hive-mind-advanced

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

Quality

41%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/hive-mind-advanced/SKILL.md

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 rich with executable commands and a clear progression ladder, but it is far too long and inlines an entire API reference and config catalog that belongs in separate reference files. Destructive/batch operations lack validation checkpoints, and the external reference links are broken placeholders.

Suggestions

Move the API Reference, Configuration, and Performance Metrics sections into separate files under references/ and leave only a concise overview plus one-level-deep links in SKILL.md.

Add explicit validation/verify checkpoints to batch and destructive workflows (e.g., check `hive-mind status` after spawning, confirm consensus outcome before proceeding, verify memory health after GC).

Fix or remove the malformed 'References' links (the URLs are broken placeholder strings) and trim verbose explanatory sections like 'Neural Pattern Training' that add no actionable content.

Dimension	Reasoning	Score
Conciseness	The ~700-line body extensively enumerates concepts, config blocks, and API surfaces Claude could derive from the CLI itself, with padded sections like 'Neural Pattern Training' containing only vague comments and redundant config examples; it is noticeably verbose beyond what the skill needs.	2 / 5
Actionability	It provides many concrete, copy-pasteable npx commands and JS snippets covering init, spawn, status, consensus, memory, and session management, with only minor gaps (some JS examples are partial object literals rather than fully runnable code).	4 / 5
Workflow Clarity	Getting-started steps are sequenced (init, spawn, monitor) and there is a 'Skill Progression' ladder, but batch/destructive operations like spawning swarms, stopping sessions, and memory GC lack explicit validation or verify-then-proceed checkpoints, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the body inlines what should be separate material — a full API reference, config schemas, troubleshooting, and benchmarks — as a monolithic wall with only section headers; the 'References' links are malformed placeholders, so navigation is poor.	2 / 5
	Total	11 / 20 Passed

Description

36%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 clearly identifies the skill's niche but is written as a feature catalog rather than user-facing trigger guidance: it lacks a 'Use when...' clause and leans on internal jargon ('queen-led', 'collective intelligence') that users would rarely say verbatim. Adding explicit trigger phrases and concrete invocable actions would lift completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming natural user phrases (e.g., 'Use when coordinating many agents on one objective, running a swarm, or needing consensus across workers').

Reword around terms users actually say ('coordinate multiple agents', 'swarm of workers', 'agents voting on a decision') instead of internal jargon like 'queen-led' and 'collective intelligence'.

Lead with concrete invocable actions (spawn swarms, run consensus votes, persist shared memory) before architectural framing.

Dimension	Reasoning	Score
Specificity	The description names the domain (multi-agent coordination) and a few concrete mechanisms ('queen-led coordination', 'consensus mechanisms', 'persistent memory'), but these are architectural categories rather than concrete user-facing actions; it lists 2-3 components but is not comprehensive.	3 / 5
Completeness	There is a clear 'what' (advanced multi-agent coordination system) but no 'when' clause or equivalent trigger guidance telling Claude when to invoke this skill; per the rubric a missing 'Use when...' clause caps completeness at 3, and here even the 'what' leans abstract, placing it at 2.	2 / 5
Trigger Term Quality	Terms like 'hive mind', 'queen-led', 'collective intelligence', and 'consensus' are internal jargon unlikely to be spoken verbatim by a user in need; it lacks the natural phrases a user would actually say, sitting just below the midpoint.	2 / 5
Distinctiveness Conflict Risk	'Hive Mind', 'queen-led', and 'consensus mechanisms' carve a fairly distinct niche unlikely to collide with unrelated skills, with only minor overlap risk against generic multi-agent or coordination skills.	4 / 5
	Total	11 / 20 Passed

Validation

81%

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 — 13 / 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
relative_links	Relative link issues: 4 suspicious	Warning

	Total	13 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/hive-mind-advanced/SKILL.md
Commit: b14c79e

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.