CtrlK
BlogDocsLog inGet started
Tessl Logo

flow-nexus-swarm

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

67

2.82x
Quality

57%

Does it follow best practices?

Impact

82%

2.82x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

65%

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

The body is highly actionable with concrete, executable MCP calls and well-sequenced worked patterns, but it is over-long and monolithic, explaining concepts Claude already knows and inlining content that belongs in separate reference files. Risky and batch operations lack the validation checkpoints the rubric expects.

Suggestions

Move the template catalog, advanced features, and full worked patterns into separate reference files (e.g., TEMPLATES.md, PATTERNS.md) and keep SKILL.md as a concise overview with one-level-deep links.

Trim explanations of concepts Claude already knows (topology types, agent roles, retry-policy basics) and de-duplicate repeated tool signatures across examples.

Add explicit validation checkpoints and error-recovery loops for batch/destructive operations (e.g., check swarm_status and workflow_status before scaling or destroying).

DimensionReasoningScore

Conciseness

The ~600-line body is mostly efficient with real code blocks, but explains concepts Claude already knows (topology types, agent roles, retry policies) and repeats tool signatures across many worked patterns, so it could be tightened considerably.

2 / 3

Actionability

Provides concrete, copy-paste-ready mcp__flow-nexus__* calls with parameters, option annotations, and multiple complete worked patterns (full-stack dev, CI/CD, ETL).

3 / 3

Workflow Clarity

Multi-step patterns are clearly sequenced with depends_on graphs, but batch/destructive operations (scaling, destroying swarms, async workflow execution) lack explicit validation checkpoints or error-recovery feedback loops, capping clarity at 2.

2 / 3

Progressive Disclosure

No bundle files exist and the body references none; a large API reference and full pattern catalog that should be split into separate reference files is instead monolithic inline, though section headers and a TOC provide some organization.

2 / 3

Total

9

/

12

Passed

Description

50%

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 identifies the platform and high-level capabilities but reads as a feature statement rather than a triggered, user-facing description. It lacks an explicit 'Use when...' trigger clause and leans on technical jargon over natural keywords.

Suggestions

Add an explicit 'Use when...' clause naming concrete user situations (e.g., 'Use when deploying multi-agent AI swarms, automating event-driven CI/CD or ETL pipelines, or coordinating agents across cloud workflows').

Replace jargon-heavy phrasing with natural trigger terms users would say ('deploy AI agents', 'automate workflows', 'run multi-agent tasks').

List several specific concrete actions to lift specificity from a domain mention to a comprehensive capability list.

DimensionReasoningScore

Specificity

Names the domain ('swarm deployment') and some concrete actions ('event-driven workflow automation') but does not enumerate multiple specific actions, so it falls short of the comprehensive list expected at score 3.

2 / 3

Completeness

It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric.

2 / 3

Trigger Term Quality

Contains relevant domain keywords ('swarm deployment', 'workflow automation') but leans on technical jargon rather than the natural phrases users would actually say, and misses common variations.

2 / 3

Distinctiveness Conflict Risk

Naming the 'Flow Nexus platform' gives it a niche, but the generic 'AI swarm deployment'/'workflow automation' framing could still overlap with other orchestration skills.

2 / 3

Total

8

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (629 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/ruvector
Reviewed

Table of Contents

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.