parallel-task-spark
Only to be triggered by explicit /parallel-task-spark commands.
62
53%
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-spark/SKILL.mdQuality
Discovery
29%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 actually does. While the explicit slash command trigger makes it distinctive and unlikely to conflict with other skills, the complete absence of capability descriptions, use cases, or natural language keywords means Claude cannot intelligently select this skill based on user intent. It functions purely as a command-gated skill with no discoverability.
Suggestions
Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Orchestrates parallel task execution by splitting work into concurrent subtasks and aggregating results').
Add a 'Use when...' clause that explains the scenarios or user needs this skill addresses, beyond just the slash command trigger.
Include natural language trigger terms that describe the skill's domain so Claude can understand its purpose even if the user doesn't use the exact slash command (e.g., 'parallel processing, concurrent tasks, task splitting').
| 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-spark' is a name, not a capability description. | 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 one explicit trigger term ('/parallel-task-spark'), which is a slash command rather than a natural language keyword. Users who know the command will trigger it, but there are no natural language terms describing what the skill does or when a user might need it. | 2 / 3 |
Distinctiveness Conflict Risk | The explicit slash command trigger '/parallel-task-spark' is highly distinctive and unlikely to conflict with other skills, since it requires an exact command match rather than natural language interpretation. | 3 / 3 |
Total | 7 / 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—clear step sequencing, validation checkpoints, and error recovery paths. Its main weaknesses are moderate verbosity (some redundant instructions and explanations that an intelligent agent could infer) and the monolithic structure that could benefit from extracting the task prompt template into a referenced file.
Suggestions
Extract the lengthy Task Prompt Template into a separate file (e.g., TASK_PROMPT_TEMPLATE.md) and reference it from the main skill to improve progressive disclosure and reduce inline bulk.
Remove redundant reminders about agent_type: sparky (mentioned 3 times) and consolidate into a single clear constraint statement.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy—e.g., repeating 'agent_type: sparky' constraints multiple times, and the task prompt template is quite verbose with instructions Claude could infer. The execution summary template at the end adds bulk but is useful as a concrete output format. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: a specific task prompt template, exact steps for parsing plans, clear subagent launch instructions, example invocations, and a structured execution summary template. The workflow is copy-paste ready for an orchestrator agent. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced (Steps 1-5) with explicit validation checkpoints (Step 4 validates outputs, requires RED->GREEN evidence or non-testable verification), feedback loops (retry or escalate on failure), and wave-based dependency management. The commit-before-next-wave checkpoint is a good safeguard. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a monolithic file with no references to external documents. The lengthy task prompt template could be extracted to a separate file. For a skill of this length (~120 lines of substantive content), some splitting would improve navigability. | 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.