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

75%

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 ./.agents/skills/parallel-agents/SKILL.md

Quality

Content

81%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 a well-structured, actionable orchestration policy with clear sequenced workflows, validation checkpoints, and concrete templates. Its main weaknesses are minor redundancy in the closing principles and the absence of a fully filled-in delegation example.

Suggestions

Add one concrete filled-in delegation template (with realistic Agent/Goal/Allowed paths/Budget values) so the pattern is copy-paste ready rather than only schematic.

Trim or merge the 'Core principles' section, which restates points already made in the Trust boundary, Delegation budget, and Isolation policy sections.

If the skill grows, move the budget YAML, delegation template, and pattern diagrams into a referenced file to keep SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean bullet lists, templates, and terse principles that assume Claude's competence; only minor trimming is needed (e.g. the 'Core principles' section restates earlier points), so it is efficient with minor over-explanation.	4 / 5
Actionability	Provides concrete, fillable artifacts (delegation template, isolation steps 1-6, budget YAML, synthesis markdown, pattern diagrams) that give executable guidance, but as an instruction-only skill it stops short of a fully worked, copy-paste-ready filled example.	4 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints and feedback loops: the synthesis protocol runs verify -> identify contradictions -> reject out-of-scope output -> combine -> validate -> report, and the monitoring section lists concrete stop/escalation conditions for a batch delegation skill.	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent) and the skill is a single well-organized file with clear section headers and no nested references; it is appropriately self-contained, with only minor room to split the larger template/pattern material into referenced files.	4 / 5
	Total	17 / 20 Passed

Description

70%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 answers both what and when with explicit trigger conditions and reasonable natural phrasing, but its 'what' is abstract and it lacks synonym coverage. It is solid but leaves room for more concrete capability statements and broader trigger terms.

Suggestions

Replace the abstract 'Multi-agent orchestration patterns' with concrete capabilities, e.g. 'Delegate independent tasks to specialist agents, run parallel read-only reviews, and synthesize multi-perspective analysis.'

Add common trigger synonyms users would say, such as 'parallel agents', 'fan out', 'delegate to specialists', or 'coordinate multiple agents'.

Tighten the 'when' clause to name the explicit anti-trigger (single-domain tasks where one agent suffices) already present in when_to_use, so the description itself signals when NOT to use it.

Dimension	Reasoning	Score
Specificity	Names the domain ('Multi-agent orchestration patterns') and a couple of conceptual actions ('multiple independent tasks can run with different domain expertise', 'comprehensive analysis requires multiple perspectives'), but these are abstract patterns rather than concrete operations like 'extract' or 'fill', so it sits at the domain-plus-1-2-actions level rather than comprehensive.	3 / 5
Completeness	Both 'what' (Multi-agent orchestration patterns) and 'when' (two explicit 'Use when' trigger conditions) are present, but the 'what' side is brief and abstract rather than enumerating concrete capabilities, keeping it just below the fully-explicit anchor.	4 / 5
Trigger Term Quality	Includes several natural phrases a user would say ('multi-agent orchestration', 'multiple independent tasks', 'comprehensive analysis', 'multiple perspectives'), but misses common synonyms like 'parallel agents', 'fan out', or 'delegate to specialists' that would push it to comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	'Multi-agent orchestration' is a clear, distinct niche unlikely to trigger for single-agent skills, with only minor overlap risk against closely related general orchestration or coordination skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/parallel-agents/SKILL.md
Commit: 211561c

Reviewed: 8 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.