ralplan

Alias for $plan --consensus

Quality

45%

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 ./plugins/oh-my-codex/skills/ralplan/SKILL.md

Quality

Content

40%

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

The body defines a clear, well-sequenced consensus workflow with strong validation gates, but it is verbose and monolithic. Inlining role-routing preflight rules and goal-mode follow-up guidance hurts both token efficiency and progressive disclosure.

Suggestions

Split the long tangential sections (native role-routing preflight/rule, pre-execution gate tables, goal-mode follow-up suggestions) into references/ files and link to them from the body.

Trim explanatory prose about runtime mechanics (e.g. why agents waste cycles on vague requests) to lean directives, assuming Claude's competence.

Specify the durable handoff record as a concrete file path and minimal required JSON shape rather than a descriptive list, so the guidance is directly executable.

Dimension	Reasoning	Score
Conciseness	The body is verbose and padded with explanatory prose (e.g. multi-paragraph 'Native role-routing preflight' and 'Native role-routing rule' digressions) that explains runtime mechanics rather than giving lean instructions.	1 / 3
Actionability	It provides concrete command invocations and a numbered consensus workflow, but several code blocks are illustrative aliases rather than directly executable commands, and key details (e.g. exact handoff-record path/format) are described rather than specified.	2 / 3
Workflow Clarity	The Planner -> Architect -> Critic loop is clearly sequenced with explicit validation checkpoints, a bounded re-review loop (max 5 iterations), and a stop rule requiring ordered role-specific subagent approval.	3 / 3
Progressive Disclosure	The skill is a single monolithic SKILL.md (~207 lines) with no references/, scripts/, or assets/ bundle files and no one-level-deep pointers, so substantial material that should be split (role-routing rules, gate tables, goal-mode guidance) is inlined.	1 / 3
	Total	7 / 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 correctly identifies the skill as a consensus-planning alias and names the agents involved, but it is terse and lacks explicit 'when to use' guidance. It is borderline-adequate rather than strong.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'plan by consensus', 'multi-agent planning', or 'review the plan before execution'.

Expand the action list beyond the single alias reference to enumerate the concrete capabilities (iterative Planner/Architect/Critic consensus, RALPLAN-DR deliberation, durable handoff).

Include common user variations like 'planning' and 'review the plan' so the trigger terms match what a user would naturally say.

Dimension	Reasoning	Score
Specificity	The description states it is an 'Alias for $plan --consensus' and 'triggers iterative planning with Planner, Architect, and Critic agents', naming the domain and one concrete action but offering no comprehensive enumeration of capabilities.	2 / 3
Completeness	It answers 'what does this do' (alias for $plan --consensus) but provides no explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	It surfaces the natural term 'consensus' and the command token '$plan', but omits common variations users might say (e.g. 'planning', 'review the plan', 'multi-agent plan').	2 / 3
Distinctiveness Conflict Risk	'Alias for $plan --consensus' is a narrow niche that is unlikely to fire for unrelated skills, but its brevity means it could still overlap with sibling planning skills and lacks a distinctive standalone trigger.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Yeachan-Heo/oh-my-codex
Path: plugins/oh-my-codex/skills/ralplan/SKILL.md
Commit: 435d4a9

Reviewed: 2 days 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.