CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-collective-intelligence-coordinator

Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator

51

1.74x
Quality

26%

Does it follow best practices?

Impact

94%

1.74x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-collective-intelligence-coordinator/SKILL.md

The canonical home for this skill is agent-collective-intelligence-coordinator in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 reasonably well-structured and directive but relies on buzzword framing, offers template/pseudocode rather than copy-paste-ready guidance, and lacks the validation checkpoints required for its continuous memory/consensus operations. It sits around the midpoint of the rubric.

Suggestions

Trim the persona opener and buzzword framing ('neural nexus of the hive mind', 'distributed cognitive processes'); lead directly with the protocols Claude must execute.

Make the memory-usage code blocks copy-paste ready with real key/namespace values and replace placeholder unions like 'mesh|hierarchical|adaptive', or convert abstract bullets such as 'Apply weighted voting' into concrete executable steps.

Add explicit validation/feedback checkpoints to the consensus and memory workflows — e.g., verify quorum was reached before storing a decision, and retry on synchronization failure — which are required for these batch/continuous operations.

DimensionReasoningScore

Conciseness

The body is mostly efficient with short bullet lists and code blocks, but opens with buzzword-laden framing ('neural nexus of the hive mind system', 'distributed cognitive processes') that could be trimmed, matching the 'mostly efficient but includes some unnecessary explanation' anchor.

3 / 5

Actionability

Memory-usage code blocks give concrete templates, but they use placeholder values ('mesh|hierarchical|adaptive', Date.now()) and the consensus/load-balancing sections are abstract bullets ('Apply weighted voting', 'Resolve conflicts through Byzantine fault tolerance') rather than executable steps, matching the 'some concrete guidance but incomplete; pseudocode instead of executable code' anchor.

3 / 5

Workflow Clarity

Sequences exist (the 30-second memory loop and handoff patterns), but validation/verification checkpoints are absent throughout; per the rubric cap, batch/continuous operations without validation cannot score above 3.

3 / 5

Progressive Disclosure

The body is well-organized into clear sections (Core Responsibilities, Coordination Patterns, Memory Requirements, Integration Points) with no nesting and appropriately scoped inline content; it lacks references but none are strictly needed, matching the 'good structure; most content appropriately placed' anchor.

4 / 5

Total

13

/

20

Passed

Description

0%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 frontmatter description is a non-descriptive templated placeholder that fails to convey what the skill does or when to trigger it; a substantive description exists only in a duplicate, ignored second frontmatter block. All four dimensions score at the floor.

Suggestions

Replace the templated description with a concrete third-person statement of capabilities, e.g. 'Orchestrates distributed cognitive processes, synchronizes collective memory, and builds consensus across agents'.

Add an explicit 'Use when…' clause with natural trigger phrases users would say, e.g. 'Use when coordinating multi-agent consensus, synchronizing hive memory, or balancing cognitive load across agents'.

Remove the duplicate second frontmatter block and consolidate into a single frontmatter so the substantive description is the one the skill system actually loads.

DimensionReasoningScore

Specificity

The description is the templated placeholder 'Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator', which names no concrete actions and is pure boilerplate, matching the 'Entirely vague; no concrete actions' anchor.

1 / 5

Completeness

It states neither what the skill does (no capability description) nor when to use it (no 'Use when…' clause), so both 'what' and 'when' are missing, matching anchor 1.

1 / 5

Trigger Term Quality

'invoke with $agent-collective-intelligence-coordinator' is an invocation command, not a natural phrase a user would say; there are no natural keywords, only technical jargon, matching anchor 1.

1 / 5

Distinctiveness Conflict Risk

The 'Agent skill for X - invoke with $X' template is entirely generic and would apply to virtually any skill, creating maximal overlap/conflict risk, matching anchor 1.

1 / 5

Total

4

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.