hive-mind-advanced

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

0.99x

Quality

58%

Does it follow best practices?

Impact

99%

0.99x

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

50%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 body is highly actionable with concrete commands and code, but is held back by significant redundancy/verbosity, missing validation in batch workflows, and an inlined API reference that belongs in a separate file.

Suggestions

Collapse the repeated consensus and queen-type explanations into a single section and remove marketing-style benchmark claims to reclaim token budget.

Add explicit validation/verification steps to the swarm-spawn workflow (e.g. check `hive-mind status` output, confirm worker count, verify consensus reached before proceeding).

Move the HiveMindCore / CollectiveMemory / HiveMindSessionManager API reference into a separate `references/api.md` file and link to it one level deep, keeping only a quick-start example inline.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is noticeably verbose: consensus mechanisms and queen types are explained multiple times, performance benchmarks ('84.8% SWE-Bench solve rate') read as marketing, and several sections restate the same material.	2 / 5
Actionability	Provides many concrete, copy-paste-ready `npx claude-flow hive-mind ...` commands and JS API examples; a minor gap is the broken `createTask` call (`priority: 8,` outside an object literal) which is not valid JS.	4 / 5
Workflow Clarity	Getting Started gives a sequence (init → spawn → monitor) but there are no validation checkpoints, and spawning parallel worker swarms is a batch operation, which per the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Section structure is present and clear, but the large API Reference and bulk detail are inlined rather than split into separate reference files, and there are no local bundle files for one-level-deep navigation.	3 / 5
	Total	12 / 20 Passed

Description

66%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 conveys a clear, specific 'what' with decent natural trigger terms, but omits any explicit 'when to use' guidance, leaving the activation context implicit.

Suggestions

Add a 'Use when ...' clause naming concrete triggering situations, e.g. 'Use when orchestrating multi-agent swarms, building consensus across workers, or coordinating queen-led agent teams.'

Include a couple of natural synonyms or phrasings users might actually say (e.g. 'swarm coordination', 'agent swarm') to broaden trigger coverage.

Tighten the capability list from architectural descriptors toward user-facing actions (spawn, orchestrate, build consensus) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names several concrete capabilities — 'queen-led multi-agent coordination', 'consensus mechanisms', 'persistent memory' — covering the system's main functions with minor gaps.	4 / 5
Completeness	The 'what' is clear but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('Hive Mind', 'multi-agent coordination', 'consensus', 'collective intelligence'); a few common synonyms are missing but coverage is good.	4 / 5
Distinctiveness Conflict Risk	'Advanced Hive Mind ... queen-led multi-agent coordination' carves a fairly distinct niche with only minor overlap risk against related swarm/consensus skills.	4 / 5
	Total	15 / 20 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 (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	14 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/hive-mind-advanced/SKILL.md
Commit: 74d2a60

Reviewed: 3 days 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.