ralplan

Consensus planning stage for Planner -> Architect -> Critic handoff to $ultragoal

Quality

61%

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 ./skills/ralplan/SKILL.md

Quality

Content

56%Weight 40%Scale 1-5

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

The body delivers a well-sequenced, validated consensus workflow with concrete commands, but is weighed down by repeated security-disclaimer padding and a monolithic structure that should be split into reference files. Tightening redundancy and externalizing detail would materially improve it.

Suggestions

Consolidate the repeated 'local evidence is not host-issued security authority' disclaimers into a single boundary section and reference it rather than restating.

Move the durable handoff contract and native role-routing rules into separate reference files (e.g., references/handoff-contract.md, references/role-routing.md) and link to them from the overview.

Pull the preflight and role-routing paragraphs out of the numbered workflow steps so the core sequence reads as a clean, uninterrupted checklist.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, repeating the 'local evidence is not host-issued security authority' disclaimer across several sections and using dense legalistic sentences that pad the token budget without adding actionable value.	2 / 5
Actionability	Provides concrete, executable commands ('$ralplan "task description"', 'omx ralplan run --task <arguments>', 'omx ralplan preflight --json') and explicit file-path conventions, with only minor gaps in full command syntax.	4 / 5
Workflow Clarity	The 8-step Planner->Architect->Critic workflow is clearly sequenced with explicit validation checkpoints and a max-5-iteration re-review feedback loop, but interleaved preflight/role-routing paragraphs interrupt the numbered flow and slightly muddy the sequence.	4 / 5
Progressive Disclosure	Section headers provide some structure, but with no bundle files the entire 150-line body is inline monolithic content; the role-routing rules and durable handoff contract details that belong in separate references are not split out.	3 / 5
	Total	13 / 20 Passed

Description

46%Weight 40%Scale 1-5

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 conveys a clear, specific 'what' but omits any 'when to use' trigger guidance and leans on internal jargon rather than natural user keywords. It is distinct within its ecosystem but would benefit from explicit invocation triggers.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g., 'Use when planning a task that needs sequential Planner, Architect, and Critic review before execution').

Replace or supplement internal role names with user-facing keywords users would actually say.

Expand the action list beyond a single composite handoff to show the discrete planning actions performed.

Dimension	Reasoning	Score
Specificity	Names the domain ('Consensus planning stage') and the concrete actor pipeline ('Planner -> Architect -> Critic handoff to $ultragoal'), but coverage is limited to a single composite action rather than a comprehensive action list.	3 / 5
Completeness	Provides a clear 'what' (consensus planning stage driving the Planner->Architect->Critic handoff) but no 'Use when...' clause or equivalent trigger guidance, so 'when' is missing and completeness is capped at 3.	3 / 5
Trigger Term Quality	Terms like 'Consensus planning', 'Planner', 'Architect', 'Critic', and 'handoff' are internal jargon; it lacks the natural phrases a user would actually say to invoke this skill.	2 / 5
Distinctiveness Conflict Risk	The niche is specific to this ecosystem's Planner/Architect/Critic->Ultragoal flow and unlikely to fire for unrelated skills, with only minor overlap risk against adjacent planning skills (autopilot, ralph, ultragoal).	4 / 5
	Total	12 / 20 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: skills/ralplan/SKILL.md
Commit: 1dcf513

Reviewed: 4 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.