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 extremely minimal and fails to communicate what the skill does or when it should be used beyond naming a slash command. It provides no concrete actions, no natural trigger terms, and no 'Use when...' guidance, making it nearly useless for skill selection among multiple options.
Suggestions
Add a clear statement of what the skill does, e.g., 'Splits a complex task into parallel subtasks and coordinates their execution' or similar concrete capability description.
Add a 'Use when...' clause describing the scenarios that should trigger this skill, such as 'Use when the user issues a /parallel-task command to break work into concurrent sub-tasks.'
Include natural language trigger terms that describe the concept (e.g., 'parallel execution', 'concurrent tasks', 'split work', 'run tasks simultaneously') so Claude can match user intent even without the exact slash command.
| 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 description answers neither 'what does this do' nor 'when should Claude use it' in any meaningful way. It only states the activation mechanism (a slash command) without explaining the skill's purpose or use cases. | 1 / 3 |
Trigger Term Quality | It includes the explicit trigger term '/parallel-task' which is specific, but it provides no natural language keywords a user might say. The trigger is a slash command rather than natural user language, though it does clearly name the command. | 2 / 3 |
Distinctiveness Conflict Risk | The explicit slash command '/parallel-task' provides some distinctiveness and reduces accidental triggering, but the lack of any description of what the skill actually does makes it hard to fully assess conflict risk with 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-structured orchestration skill with strong actionability and workflow clarity. The dependency-based wave execution, TDD validation loops, and explicit commit/logging rules make it highly practical. The main weakness is that the lengthy task prompt template and execution summary template inflate the token cost and could benefit from being extracted into referenced files.
Suggestions
Extract the Task Prompt Template and Execution Summary Template into separate referenced files (e.g., TASK_PROMPT.md, SUMMARY_TEMPLATE.md) to reduce the main skill's token footprint and improve progressive disclosure.
Trim minor redundancies in the task prompt instructions (e.g., the 'Important' section at the end partially repeats earlier guidance about focusing on the specific task and handling blockers).
| 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 rules for plan files, a complete task prompt template with numbered instructions, explicit validation criteria (RED -> GREEN), commit rules (stage only task files, never push), and clear example invocations. The workflow is copy-paste ready for orchestration. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (Parse → Read → Launch → Validate → Repeat) with explicit validation checkpoints at Step 4, feedback loops for retrying failed tasks, and a clear dependency-based wave execution model. The TDD RED→GREEN cycle provides a built-in verification loop, and the instruction to not proceed until validation passes is explicit. | 3 / 3 |
Progressive Disclosure | The skill is a single monolithic file with no references to external documents. The task prompt template is very long and could be extracted to a separate file. The execution summary template could also be a separate reference. However, the sections are well-organized with clear headers, which partially compensates. | 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
633b7e0
- 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.