omc-plan
Strategic planning with optional interview workflow
30
23%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/plan/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is far too vague to be useful for skill selection. It names a broad domain ('strategic planning') without specifying concrete actions, target artifacts, or trigger conditions. Without a 'Use when...' clause or natural keywords, Claude would struggle to correctly select this skill from a pool of alternatives.
Suggestions
Specify concrete actions the skill performs, e.g., 'Creates strategic plans, conducts stakeholder interviews, generates SWOT analyses, and produces roadmap documents.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for a strategic plan, business strategy, roadmap, stakeholder interviews, or SWOT analysis.'
Clarify the domain niche to reduce conflict risk — is this for business strategy, product strategy, organizational planning? Be specific about the context.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is extremely vague. 'Strategic planning' is abstract and does not list any concrete actions. 'Optional interview workflow' hints at a capability but doesn't describe what it actually does. | 1 / 3 |
Completeness | The description barely addresses 'what' (strategic planning with interviews) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'strategic planning' and 'interview workflow' are generic and unlikely to match natural user queries. There are no specific trigger terms like file types, tools, or common user phrases. | 1 / 3 |
Distinctiveness Conflict Risk | 'Strategic planning' is extremely broad and could overlap with project management, business analysis, roadmapping, or many other skills. There is nothing to distinguish this skill's niche. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a thorough and well-structured workflow for strategic planning with multiple modes, but suffers significantly from verbosity and redundancy — the same rules (state lifecycle, no auto-execution, sequential agent calls) are restated 3-4 times across sections. The workflow clarity is excellent with clear sequencing, validation gates, and error recovery, but the sheer volume of content undermines its effectiveness as a skill file that competes for context window space. The lack of bundle files means all the complexity is crammed into one document.
Suggestions
Reduce redundancy by consolidating state lifecycle rules, execution boundary constraints, and sequential-agent requirements into single authoritative sections rather than repeating them in Execution_Policy, Steps, Tool_Usage, and Escalation_And_Stop_Conditions.
Extract the detailed consensus mode workflow (RALPLAN-DR specifics, state lifecycle, provider overrides) into a separate CONSENSUS.md bundle file and reference it from the main SKILL.md.
Remove the Why_This_Exists section entirely — Claude understands why planning before coding is valuable — and trim conversational explanations in examples (e.g., 'Why good/bad' annotations add little for Claude).
Provide concrete function signatures or JSON schemas for state_write, state_clear, and ralplan-state.json rather than describing them abstractly across multiple sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines with significant redundancy. The state lifecycle rules are repeated across Execution_Policy, Steps, Tool_Usage, and Escalation_And_Stop_Conditions. Concepts like 'don't batch questions' and 'explore before asking' are explained multiple times. The Why_This_Exists section explains obvious planning rationale Claude already knows. Many sections could be compressed by 50%+ without losing actionable content. | 1 / 3 |
Actionability | The skill provides specific tool invocations (Task, Skill, AskUserQuestion, explore agent), concrete CLI flags, and structured output formats. However, there is no executable code — the examples are conversational pseudocode rather than actual tool call syntax. Key details like state_write/state_clear function signatures and ralplan-state.json schema are referenced but never concretely defined. | 2 / 3 |
Workflow Clarity | The multi-step consensus workflow is clearly sequenced with numbered steps, explicit validation checkpoints (Critic approval gates), a bounded re-review loop (max 5 iterations), and detailed error recovery paths. The state lifecycle management includes explicit guidance on when to use state_write vs state_clear. The sequential constraint on Architect→Critic is called out multiple times with clear rationale. | 3 / 3 |
Progressive Disclosure | The skill uses XML sections (Purpose, Steps, Tool_Usage, Advanced) for some structure, and references external files like docs/shared/mode-selection-guide.md and docs/REFERENCE.md. However, no bundle files are provided to support these references, and the main body is a monolithic wall of text with substantial inline content that could be split into separate reference files (e.g., RALPLAN-DR details, state lifecycle rules, consensus mode specifics). | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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
Table of Contents
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.