omc-plan

Strategic planning with optional interview workflow

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

55%

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

The body is well-sequenced with strong validation checkpoints and concrete agent/state commands, but it is a monolithic 280-line document with significant repetition across sections and no bundle files to offload reference material. It would benefit from extracting schemas and advanced guidance into referenced files.

Suggestions

Split the RALPLAN-DR summary format, ADR section spec, and Question/Review classification tables into separate reference files (e.g. references/ralplan-dr.md) and link to them one level deep.

De-duplicate the repeated state-lifecycle and planning/execution-boundary reminders — state them once authoritatively and reference that section elsewhere.

Move the Deprecation Notice and Advanced design-option-presentation guidance to a separate advanced.md to reduce inline token load.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence without explaining basic concepts, but the body is heavily padded with repeated CRITICAL state-lifecycle and approval-boundary reminders across Execution_Policy, Steps, Tool_Usage, and Final_Checklist that could be tightened.	2 / 3
Actionability	Provides concrete agent Task invocations, AskUserQuestion gates, and specific state_write/state_clear commands, but execution paths (ralph/team) are named by skill rather than given executable code, and several steps are directive prose rather than copy-paste-ready commands.	2 / 3
Workflow Clarity	Multi-step processes (interview, direct, consensus, review) are explicitly numbered and sequenced with validation gates, a max-5-iteration re-review loop, and explicit stop/state-clear checkpoints for destructive/handoff operations.	3 / 3
Progressive Disclosure	No bundle files exist in references/, scripts/, or assets/, yet the body is a 280-line monolithic wall containing inline ADR formats, RALPLAN-DR schemas, deprecation notices, and repeated reference tables that should be split into separate referenced files.	1 / 3
	Total	8 / 12 Passed

Description

50%

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 concise and names the domain, but it omits an explicit 'Use when' trigger clause and only surfaces 'plan'/'planning' as a natural keyword, leaving its distinctiveness weak. It reads more like a label than a trigger-rich description.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases such as 'plan this', 'review this plan', 'let's plan', or 'ralplan'.

List concrete actions (interview for requirements, generate plans, run Planner/Architect/Critic consensus, review existing plans) rather than relying on 'optional interview workflow'.

Distinguish the skill from execution skills (e.g. 'produces plans only; does not implement code') to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain (strategic planning) and the interview workflow feature, but lists only one concrete action ('planning') with the rest implied by 'optional interview workflow'; not a comprehensive enumeration of actions.	2 / 3
Completeness	States what the skill does (planning) but has no explicit 'Use when...' trigger clause; the 'when' is only implied by the domain, which the rubric caps at 2.	2 / 3
Trigger Term Quality	Contains the natural term 'plan'/'planning' that users say, but lacks common phrasings like 'review this plan' or 'consensus'/'ralplan' that the body reveals as triggers, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	'Strategic planning' has a recognizable niche but the description is generic enough that it could overlap with other planning/exec skills; distinct triggers are absent.	2 / 3
	Total	8 / 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.