ultrawork

Parallel execution engine for high-throughput task completion

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is action-oriented and well-sequenced with concrete Task-delegation patterns, tier routing, and verification checkpoints. Its main weaknesses are redundancy across the Execution_Policy/Steps/Tool_Usage sections and a monolithic structure with unbundled doc references rather than true progressive disclosure.

Suggestions

Collapse the overlapping tier-routing and background-execution guidance in Execution_Policy, Steps, and Tool_Usage into one canonical section to remove redundancy.

Move the Advanced and Parallel-session-caveats material into a bundled reference file (e.g. references/ADVANCED.md) and link to it, so SKILL.md stays a lean overview.

If docs/shared/agent-tiers.md is relied upon for tier selection, bundle it under references/ so the path is verifiable rather than pointing outside the skill.

Dimension	Reasoning	Score
Conciseness	The body is reasonably lean (tagged sections, bullets, no basic-concept padding), but Execution_Policy, Steps, and Tool_Usage repeat the same tier-routing and background-execution guidance, so it could be tightened to reach 3.	2 / 3
Actionability	Concrete `Task(subagent_type="oh-my-claudecode:executor", model="haiku"...)` calls, explicit `run_in_background: true` usage, and tier-routing rules give copy-paste-ready, executable delegation guidance, matching the 3 anchor.	3 / 3
Workflow Clarity	Steps 1–10 are clearly sequenced with an explicit verification step (build/typecheck/tests/manual QA), a Final_Checklist, and Escalation_And_Stop_Conditions providing feedback loops for error recovery.	3 / 3
Progressive Disclosure	It is a single well-organized file, but at >50 lines with no bundle files present it is monolithic; inline Advanced/Parallel-session-caveats content and references to unbundled docs/*.md keep it at the 'could be better organized' anchor rather than 3.	2 / 3
	Total	10 / 12 Passed

Description

35%

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 a concise tagline that conveys the skill's purpose but lacks trigger terms and any 'when to use' guidance, and leans on jargon ('high-throughput task completion') rather than natural user language. It is distinguishable but not strongly differentiated.

Suggestions

Add a 'Use when...' clause naming natural triggers like 'run tasks in parallel', 'fan out independent work', or 'do several things at once'.

Replace the jargon 'high-throughput task completion' with concrete capabilities (e.g. 'fire multiple agents simultaneously and route each to the right model tier').

Tighten distinctiveness by contrasting with sibling modes, e.g. 'parallelism only — for verified completion use ralph'.

Dimension	Reasoning	Score
Specificity	"Parallel execution engine for high-throughput task completion" names a clear domain and a goal, but lists no concrete actions a user can map to behavior, so it stops short of the multi-action anchor at 3.	2 / 3
Completeness	It states what the skill does (parallel execution engine) but gives no "Use when..." clause or equivalent trigger guidance, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	The phrase "high-throughput task completion" is jargon users would not naturally say, and there are no natural trigger keywords (e.g. "run in parallel", "do these at once"), matching the technical-jargon anchor at 1.	1 / 3
Distinctiveness Conflict Risk	"Parallel execution engine" carves out a niche but the description is generic enough to overlap with other orchestration/execution skills, so it sits at the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	7 / 12 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
Commit: 6c59219

Reviewed: about 6 hours 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.