parallel-agents

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

Quality

62%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/parallel-agents/SKILL.md

Quality

Discovery

67%

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 adequately covers when to use the skill with explicit trigger conditions, which is its strongest aspect. However, it lacks concrete action verbs describing what the skill actually does (e.g., spawning agents, coordinating tasks, merging results) and could benefit from more natural trigger terms users would actually say.

Suggestions

Add specific concrete actions like 'Spawns specialized sub-agents, coordinates parallel workflows, aggregates results from multiple agents'

Include more natural trigger terms users might say: 'parallel tasks', 'delegate work', 'fan-out', 'concurrent', 'sub-agents'

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-agent orchestration') and mentions some actions ('independent tasks', 'comprehensive analysis'), but lacks concrete specific actions like 'spawn agents', 'coordinate workflows', or 'aggregate results'.	2 / 3
Completeness	Clearly answers both what ('Multi-agent orchestration patterns') and when ('Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some relevant terms ('multiple independent tasks', 'domain expertise', 'multiple perspectives') but misses common natural variations users might say like 'parallel tasks', 'delegate', 'sub-agents', 'fan-out', or 'concurrent work'.	2 / 3
Distinctiveness Conflict Risk	The term 'orchestration patterns' is somewhat specific to multi-agent scenarios, but 'comprehensive analysis' and 'multiple perspectives' could overlap with general analysis or review skills.	2 / 3
	Total	9 / 12 Passed

Implementation

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides a solid overview of multi-agent orchestration with good structure and clear patterns. However, it lacks concrete executable examples (the invocation syntax is ambiguous), misses validation/error handling steps in workflows, and has some redundant content. The agent reference tables are useful but the actual mechanics of agent invocation need clarification.

Suggestions

Clarify the exact syntax for agent invocation - is 'Use the security-auditor agent' literal syntax or natural language? Provide a concrete, copy-paste ready example.

Add validation checkpoints to orchestration patterns: how to verify an agent completed successfully before proceeding, and what to do if an agent fails or returns incomplete results.

Remove redundant sections (Key Benefits largely duplicates earlier content) to improve token efficiency.

Add a concrete end-to-end example showing actual agent invocation, context passing syntax, and synthesis output.

Dimension	Reasoning	Score
Conciseness	Content is reasonably efficient but includes some redundancy (e.g., the 'Key Benefits' section largely repeats information from earlier sections, and the 'When to Use' section states obvious points). The agent table is comprehensive but could be more compact.	2 / 3
Actionability	Provides invocation patterns and examples, but they are more like templates/pseudocode than executable commands. The actual syntax for invoking agents (e.g., 'Use the security-auditor agent') is vague - unclear if this is literal syntax or natural language instruction.	2 / 3
Workflow Clarity	Patterns show clear sequences (discovery → analysis → synthesis), but lack validation checkpoints. No guidance on what to do if an agent fails, returns unexpected results, or how to verify agent outputs before proceeding to synthesis.	2 / 3
Progressive Disclosure	Well-organized with clear sections, appropriate use of tables for reference material, and logical flow from overview to patterns to available agents. Content is appropriately structured for a single file without needing external references.	3 / 3
	Total	9 / 12 Passed

Validation

90%

Warnings & errors only

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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: lchenrique/politron-ide
Commit: 7114206

Reviewed: 29 days ago

Table of Contents

Discovery Implementation Validation

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.