ultragoal

Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

Quality

65%

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/ultragoal/SKILL.md

Quality

Content

85%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 content is highly actionable and exceptionally well-sequenced with robust validation for a durable state workflow, but it is monolithic with no progressive disclosure via separate reference files.

Suggestions

Move the large inline quality-gate JSON schema and detailed steering API into separate reference files (e.g., quality-gate.json, STEERING.md) linked one level deep from the body.

Consider extracting the phase/HUD contract details into a reference file to shorten the main SKILL.md overview.

Add bundle files under references/ or scripts/ for reusable artifacts so progressive disclosure has an actual structure to navigate.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's knowledge (no padded explanations of what Codex or goals are); length reflects genuine multi-phase complexity with only minor areas that could be tightened.	4 / 5
Actionability	Fully executable guidance throughout: exact shell commands with flags, precise get_goal/create_goal/update_goal call sequences, and a complete copy-paste-ready JSON quality-gate schema.	5 / 5
Workflow Clarity	Numbered sequences (the 11-step complete-goals loop and 7-step final gate) have explicit validation checkpoints, Codex snapshot reconciliation, rerun-after-cleaner feedback loops, and blocked/failed/retry recovery paths.	5 / 5
Progressive Disclosure	Section structure is reasonable, but no bundle files exist and all detail (the full quality-gate JSON schema, steering API, phase contracts) is inlined in one file rather than split into one-level-deep references.	3 / 5
	Total	17 / 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 clearly states what the skill does but relies on technical jargon and omits any 'when to use' trigger guidance, which limits trigger-term quality and completeness.

Suggestions

Add a 'Use when...' clause with natural trigger phrases (e.g., 'Use when the user asks for durable multi-goal planning or sequential execution over Codex /goal') so triggers live in the description, not just the body.

Replace jargon like 'Codex goal mode artifacts' and 'repo-native' with terms users would naturally say.

Expand the action list beyond 'Create and execute' to name more concrete capabilities (e.g., checkpoint, steer, audit).

Dimension	Reasoning	Score
Specificity	Names the domain ('durable repo-native multi-goal plans over Codex goal mode artifacts') with two concrete actions ('Create and execute'), but the action vocabulary is limited and not comprehensive.	3 / 5
Completeness	It has a clear 'what' but no 'Use when...' or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	The description uses technical jargon ('Codex goal mode artifacts', 'repo-native') rather than natural phrases a user would say; the natural trigger terms only appear in the body, not the description.	2 / 5
Distinctiveness Conflict Risk	The niche is specific (Codex goal mode multi-goal planning) and mostly distinct with only minor overlap risk against closely related planning skills.	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: plugins/oh-my-codex/skills/ultragoal/SKILL.md
Commit: e94437f

Reviewed: 8 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.