parallel-task
Coordinate plan files by launching multiple parallel subagents for unblocked tasks. Triggers on explicit "/parallel-task" commands.
74
68%
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
75%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 functional with a clear trigger mechanism and distinct niche, making it easy to identify when to use. However, it could benefit from more specific concrete actions beyond 'coordinate' and 'launching', and from including more natural language trigger terms that users might use beyond the slash command.
Suggestions
Add more specific concrete actions, e.g., 'Splits plan tasks into parallel workstreams, launches subagents for independent tasks, and merges results back into the plan.'
Include natural language trigger variations beyond the slash command, e.g., 'Use when the user wants to run multiple tasks simultaneously, parallelize work, or speed up plan execution.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (parallel subagents, plan files) and a key action (launching multiple parallel subagents for unblocked tasks), but doesn't list multiple concrete actions beyond coordination and launching. | 2 / 3 |
Completeness | Clearly answers both 'what' (coordinate plan files by launching parallel subagents for unblocked tasks) and 'when' (triggers on explicit '/parallel-task' commands), with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes the explicit trigger '/parallel-task' which is useful, and mentions 'subagents', 'unblocked tasks', and 'plan files', but these are somewhat technical terms. Missing natural user phrases like 'run tasks in parallel', 'concurrent execution', or 'speed up tasks'. | 2 / 3 |
Distinctiveness Conflict Risk | The explicit '/parallel-task' command trigger and the specific niche of parallel subagent coordination make this highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
62%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 workflow clarity, explicit safety boundaries, and a clear iterative loop with validation. Its main weaknesses are the lack of concrete tool invocation examples (how exactly to launch subagents, what API/tool calls to use) and some verbosity in templates that partially overlap. The skill would benefit from showing actual subagent launch syntax rather than describing it abstractly.
Suggestions
Add a concrete example of the actual subagent launch mechanism (e.g., the specific tool_use call or API syntax for launching parallel subagents) so Claude knows exactly how to execute Step 3.
Show a brief concrete example of dependency detection—how to determine which tasks are 'unblocked' from a plan file's markdown structure.
Remove redundant output format specifications—the summary fields appear in both the task prompt and the run summary template; consolidate or reference one from the other.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some redundancy—the summary output format appears both in the task prompt template and the run summary template, and some instructions (like 'be careful with paths') are things Claude already knows. The task prompt template is somewhat verbose but justified given it's a template for subagent prompts. | 2 / 3 |
Actionability | The skill provides a clear process and templates, but lacks concrete executable code for the core operations—how to actually parse plan files, how to launch subagents (no tool_use examples or API calls shown), and how to detect dependencies/blockers. The task prompt template is well-structured but the orchestration mechanics are described abstractly rather than with concrete tool invocations. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (parse → read → launch → monitor → repeat → validate) with explicit validation checkpoints (Step 6), error handling for blockers, and a feedback loop (Step 5 re-reads the plan and repeats). Safety boundaries explicitly prevent skipping validation or continuing past blockers. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's somewhat long for a single file. The task prompt template and run summary template could potentially be referenced as separate files. However, the organization within the single file is logical and navigable. | 2 / 3 |
Total | 9 / 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
- jdrhyne/agent-skills
- Commit
6768672
- 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.