ultrawork
Parallel execution engine for high-throughput task completion
40
38%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ultrawork/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a buzzword-laden tagline with no actionable content. It fails to specify what tasks are executed, what domain it applies to, or when Claude should select it. It would be nearly impossible for Claude to correctly choose this skill from a list of alternatives.
Suggestions
Replace abstract jargon with concrete actions — specify exactly what types of tasks this skill executes in parallel (e.g., 'Runs multiple API calls, file processing jobs, or data transformations concurrently').
Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user wants to run multiple tasks simultaneously, batch process files, or speed up repetitive operations').
Define the skill's niche clearly to distinguish it from general task-handling skills — specify the input types, output types, or domain context.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('parallel execution engine', 'high-throughput task completion') without naming any concrete actions. It doesn't specify what tasks are being completed or what domain it operates in. | 1 / 3 |
Completeness | The description barely addresses 'what' (vaguely implies parallel task execution) and completely omits 'when' — there is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'parallel execution engine' and 'high-throughput task completion' are technical jargon that users would almost never naturally say. No natural keywords or common user phrases are included. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic — 'task completion' could apply to virtually any skill. There is nothing to distinguish this from other skills or prevent false triggering. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with strong actionability and workflow clarity. The concrete Task() examples with tier routing and background execution patterns give Claude clear, executable guidance. The main weaknesses are moderate verbosity (explanatory sections like Why_This_Exists and some redundancy between Purpose/Use_When) and the lack of bundle files to support the referenced agent-tiers.md dependency.
Suggestions
Remove or significantly trim <Why_This_Exists> and <Purpose> sections — the Use_When/Do_Not_Use_When sections already convey when and why to use this skill
Include the referenced `docs/shared/agent-tiers.md` as a bundle file, or inline the essential tier definitions to make the skill self-contained
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like <Why_This_Exists> which explains motivation Claude doesn't need, and <Purpose> partially restates what <Use_When> already covers. The <Do_Not_Use_When> section is useful but slightly verbose with parenthetical explanations. Overall mostly tight but could be trimmed. | 2 / 3 |
Actionability | Provides concrete, executable Task() invocations with specific parameters (model, subagent_type, prompt, run_in_background). The examples section shows both good and bad patterns with real code. The steps are specific and the tool usage section gives copy-paste ready patterns. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced from intent grounding through context gathering, task classification, graph creation, parallel execution, and verification. It includes explicit validation checkpoints (step 10), dependency handling (step 8), and escalation/stop conditions. The task graph concept with parallel waves and dependency matrices provides strong structure for complex work. | 3 / 3 |
Progressive Disclosure | References `docs/shared/agent-tiers.md` as an external file which is good, but no bundle files are provided to verify it exists. The content is somewhat monolithic — the examples, escalation conditions, and advanced relationship diagram are all inline when some could be separated. However, the XML-tag structure provides reasonable internal organization. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
679b418
- Reviewed
Table of Contents
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.