ultrawork

Parallel execution engine for high-throughput task completion

Quality

56%

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

67%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 a well-structured, actionable orchestration skill with explicit state-management commands, acceptance-criteria discipline, and a closing evidence checklist. Its main weaknesses are redundancy across the mode-boundary sections and a softer fix-retry feedback loop.

Suggestions

Consolidate the repeated mode-boundary material in Do_Not_Use_When, Escalation_And_Stop_Conditions, and Advanced into one canonical section to reduce token cost.

Add an explicit validate->fix->retry loop in Steps or Escalation for failed builds/tests before escalating to the user.

Move the Relationship-to-Other-Modes diagram into a reference file and keep a brief pointer in SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's intelligence and avoids basic-concept padding, but mode boundaries are restated across Do_Not_Use_When, Escalation_And_Stop_Conditions, and the Advanced section, creating clear tightening opportunities.	3 / 5
Actionability	It provides concrete executable commands (omx state write --input '...' --json), explicit tier guidance, and rules like run_in_background: true for >30s ops, with only minor gaps such as the <now> placeholder and an unshown delegation command form.	4 / 5
Workflow Clarity	Steps 1-8 are clearly sequenced with validation checkpoints (acceptance criteria before execution, evidence at close) plus a Final_Checklist, but the validate->fix->retry feedback loop is weak, modeled mostly as escalate-if-repeated rather than fix-and-retry.	4 / 5
Progressive Disclosure	Sections are well-organized and the single reference (references/agent-tiers.md) is one level deep, clearly signaled, and verified to exist, but the body is somewhat monolithic and the Advanced mode-relationship section could be offloaded to a reference.	4 / 5
	Total	15 / 20 Passed

Description

45%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 what the skill is at a high level but lacks concrete actions, natural trigger phrases, and an explicit when-to-use clause. It is recognizable but not distinctive enough to confidently win routing over sibling execution skills.

Suggestions

Add concrete actions, e.g. 'Fans out independent agent lanes, runs background evidence checks in parallel, and delegates with explicit model tiers.'

Append a 'Use when...' clause with natural triggers, e.g. 'Use when the user says ulw/ultrawork or wants independent tasks run in parallel without a durable goal workflow.'

Differentiate from siblings in the description itself, e.g. 'for lightweight parallel execution without tmux coordination or durable ledgers (use team/ultragoal for those).'

Dimension	Reasoning	Score
Specificity	The phrase 'Parallel execution engine for high-throughput task completion' names the domain but offers only generic, abstract action framing rather than concrete actions like fanning out agent lanes or background evidence gathering.	2 / 5
Completeness	It gives a clear 'what' (a parallel execution engine) but no 'when' or Use-when trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	'Parallel execution' is a natural keyword users would say, but 'high-throughput task completion' is jargon and common synonyms/variations (ulw, parallelize, fan out) are absent.	3 / 5
Distinctiveness Conflict Risk	It signals a parallelism niche but does not disambiguate from sibling execution skills (team, ultragoal) that also handle parallel work, so overlap risk remains.	3 / 5
	Total	11 / 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/ultrawork/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.