flow-nexus-swarm

Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform

2.07x

Quality

59%

Does it follow best practices?

Impact

87%

2.07x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/flow-nexus-swarm/SKILL.md

Quality

Content

65%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 content is highly actionable with comprehensive executable examples, but it is over-long and redundant, lacks validation checkpoints in its batch/destructive workflows, and inlines material that should be split into reference files.

Suggestions

Move the template catalog and full workflow patterns into separate reference files (e.g. TEMPLATES.md, PATTERNS.md) and link to them from SKILL.md to improve progressive disclosure and cut inline bulk.

Add explicit validation checkpoints and feedback loops to batch/destructive workflows (e.g. verify swarm_status after swarm_scale, validate workflow steps before deploy_prod, re-run on failure) to satisfy the validation requirement.

Remove redundant code blocks — swarm_status is shown in both Swarm Management and Advanced Features, and topology examples are repeated in Best Practices — to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete code, but redundancy (swarm_status repeated in Swarm Management and Advanced Features, topology choice re-explained in Best Practices, Overview bullets restating later sections) goes beyond minor trimming.	3 / 5
Actionability	Dense, copy-paste-ready MCP tool calls with full parameters, and specific pattern examples (full-stack, research, CI/CD, ETL) that cover the common cases.	5 / 5
Workflow Clarity	Numbered sequences appear in the patterns, but there are no explicit validation checkpoints or validate-fix-retry loops, and the workflows include batch and destructive operations (swarm_scale, swarm_destroy, deploy_prod, ETL) which caps this dimension at 3.	3 / 5
Progressive Disclosure	Good section headers and a table of contents provide structure, but ~600 lines are entirely inline with no bundle files and no references to separate files; the template catalog and full pattern library clearly belong in their own files.	3 / 5
	Total	14 / 20 Passed

Description

53%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 conveys the platform and domain but omits explicit trigger guidance and leans on technical phrasing over natural user language. It is distinct but not maximally actionable for activation.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when deploying cloud-based AI agent swarms, orchestrating event-driven workflows, or processing message queues with Flow Nexus.'

Broaden trigger term coverage with natural synonyms users would actually say, such as 'agent swarms', 'message queue processing', and 'MCP swarm orchestration'.

List a few more concrete capabilities (e.g. topology selection, template library, real-time monitoring) to lift specificity from domain-naming to several specific actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('AI swarm deployment') and two concrete actions ('deployment', 'event-driven workflow automation') but the coverage is not comprehensive enough for anchor 4.	3 / 5
Completeness	Clearly states what the skill does but lacks any 'Use when...' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms (swarm, workflow, automation, Flow Nexus) are present but lean technical and miss common natural variations or synonyms a user would actually say.	3 / 5
Distinctiveness Conflict Risk	Naming the Flow Nexus platform and the cloud-AI-swarm niche makes it mostly distinct with only minor overlap risk, above anchor 3 but without the explicit distinct triggers needed for 5.	4 / 5
	Total	13 / 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
skill_md_line_count	SKILL.md is long (611 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ruvnet/agentic-flow
Path: .claude/skills/flow-nexus-swarm/SKILL.md
Commit: e993605

Reviewed: 9 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.