dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Install with Tessl CLI
npx tessl i github:projectbluefin/dakota --skill dispatching-parallel-agentsOverall
score
59%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
7%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 fails to explain what the skill actually does, only describing when to use it. The language is technical and abstract rather than action-oriented, and lacks natural trigger terms users would employ. It reads more like a usage condition than a skill description.
Suggestions
Add concrete actions describing what this skill does (e.g., 'Executes multiple tasks in parallel', 'Processes independent workloads concurrently')
Include natural trigger terms users would say such as 'parallel', 'batch processing', 'multiple tasks at once', 'concurrent', 'simultaneously'
Restructure to lead with capabilities before the 'Use when' clause (e.g., 'Runs multiple independent tasks in parallel to speed up processing. Use when...')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'independent tasks' and 'worked on' without specifying any concrete actions. It describes a condition for use rather than what the skill actually does. | 1 / 3 |
Completeness | Only provides a 'when' clause but completely omits 'what' the skill does. There's no explanation of the capability or actions this skill performs. | 1 / 3 |
Trigger Term Quality | Contains technical jargon ('shared state', 'sequential dependencies') that users would not naturally say. Missing natural trigger terms like 'parallel', 'multiple tasks', 'batch', or 'concurrent'. | 1 / 3 |
Distinctiveness Conflict Risk | The concept of 'independent tasks without shared state' is somewhat specific to parallel/concurrent processing, but '2+ tasks' is generic enough to potentially conflict with task management or workflow skills. | 2 / 3 |
Total | 5 / 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 solid, actionable skill that clearly explains when and how to dispatch parallel agents. The workflow is well-sequenced with good verification steps, and the agent prompt structure section provides excellent concrete guidance. The main weakness is some redundancy between sections (real example appears twice in different forms) and the content could be more concise by consolidating similar sections.
Suggestions
Consolidate 'Real Example from Session' and 'Real-World Impact' sections - they contain overlapping information about the same debugging session
Consider merging 'When to Use' and 'When NOT to Use' into a single decision section to reduce redundancy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy - the 'Real Example from Session' and 'Real-World Impact' sections largely repeat the same information, and some concepts are explained multiple times (when to use vs when NOT to use could be consolidated). | 2 / 3 |
Actionability | Provides concrete, executable guidance with specific TypeScript dispatch syntax, detailed agent prompt templates with exact structure, and real examples showing exact test file names and error messages. The prompt structure section is copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear 4-step sequence (Identify → Create → Dispatch → Review) with explicit verification steps at the end. The decision flowchart (dot diagram) clearly shows when to use the pattern, and the verification section provides explicit checkpoints for integration. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections, but it's somewhat monolithic at ~150 lines. The real example and real-world impact sections could be consolidated or moved to a separate file. No external references are provided for deeper dives on agent prompting or parallel execution patterns. | 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.
- 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.