parallel-agents
Coordinates parallel subagent dispatch to solve multiple independent problems concurrently, with structured prompts and conflict-free integration. Use when there are 2+ independent failures, bugs, tasks, or investigations that do not share state -- e.g. multiple test files failing for different reasons, unrelated subsystems broken, or batch tasks that can run simultaneously. DO NOT TRIGGER when failures are related, require shared context, or agents would edit the same files.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is an excellent skill description that clearly defines its purpose, provides rich trigger terms, and explicitly delineates both positive and negative activation conditions. The inclusion of concrete examples (multiple test files, unrelated subsystems, batch tasks) and the 'DO NOT TRIGGER' anti-pattern clause make it highly actionable for skill selection. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'parallel subagent dispatch', 'structured prompts', 'conflict-free integration'. Also enumerates concrete use cases like 'multiple test files failing for different reasons, unrelated subsystems broken, or batch tasks that can run simultaneously'. | 3 / 3 |
Completeness | Clearly answers both 'what' (coordinates parallel subagent dispatch with structured prompts and conflict-free integration) and 'when' (explicit 'Use when' clause with specific triggers, plus a 'DO NOT TRIGGER' clause for negative cases). Exemplary completeness. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'independent failures', 'bugs', 'tasks', 'investigations', 'multiple test files failing', 'unrelated subsystems broken', 'batch tasks', 'parallel', 'concurrently'. Good coverage of variations a user might naturally express. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around parallel/concurrent independent task execution. The explicit 'DO NOT TRIGGER' clause for related failures or shared-file edits further reduces conflict risk with sequential debugging or single-task skills. | 3 / 3 |
Total | 12 / 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 with clear workflow steps and excellent concrete examples including real agent prompts and dispatch patterns. Its main weakness is verbosity — several sections are redundant (When NOT to Use repeats Don't use when; Real-World Impact repeats Real Example; Key Benefits states the obvious), and the content could be ~30% shorter without losing information. The decision flowchart as a dot graph is creative but adds tokens for marginal value.
Suggestions
Consolidate the redundant sections: merge 'When NOT to Use' into the 'Don't use when' bullets, remove 'Real-World Impact' (it repeats the Real Example), and cut 'Key Benefits' (the benefits are self-evident from the pattern description).
Replace the dot graph with a simple 2-3 line decision rule, e.g., 'Use parallel dispatch when: multiple failures + independent domains + no shared files. Otherwise: investigate sequentially.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some redundancy — the 'When NOT to Use' section largely repeats the 'Don't use when' bullets, the 'Key Benefits' section restates obvious points, and the 'Real-World Impact' section repeats the 'Real Example from Session' content. The dot graph is a nice idea but verbose for what could be a simple bullet list. However, it mostly avoids explaining things Claude already knows. | 2 / 3 |
Actionability | Provides concrete, copy-paste-ready agent prompt templates, specific TypeScript dispatch syntax, detailed example with actual test file names and error descriptions, and clear do/don't patterns with specific examples. The agent prompt structure section is particularly actionable. | 3 / 3 |
Workflow Clarity | The 4-step workflow (Identify → Create Tasks → Dispatch → Review/Integrate) is clearly sequenced with explicit validation steps in the 'Verification' section (review summaries, check conflicts, run full suite, spot check). The integration step includes conflict detection as a feedback loop. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers, but it's a monolithic document that could benefit from splitting the detailed real-world example and the agent prompt template into separate referenced files. At ~150 lines, some sections (Key Benefits, Real-World Impact) could be trimmed or consolidated rather than adding length. | 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
- shousper/claude-kit
- Commit
a01bac9
- 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.