Name: parallel-agents
Rating: 50.4 (1 reviews)
Author: administrakt0r

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

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/parallel-agents/SKILL.md

The canonical home for this skill is parallel-agents in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

53%Weight 40%Scale 1-5

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

The body is well-structured with clear patterns and a synthesis template, but its 'examples' are prose rather than real executable Agent-tool invocations, the agent roster includes speculative entries, and workflows lack validation/feedback checkpoints for batch orchestration. It reads more as a conceptual guide than actionable, executable instruction.

Suggestions

Replace the natural-language invocation blocks with real Agent-tool call syntax (or a concrete example showing the actual tool invocation and expected return), so guidance is executable rather than prose.

Add a validation/feedback step to each pattern, e.g. 'if agent findings conflict or are thin, re-run with a tighter prompt before synthesizing', to satisfy the batch-operation feedback-loop requirement.

Trim the padded 'Key Benefits' section and verify the agent table against agents that actually exist, removing speculative entries like seo-specialist and game-developer.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational but padded: 'Key Benefits' restates the Overview, and the 17-row agent table (including speculative entries like seo-specialist and game-developer) adds bulk that could be trimmed, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	Invocation 'code' blocks are natural-language prompts (e.g. "Use the security-auditor agent to review authentication") rather than executable Agent-tool calls, and the listed agents are hypothetical, matching 'some concrete guidance but incomplete; pseudocode instead of executable code'.	3 / 5
Workflow Clarity	Patterns provide numbered sequences and a synthesis template, but there are no validation or verification checkpoints and no feedback loops for this batch (multi-agent) operation, which caps the score at 3 per the rubric's batch-operation guidance.	3 / 5
Progressive Disclosure	With no bundle files present, the skill is self-contained with clear section headers and reasonable organization; the inlined agent table and synthesis template prevent a 5, but structure is good, matching 'good structure; most content appropriately placed'.	4 / 5
	Total	13 / 20 Passed

Description

57%Weight 40%Scale 1-5

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 clearly answers what and when with an explicit 'Use when' trigger, but the what is an abstract noun phrase lacking concrete actions, and the trigger terms lean technical rather than natural. It is moderately strong but could be sharpened with specific verbs and more colloquial phrasing.

Suggestions

Replace the abstract noun phrase 'Multi-agent orchestration patterns' with concrete verbs, e.g. 'Dispatches multiple specialized agents in parallel and synthesizes their findings'.

Add natural trigger phrases users would actually say, such as 'run agents in parallel', 'fan out work across agents', or 'split a task across experts'.

Tie the 'when' clause to a concrete example trigger (e.g. 'Use when a task spans security, backend, and frontend and needs parallel expert review').

Dimension	Reasoning	Score
Specificity	The description names the domain ("Multi-agent orchestration patterns") but offers no concrete action verbs, matching the anchor 'names the domain but actions are minimal or generic'; it does not reach 3 because no specific actions are enumerated.	2 / 5
Completeness	Both a what ("Multi-agent orchestration patterns") and an explicit when ("Use when multiple independent tasks can run...") are present, but the what is a vague noun phrase rather than concrete actions, so it does not reach 5.	4 / 5
Trigger Term Quality	Terms like "multi-agent", "comprehensive analysis", and "multiple perspectives" are relevant but jargon-leaning, and natural phrasings such as "run agents in parallel" are absent, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The orchestration niche is fairly specific with distinct triggers, carrying only minor overlap risk with other agent/workflow skills, matching 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/parallel-agents/SKILL.md
Commit: 57c135b

Reviewed: 3 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.