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

44%

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 ./skills/parallel-agents/SKILL.md

Quality

Content

35%Scale 1-5

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 high-level conceptual framework for multi-agent orchestration but lacks the concrete, executable guidance needed to be truly actionable. The content is padded with explanations of obvious concepts and a large reference table, while the actual 'how-to' remains at the pseudocode/natural-language level. The orchestration patterns are logically sequenced but missing validation checkpoints and error recovery steps.

Suggestions

Replace natural-language pseudocode blocks with actual executable agent tool invocations showing real parameters, expected inputs/outputs, and concrete syntax Claude should use.

Add validation checkpoints to orchestration patterns: how to verify each agent's output before passing context to the next agent, and what to do when an agent returns incomplete or conflicting results.

Move the 17-row agent reference table to a separate AGENTS.md file and keep only the most commonly used 3-4 agents inline with brief descriptions.

Remove the 'Key Benefits' and 'When to Use Orchestration' sections — Claude already understands when parallelism and specialization are appropriate.

Dimension	Reasoning	Score
Conciseness	Significant verbosity throughout. The 'When to Use Orchestration' section explains obvious concepts. The 17-row agent table with trigger phrases is excessive padding. The 'Key Benefits' section restates what's already implied. The 'Best Practices' section is mostly filler that Claude would already know (e.g., 'logical order', 'share context').	2 / 5
Actionability	The guidance is almost entirely abstract and descriptive rather than executable. The 'code' blocks contain natural language descriptions and pseudocode patterns, not actual executable commands or real tool invocations. There are no concrete examples showing actual agent tool calls, real parameters, or expected outputs. The agent names and trigger phrases appear to reference a custom system but provide no concrete implementation details.	2 / 5
Workflow Clarity	The orchestration patterns show a logical sequence (discovery → analysis → synthesis), and the synthesis protocol provides a template. However, there are no validation checkpoints, no error handling, and no feedback loops for when agents produce conflicting or incomplete results. For multi-agent orchestration involving potentially destructive operations (code modifications), the lack of verification steps is a notable gap.	3 / 5
Progressive Disclosure	The content is structured with clear sections and headers, which aids navigation. However, the large agent reference table and synthesis template are inlined when they could be in separate files. There are no references to external files for detailed agent configurations or extended examples. For a skill of this length (~150 lines), some content should be split out.	3 / 5
	Total	10 / 20 Passed

Description

53%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 identifies a domain (multi-agent orchestration) and provides a 'Use when' clause, which is good structurally. However, it lacks concrete actions — it doesn't specify what the skill actually does (e.g., spawning sub-agents, coordinating parallel tasks, merging results). The trigger terms lean toward technical jargon rather than natural user language.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Spawns multiple sub-agents to handle independent tasks in parallel, coordinates their outputs, and merges results into a unified response.'

Include more natural trigger terms users might say, such as 'parallel tasks', 'delegate work', 'fan-out', 'split into sub-tasks', 'concurrent processing'.

Sharpen distinctiveness by specifying what differentiates this from single-agent task handling or simple sequential workflows.

Dimension	Reasoning	Score
Specificity	Names the domain ('multi-agent orchestration patterns') but the actions described are vague — 'multiple independent tasks can run' and 'comprehensive analysis requires multiple perspectives' don't describe concrete actions like spawning agents, coordinating results, or merging outputs.	2 / 5
Completeness	Has both 'what' (multi-agent orchestration patterns) and 'when' (multiple independent tasks with different domain expertise, or comprehensive analysis requiring multiple perspectives). The 'when' clause is present and somewhat specific, but the 'what' is vague about actual capabilities.	4 / 5
Trigger Term Quality	Includes some relevant terms like 'multi-agent', 'orchestration', 'multiple perspectives', and 'domain expertise', but misses natural user phrases like 'parallel tasks', 'fan-out', 'delegate', 'sub-agents', 'concurrent', or 'split work'. Users are unlikely to say 'orchestration patterns' naturally.	3 / 5
Distinctiveness Conflict Risk	The term 'multi-agent orchestration' provides some distinctiveness, but 'comprehensive analysis requires multiple perspectives' is broad enough to overlap with general analysis or review skills. The description doesn't clearly carve out a unique niche.	3 / 5
	Total	12 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: 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.