much of this content could be cut in half without losing clarity.	1 / 3
Actionability	The skill provides fully executable bash commands, specific file paths, concrete flag parsing logic, and exact scripts to run. The workflow is copy-paste ready with real commands like `bash "${OMC_SETUP_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/setup-claude-md.sh" local` and includes specific jq queries for config checking.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced with explicit phases (1-4), resume detection with state checking, pre-setup checks, flag-based branching, and graceful interrupt handling. Validation checkpoints exist (checking if already configured, resume detection prompts) and there are clear feedback loops for user decisions.	3 / 3
Progressive Disclosure	The skill appropriately delegates detailed phase instructions to separate files (phases/01-install-claude-md.md through phases/04-welcome.md) and references external scripts. The main SKILL.md serves as an orchestrator/overview with clear one-level-deep references to phase files. Navigation is well-signaled.	3 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 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: 3e94567

Reviewed: about 22 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.