ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
62
42%
Does it follow best practices?
Impact
98%
1.19xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ralplan/SKILL.mdQuality
Discovery
7%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 heavily jargon-laden and fails to communicate concrete actions, natural trigger terms, or explicit usage guidance. It reads like an internal implementation note rather than a skill description designed to help Claude select the right skill. The lack of a 'Use when...' clause and absence of user-facing language make it very difficult for Claude to appropriately match this skill to user requests.
Suggestions
Replace jargon like 'auto-gates', 'entrypoint', and 'ralph/autopilot' with plain language describing what the skill actually does (e.g., 'Validates and clarifies ambiguous team task requests before executing them').
Add an explicit 'Use when...' clause with natural trigger terms users would say, such as 'Use when a user submits a vague or underspecified team task, multi-agent request, or automated workflow that needs clarification before proceeding'.
List 2-3 specific concrete actions the skill performs, such as 'Prompts for missing details, confirms scope with the user, and routes clarified requests to the appropriate execution workflow'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, jargon-heavy language like 'auto-gates' and 'consensus planning entrypoint' without listing any concrete actions the skill performs. There are no specific capabilities described. | 1 / 3 |
Completeness | The 'what' is extremely vague ('auto-gates vague requests') and there is no explicit 'when' clause or trigger guidance. It's unclear what the skill actually does or when Claude should select it. | 1 / 3 |
Trigger Term Quality | The terms 'ralph', 'autopilot', and 'consensus planning' are internal jargon unlikely to match natural user language. 'Team requests' is somewhat natural but too generic. Users would not naturally say 'auto-gates' or 'entrypoint'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of specific terms like 'ralph/autopilot' and 'consensus planning' gives it some niche identity, but the vague nature of 'team requests' and 'execution' could overlap with other planning or orchestration skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent workflow clarity and actionability — the consensus planning loop is precisely specified with clear sequencing, validation checkpoints, and error recovery. The pre-execution gate section is thorough with good examples but adds significant length; the overall document could be more concise by trimming rationale explanations and consolidating redundant sections. Progressive disclosure would benefit from splitting the gate documentation into a separate reference file.
Suggestions
Trim the 'Why the Gate Exists' rationale section — Claude doesn't need motivation for following instructions; keep only the behavioral rules.
Consider splitting the Pre-Execution Gate section (good/bad prompts, signal table, troubleshooting) into a separate reference file like `docs/gate-reference.md` to keep the main skill leaner.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some redundancy (e.g., the usage section shows the command twice for interactive mode, the gate explanation is verbose with extensive tables and examples that could be more compact). Some sections like 'Why the Gate Exists' explain rationale Claude doesn't need. | 2 / 3 |
Actionability | The skill provides highly concrete guidance: exact command syntax, specific flags with precise behavior descriptions, a detailed step-by-step consensus workflow with numbered steps, clear good/bad prompt examples in a table, concrete signal types for gate detection, and specific troubleshooting solutions. The workflow is fully specified with explicit sequencing constraints. | 3 / 3 |
Workflow Clarity | The multi-step consensus workflow is clearly sequenced (steps 0-8) with explicit validation checkpoints (Critic APPROVE/ITERATE/REJECT verdicts), a re-review loop with max iterations and fallback behavior, sequential ordering constraints (steps 3-4 must be sequential), and clear branching for interactive vs non-interactive modes. The end-to-end flow example further reinforces the sequence. | 3 / 3 |
Progressive Disclosure | The skill references external files like `docs/company-context-interface.md` and other skills (`oh-my-claudecode:plan`, `oh-my-claudecode:team`, `oh-my-claudecode:ralph`), but the main file is quite long and monolithic. The gate documentation, troubleshooting, and signal tables could potentially be split into a separate reference file. However, no bundle files are provided to verify references, and the inline content is reasonably well-organized with clear headers. | 2 / 3 |
Total | 10 / 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
679b418
- 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.