flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges
59
41%
Does it follow best practices?
Impact
94%
2.04xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/flow-nexus-platform/SKILL.mdQuality
Discovery
32%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 specific platform (Flow Nexus) and lists broad capability areas, but lacks concrete actions, explicit trigger guidance, and a 'Use when...' clause. It reads more like a category label than a skill description that would help Claude reliably select it from a large pool of skills.
Suggestions
Add a 'Use when...' clause specifying when this skill should be selected, e.g., 'Use when the user mentions Flow Nexus, or needs to manage Flow Nexus sandboxes, deploy apps to Flow Nexus, or configure Flow Nexus payments.'
Replace the high-level category list with specific concrete actions, e.g., 'Creates and manages Flow Nexus sandboxes, deploys applications to Flow Nexus environments, configures payment integrations, and sets up authentication flows.'
Include natural trigger terms and variations users might say, such as 'Flow Nexus API', 'FN sandbox', 'deploy to Flow Nexus', or specific CLI/tool names associated with the platform.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific platform ('Flow Nexus') and lists several domain areas (authentication, sandboxes, app deployment, payments, challenges), but these are high-level categories rather than concrete actions. It doesn't describe what specific operations are performed (e.g., 'create sandboxes', 'deploy apps', 'process payments'). | 2 / 3 |
Completeness | The description addresses 'what' at a high level (platform management across several domains) but completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric should cap completeness at 2, and since the 'what' is also quite vague, a score of 1 is appropriate. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'authentication', 'sandboxes', 'app deployment', 'payments', and 'challenges' that users might mention, but 'Flow Nexus' is the primary distinguishing term and the other terms are generic enough to overlap with many other skills. Missing natural variations or more specific trigger phrases. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Flow Nexus' as a specific platform name provides some distinctiveness, but terms like 'authentication', 'payments', and 'app deployment' are very generic and could easily conflict with other skills handling those domains on different platforms. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent concrete code examples for every API operation, but it is severely bloated with non-essential reference material (pricing tiers, tips, category lists, troubleshooting FAQs, achievement descriptions) that wastes context window space. The workflow lacks validation checkpoints for destructive operations, and the massive inline content should be split into separate reference files with the SKILL.md serving as a concise overview.
Suggestions
Extract pricing tiers, category lists, achievement types, troubleshooting, best practices, and tips into separate reference files (e.g., PRICING.md, TROUBLESHOOTING.md, BEST_PRACTICES.md) and link to them from a concise overview.
Reduce the main SKILL.md to a quick-start section plus brief API reference with one example per category, cutting at least 60% of the current content.
Add explicit validation/verification steps for destructive operations (sandbox_delete, storage_delete, app publishing) - e.g., 'Check sandbox_status before deleting' or 'Verify deployment health after template_deploy'.
Remove generic advice sections (Tips for Success, Publishing Best Practices, Cost Optimization Tips) that Claude can infer or that belong in user-facing documentation rather than an agent skill file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 700+ lines. Includes extensive lists of tips, best practices, pricing tiers, achievement types, challenge categories, and other reference material that Claude doesn't need inline. Much of this (subscription tiers, cost optimization tips, achievement types, troubleshooting FAQs) is not actionable instruction and bloats the context window enormously. | 1 / 3 |
Actionability | Every API call is shown with concrete, copy-paste-ready JavaScript examples including realistic parameters. The MCP tool call syntax is consistent and executable throughout, covering all major operations with complete argument structures. | 3 / 3 |
Workflow Clarity | The Quick Start Guide provides a reasonable 5-step sequence, but there are no validation checkpoints or error-handling feedback loops. For destructive operations like sandbox deletion, storage deletion, and app publishing, there are no verification steps. The multi-stage execution pattern lacks validation between stages. | 2 / 3 |
Progressive Disclosure | The collapsible details sections at the bottom show awareness of progressive disclosure, and there's a table of contents. However, the main body is a monolithic wall of content that should be split into separate reference files. Hundreds of lines of pricing info, tips, categories, and troubleshooting are inlined rather than referenced externally. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1158 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- ruvnet/claude-flow
- Commit
01070ed
- 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.