ultrawork

Parallel execution engine for high-throughput task completion

Quality

52%

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/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 protocol with concrete examples, a sequenced workflow, and verification checkpoints. Its main weakness is redundancy in restating the mode hierarchy and reliance on external doc references that are not part of the skill bundle.

Suggestions

Consolidate the ralph/autopilot/ultrawork relationship into a single section (e.g. keep only the Advanced diagram) to remove the repetition across Purpose, Do_Not_Use_When, and Why_This_Exists.

Either inline the essential tier-selection guidance from agent-tiers.md or confirm the reference path resolves within the skill bundle so the 'Read agent reference' step is self-contained.

Tighten the 'Parallel session caveats' section, which mixes implementation detail that may not be needed on every invocation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the ralph/autopilot/ultrawork relationship is restated across Purpose, Do_Not_Use_When, Why_This_Exists, and Advanced, which could be consolidated.	3 / 5
Actionability	Tool_Usage and Examples provide concrete, copy-pasteable Task() calls with explicit model and run_in_background parameters, plus Good/Bad contrasts; only minor gaps remain.	4 / 5
Workflow Clarity	A clear 10-step sequence is paired with an explicit verification step (step 10), a Final_Checklist, and Escalation_And_Stop_Conditions, so the batch-operation cap does not apply; the validation is explicitly 'lightweight' with a minimal fix-retry loop.	4 / 5
Progressive Disclosure	Content is organized into clearly labeled sections with one-level references (agent-tiers.md, REFERENCE.md), but those referenced files are external repo docs not present in the skill bundle, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

37%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 is concise and identifies the parallelism niche, but it is generic: it lacks concrete actions, natural trigger terms, and any explicit 'when to use' guidance. It reads more as a tagline than a trigger-ready skill description.

Suggestions

Add concrete actions the skill performs, e.g. 'Fires multiple agents simultaneously and routes each to the right model tier'.

Append a 'Use when...' clause with natural triggers such as 'Use when the user says ulw/ultrawork or wants independent tasks run in parallel'.

Replace the jargon 'high-throughput task completion' with plain user-facing language like 'running many independent tasks at once'.

Dimension	Reasoning	Score
Specificity	The phrase 'Parallel execution engine' names the domain, but the only stated action 'high-throughput task completion' is generic and abstract with no concrete capabilities listed.	2 / 5
Completeness	There is a clear 'what' (parallel execution engine) but no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	'Parallel execution' is one relevant keyword, but 'high-throughput task completion' is technical jargon rather than a phrase users naturally say; the natural triggers 'ulw'/'ultrawork' documented in the body are absent from the description.	2 / 5
Distinctiveness Conflict Risk	'Parallel execution engine' identifies a niche, but 'high-throughput task completion' is broad enough to overlap with general task-delegation or execution skills.	3 / 5
	Total	10 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/ultrawork/SKILL.md
Commit: 5aa678c

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.