ultragoal

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

Quality

80%

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/ultragoal/SKILL.md

Quality

Content

96%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 is an exemplary operational skill: lean, command-complete, with a clearly sequenced execute loop, explicit validation checkpoints, error-recovery paths, and a rigorous final gate. The only minor weakness is its dependency on an external AGENTS.md anchor reference that is not part of the skill bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense, purely operational bullets and commands with zero concept explanation or padding (e.g. "Ordinary prose does not mutate the plan; repeated structured directives dedupe."), assuming Claude's competence throughout — every token earns its place.	5 / 5
Actionability	Every operation has copy-paste-ready commands with full flags: create-goals with all four input modes, checkpoint with --goal-id/--status/--evidence/--codex-goal-json, steer with enumerated supported kinds, record-review-blockers, and the exact `omx state write` JSON payload — covering create, execute, steer, checkpoint, and exit cases.	5 / 5
Workflow Clarity	The execute loop is numbered with an explicit termination condition (`omx ultragoal status` reporting all goals complete), validation is explicit (audit each story against real artifacts and verification evidence; the 5-step final gate), and error recovery is built in (--status blocked\|failed, --retry-failed, and 'If review or invariant proof is not clean, do not update the Codex goal').	5 / 5
Progressive Disclosure	Sections are well-organized and the body is appropriately compact, with one-level-deep, clearly signaled references ("Read AGENTS.md#durable-runtime-invariants-canonical-ssot", "see the Team skill for the bridge details"). However, no bundle files exist and the AGENTS.md anchor points outside the skill bundle where its presence cannot be assumed — a minor organization gap versus the fully self-contained anchor 5.	4 / 5
	Total	19 / 20 Passed

Description

53%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 states a specific, niche capability in third person, but it is missing any explicit 'when to use' trigger guidance and leans on internal jargon rather than natural user phrasing. It is serviceable but below the quality of the good examples, which pair a concrete what with a concrete when.

Suggestions

Add an explicit 'Use when...' clause with natural triggers, e.g. 'Use when the user mentions ultragoal, goal planning, creating or completing multi-goal plans, or executing Codex goals sequentially.'

Replace internal jargon with synonyms users would actually say: mention 'goal planning', 'track goals', 'execute goals', and the tool command names (create-goals, complete-goals) alongside 'Codex goal mode'.

Broaden the action list beyond 'create and execute' to name the other concrete operations (checkpoint progress, steer/re-plan blocked stories, run final quality gates) for fuller capability coverage.

Dimension	Reasoning	Score
Specificity	"Create and execute" are two concrete actions on a named domain ("durable repo-native multi-goal plans", "Codex goal mode artifacts"), matching the anchor for 1-2 concrete actions without comprehensive coverage; it does not list several specific actions needed for a 4.	3 / 5
Completeness	The description clearly states what the skill does but has no 'Use when...' clause or equivalent trigger guidance, which per the guidelines caps completeness at 3; it is not a 2 because the 'what' is specific rather than vague.	3 / 5
Trigger Term Quality	"multi-goal plans", "Codex", and "goal mode" are relevant keywords, but "repo-native" and "goal mode artifacts" are internal jargon and common natural phrasings (goal planning, track goals, execute goals) are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"Codex goal mode artifacts" carves a distinct niche with low conflict risk, but the absence of unique trigger phrases leaves minor overlap with generic planning/roadmap skills, matching the 'mostly distinct; minor overlap risk' anchor rather than the fully distinct 5.	4 / 5
	Total	13 / 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/ultragoal/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.