CtrlK
BlogDocsLog inGet started
Tessl Logo

flow-nexus-swarm

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

66

1.88x
Quality

50%

Does it follow best practices?

Impact

100%

1.88x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The canonical home for this skill is flow-nexus-swarm in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

46%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 concrete MCP examples but is verbose and monolithic, inlining API reference material that should live in separate files, and lacks validation checkpoints for destructive/batch operations.

Suggestions

Move the full API reference, template catalog, and pattern library into separate reference files (e.g. REFERENCE.md, TEMPLATES.md, PATTERNS.md) and keep SKILL.md as a concise overview with one-level-deep links.

Trim repeated examples (e.g. Best Practices swarm_init calls already shown in Swarm Management) and remove explanatory padding Claude already knows.

Add explicit validate→fix→retry checkpoints around destructive/batch steps (swarm_destroy, deploy_prod, ETL load) to raise workflow clarity above 3.

DimensionReasoningScore

Conciseness

The ~600-line body inlines an exhaustive API reference, four full workflow patterns, and a template catalog with repeated examples; noticeably verbose with substantial padding that belongs in reference files.

2 / 5

Actionability

Concrete, copy-paste-ready mcp__flow-nexus__* calls with documented parameters cover the common cases, with only minor placeholder gaps (e.g. "workflow_id").

4 / 5

Workflow Clarity

Sections and numbered patterns are sequenced, but batch/destructive operations (swarm destroy, prod deploy) lack validation/verification checkpoints, capping workflow clarity at 3.

3 / 5

Progressive Disclosure

No bundle files exist; the entire API reference, template catalog, and full patterns are inlined in SKILL.md rather than split into one-level-deep reference files.

2 / 5

Total

11

/

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 identifies the platform and two core capabilities but is generic and lacks explicit trigger guidance. It is distinguishable mainly because it names a specific platform.

Suggestions

Add an explicit "Use when..." clause listing concrete triggers (e.g. swarms, message-queue workflows, multi-agent coordination, CI/CD pipelines).

Replace high-level phrasing with several specific concrete actions (spawn agents, orchestrate tasks, monitor queues, scale swarms) to raise specificity.

Include natural synonyms and product/file tokens users would actually say (e.g. "Flow Nexus", "claude-flow", ".nexus") to improve trigger term quality.

DimensionReasoningScore

Specificity

Names the domain (swarm orchestration) and two high-level actions ("swarm deployment", "event-driven workflow automation") but does not enumerate multiple specific concrete operations.

3 / 5

Completeness

Provides a clear "what" but lacks any "Use when..." trigger clause, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords like "swarm", "workflow", and "automation" appear, but natural user phrases, common synonyms, and file extensions are missing.

3 / 5

Distinctiveness Conflict Risk

Tying the skill to the named "Flow Nexus platform" gives it a clear niche with only minor overlap risk against generic orchestration skills.

4 / 5

Total

13

/

20

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 (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/ruflo
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.