ultrawork

Parallel execution engine for high-throughput task completion

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/ultrawork/SKILL.md

Quality

Content

73%

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

The content is a well-structured, actionable meta-workflow with clear sequencing, verification checkpoints, and a clean single reference; its main weakness is verbosity and some cross-section redundancy.

Dimension	Reasoning	Score
Conciseness	The body is operational and does not explain concepts Claude already knows, but it is lengthy and repetitive — e.g., Ralph/persistence ownership is restated across Escalation_And_Stop_Conditions and the Advanced section.	2 / 3
Actionability	It provides copy-paste-ready `omx state` commands, explicit tier routing, and concrete good/bad examples, though a fair portion of the execution guidance remains abstract decision prose.	2.5 / 3
Workflow Clarity	The 8-step sequence is clearly ordered with acceptance criteria defined before execution, explicit verification checkpoints (build/typecheck, affected tests, manual QA), a final checklist, and stop/escalation rules.	3 / 3
Progressive Disclosure	It signals one real one-level-deep reference (references/agent-tiers.md) clearly in Step 1 and Execution_Policy, though the main SKILL.md itself is fairly dense and could split some inline material.	2.5 / 3
	Total	10 / 12 Passed

Description

17%

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 is too abstract and jargon-heavy to function as a reliable trigger: it states a vague capability but gives no concrete actions and no usage triggers, leaving it indistinct from related execution skills.

Suggestions

Replace 'high-throughput task completion' with concrete action verbs (e.g., 'Runs independent tasks in parallel lanes, delegates agent work by tier, and gathers lightweight verification evidence').

Add an explicit 'Use when...' clause with natural trigger terms a user would actually say (e.g., 'Use when the user says ulw/ultrawork, asks to run independent tasks in parallel, or wants concurrent execution without a durable goal workflow').

Sharpen distinctiveness by contrasting the trigger against siblings (e.g., 'Use for parallel execution without durable goal tracking — for durable tracking use ultragoal').

Dimension	Reasoning	Score
Specificity	It names a domain ('Parallel execution engine') but lists no concrete actions, and 'high-throughput task completion' is vague buzzword phrasing rather than specific capability verbs.	1.5 / 3
Completeness	A weak 'what' is present but the 'when' is entirely missing, and the missing explicit trigger guidance caps completeness below 2 per the rubric.	1.5 / 3
Trigger Term Quality	There are no natural user-facing keywords or 'Use when...' triggers; 'Parallel execution engine for high-throughput task completion' reads as technical jargon a user would not naturally say.	1 / 3
Distinctiveness Conflict Risk	'Parallel execution' signals a niche, but 'task completion' is generic and would overlap with the sibling modes (ultragoal, team) described in the body.	1.5 / 3
	Total	5.5 / 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/ultrawork/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.