hive-mind-advanced
Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory
45
17%
Does it follow best practices?
Impact
99%
0.99xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/hive-mind-advanced/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily laden with abstract buzzwords and technical jargon without specifying concrete actions or when the skill should be used. It reads more like a product marketing tagline than a functional skill description. The lack of natural trigger terms and explicit usage guidance would make it very difficult for Claude to correctly select this skill.
Suggestions
Replace abstract terms with concrete actions: specify what the skill actually does (e.g., 'Coordinates multiple agents to collaboratively solve complex tasks, aggregates responses, and resolves conflicts through voting mechanisms').
Add an explicit 'Use when...' clause with natural trigger terms users might say (e.g., 'Use when the user asks to split work across multiple agents, coordinate parallel tasks, or aggregate results from multiple sources').
Remove marketing buzzwords like 'Advanced', 'collective intelligence system', and 'queen-led' in favor of plain, descriptive language that clearly communicates the skill's purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, buzzword-heavy language ('collective intelligence system', 'consensus mechanisms', 'persistent memory') without listing any concrete actions the skill performs. There are no specific verbs describing what it actually does. | 1 / 3 |
Completeness | The description vaguely addresses 'what' (multi-agent coordination) but provides no 'when' clause or explicit trigger guidance. Both dimensions are weak, with no 'Use when...' clause present. | 1 / 3 |
Trigger Term Quality | The terms used ('Hive Mind', 'queen-led', 'consensus mechanisms') are highly technical jargon that users would almost never naturally say. No common user-facing keywords are included. | 1 / 3 |
Distinctiveness Conflict Risk | The 'Hive Mind' and 'queen-led' terminology is fairly unique and unlikely to conflict with most other skills, but the vague nature of 'multi-agent coordination' could overlap with other orchestration or agent-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but bloated reference document that tries to cover everything in a single file. It suffers from significant verbosity, explaining concepts Claude already understands, repeating information across sections, and including marketing-style content. While it provides some concrete CLI commands and code examples, the sheer volume undermines usability, and the lack of bundle files means all referenced external documentation is inaccessible.
Suggestions
Reduce content by 60-70%: remove concept explanations Claude already knows (Byzantine consensus theory, LRU cache mechanics, WAL mode), the Skill Progression section, benchmark claims, and the marketing-style overview paragraph.
Split into multiple files: move API Reference to API.md, Configuration to CONFIG.md, Troubleshooting to TROUBLESHOOTING.md, and Examples to EXAMPLES.md, keeping SKILL.md as a concise overview with clear links.
Add validation checkpoints to workflows: after `hive-mind init`, verify initialization succeeded; after `spawn`, check status; include error recovery steps for common failure modes.
Fix code examples: the `createTask` call has a syntax error (misplaced `priority` parameter outside the options object), and API examples need import paths and initialization context to be truly executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Explains concepts Claude already knows (what Byzantine fault tolerance is, what LRU caches are, what WAL mode is). Includes a 'Skill Progression' section, marketing-style benchmarks, and extensive redundancy between sections (consensus algorithms explained multiple times). The overview paragraph is pure fluff. | 1 / 3 |
Actionability | Provides concrete CLI commands and JavaScript code snippets, but many code examples are incomplete (e.g., `createTask` has a syntax error with misplaced `priority`), some are pseudocode-like with comments saying 'Automatic - no configuration needed', and the JavaScript API examples lack import paths or setup context. The mix of CLI and programmatic interfaces without clear guidance on when to use which reduces actionability. | 2 / 3 |
Workflow Clarity | The Getting Started section provides a reasonable 3-step sequence (init → spawn → monitor), but lacks validation checkpoints. There's no explicit verification after initialization, no error recovery flow for failed spawns, and the session management workflow doesn't include validation steps. For a system involving multi-agent coordination with potential failures, the absence of feedback loops is notable. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with everything inlined into a single massive file. References external docs at the bottom but no bundle files exist to support them. The API Reference, Configuration, Troubleshooting, Examples, and Advanced Topics sections all belong in separate files. The 'Related Skills' section references skills that may not exist. No actual progressive disclosure structure. | 1 / 3 |
Total | 6 / 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 (730 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/ruvector
- Commit
c2089c4
- 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.