hive-mind-advanced

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory

1.88x

Quality

42%

Does it follow best practices?

Impact

100%

1.88x

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/hive-mind-advanced/SKILL.md

Quality

Content

35%

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

The skill is rich with concrete commands and code but is far too verbose, explains knowledge Claude already has, repeats content, and keeps everything in a single monolithic file. Some code examples are also not executable as written.

Suggestions

Cut definitional padding (LRU cache, WAL mode, object pooling, Byzantine fault tolerance explanations) and remove the duplicate restating of consensus algorithms and config blocks to respect the context window.

Fix non-executable code samples — correct the createTask() call syntax and replace comment-only pseudocode blocks with runnable snippets.

Split the API Reference, Troubleshooting, and Advanced Topics into separate reference files under references/ and link to them one level deep, turning SKILL.md into a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~700-line body explains concepts Claude already knows (LRU cache, WAL mode, object pooling, Byzantine fault tolerance) and restates consensus algorithms and config blocks, padded with marketing language like 'represents the pinnacle of multi-agent coordination'.	1 / 3
Actionability	It offers many concrete CLI commands and mostly executable JS snippets, but several examples are non-runnable (e.g., `priority: 8` placed invalidly inside the createTask() call) or comment-only pseudocode, leaving guidance incomplete.	2 / 3
Workflow Clarity	Getting Started gives a clear init-spawn-monitor sequence, but batch/multi-agent operations carry no validation checkpoints or error-recovery feedback loops, capping workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	No bundle files exist to offload detail to, and the body is a monolithic ~700-line document keeping API reference, troubleshooting, and advanced topics inline rather than splitting them into one-level-deep reference files.	2 / 3
	Total	7 / 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 conveys a clear, domain-specific capability but reads as a feature enumeration without explicit 'when to use' guidance. It is competent but lacks the trigger clause and concrete action verbs needed for a top score.

Suggestions

Add an explicit 'Use when ...' clause stating the natural situations that should trigger this skill (e.g., 'Use when coordinating many specialized agents on a shared objective or when the user mentions hive mind, swarms, or queen-worker coordination').

Lead with concrete action verbs (spawn, orchestrate, build consensus, persist shared memory) instead of a feature list to lift specificity toward the multi-action anchor.

Include common natural phrasings users would say ('hive mind', 'swarm of agents', 'multi-agent consensus') alongside the technical terms to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete subsystems ('queen-led multi-agent coordination', 'consensus mechanisms', 'persistent memory') but enumerates features rather than concrete actions the skill performs, so it stops short of the multi-action anchor 3.	2 / 3
Completeness	It states what the system does but provides no 'Use when...' or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Terms like 'hive mind', 'multi-agent coordination', and 'consensus' are relevant but lean technical; common natural-language variations a user would actually say are missing and there is no trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	The queen-led hive-mind niche is fairly distinct yet overlaps with sibling multi-agent/swarm skills listed in the body and lacks a distinct trigger, so it could still trigger the wrong skill.	2 / 3
	Total	8 / 12 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 (713 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/hive-mind-advanced/SKILL.md
Commit: d069fff

Reviewed: about 10 hours 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.