parallel-task
Only to be triggered by explicit /parallel-task commands.
60
49%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/parallel-task/SKILL.mdQuality
Discovery
22%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 critically deficient: it specifies only a trigger mechanism (/parallel-task command) without describing any capabilities, actions, or use cases. Claude would have no basis for understanding what this skill does or when to apply it beyond the exact slash command. It fails to serve the primary purpose of helping Claude choose the right skill from a large pool.
Suggestions
Add concrete capability descriptions explaining what the skill does (e.g., 'Breaks down complex tasks into parallel subtasks and coordinates their execution').
Add a 'Use when...' clause with natural language trigger terms describing scenarios where this skill is appropriate (e.g., 'Use when the user wants to run multiple independent tasks simultaneously, mentions parallelism, or needs to split work across threads').
Include natural keywords users might say such as 'parallel', 'concurrent tasks', 'split work', 'run simultaneously' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It does not describe what the skill does—only that it is triggered by a specific command. 'parallel-task' hints at a domain but no capabilities are listed. | 1 / 3 |
Completeness | The 'what does this do' is entirely missing—there is no explanation of the skill's functionality. The 'when' is partially addressed (only on explicit /parallel-task commands), but without knowing what the skill does, this is insufficient. Missing 'Use when...' equivalent caps this at 2, but the absence of 'what' drops it to 1. | 1 / 3 |
Trigger Term Quality | It includes the specific trigger term '/parallel-task' which is a concrete keyword, but it provides no natural language keywords a user might say. The trigger is a slash command rather than natural user language, and there are no variations or synonyms. | 2 / 3 |
Distinctiveness Conflict Risk | The explicit slash command trigger '/parallel-task' provides some distinctiveness and reduces accidental triggering, but without describing what the skill actually does, it's unclear how it differs from other task-management or parallelism-related skills. | 2 / 3 |
Total | 6 / 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-crafted orchestration skill with strong actionability and workflow clarity. The step-by-step process with explicit validation checkpoints, error handling, and the TDD-first approach demonstrates thoughtful design for a complex multi-agent workflow. The main weakness is that the inline task prompt template and execution summary template make the file somewhat long, though the content density is generally justified by the complexity of the task.
Suggestions
Consider extracting the Task Prompt Template and Execution Summary Template into separate referenced files to improve progressive disclosure and reduce the main skill's token footprint.
Trim minor redundancies — e.g., the instruction to commit but never push appears in the template and could be consolidated with Step 4's commit validation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some verbosity, particularly in the task prompt template which is quite long. The execution summary template at the end adds bulk. However, most content is instructional rather than explanatory, and it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: specific parsing patterns (e.g., `### T1:` format), a complete task prompt template with numbered steps, explicit validation criteria (RED -> GREEN), commit instructions, and example invocations. Claude knows exactly what to do at each stage. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (Steps 1-5) with explicit validation checkpoints: Step 4 includes inspection, validation against expected outcomes, retry/escalation for failures, and ensuring commits exist before proceeding. The feedback loop (launch → validate → retry or proceed → repeat) is well-defined, and the TDD RED→GREEN cycle provides built-in verification. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but the task prompt template is a large inline block that could potentially be referenced separately. The skill is somewhat monolithic — the execution summary template and the full subagent prompt template inflate the main file when they could be separate references. However, for a single-file skill this is acceptable organization. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- am-will/codex-skills
- Commit
ca2c3b3
- 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.