agent-adaptive-coordinator

Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator

1.51x

Quality

31%

Does it follow best practices?

Impact

100%

1.51x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

42%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 a monolithic, buzzword-heavy spec that describes an aspirational architecture rather than instructing the agent what to do. Concrete MCP commands are buried among long pseudocode classes and marketing-style diagrams, with no reference files to offload detail and no executable decision workflow.

Suggestions

Cut the emoji architecture diagram, 'Core Intelligence Systems' buzzword lists, and 'Performance Metrics & KPIs' sections — they state what the coordinator is, not what to do; keep only actionable decision rules.

Replace the pseudocode Python classes (TopologyOptimizer, AdaptiveAgentAllocator, PredictiveLoadManager) with a concrete, ordered decision procedure: analyze workload -> apply the topology switching conditions (which are the most useful content) -> monitor -> rollback triggers, with explicit validate-checkpoints.

Move the MCP command reference and the topology switching conditions into a references/ file (e.g. references/topology-conditions.md), leaving SKILL.md as a concise overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The ~360-line body is heavily padded: emoji ASCII architecture art, buzzword section headers ('Self-Organizing Coordination', 'Emergent Behaviors'), KPI lists, and long Python classes that describe behavior rather than add non-obvious knowledge; it is above anchor 1 only because some MCP command blocks carry real information.	2 / 5
Actionability	The MCP bash commands (e.g. 'mcp__claude-flow__swarm_scale --swarmId="${SWARM_ID}" --targetSize="12"') are concrete, but the large Python blocks are pseudocode calling undefined methods (self.predict_performance, self.collect_performance_metrics, self.analyze_task_requirements), matching the 'pseudocode instead of executable code' anchor; it is not anchor 2 because usable command-level guidance does exist.	3 / 5
Workflow Clarity	The 4-phase 'Topology Transition Protocols' and rollback triggers provide a recognizable sequence, but the phases are descriptive labels rather than runnable steps, and validation checkpoints are implicit (no 'validate, then fix and retry' loop) — matching 'sequence present but checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Section headers give the document structure (above anchor 2's 'minimal structure'), but all ~360 lines — algorithms, MCP command reference, KPI lists, transition protocols — are inlined in SKILL.md with zero external reference files (no references/, scripts/, or assets/ exist), fitting 'content that should be separate is inline'.	3 / 5
	Total	11 / 20 Passed

Description

21%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 is pure boilerplate: it identifies the skill's domain but conveys nothing about its capabilities, when to use it, or how it differs from sibling skills. It would almost never be selected on merit because it contains no natural trigger language or concrete actions.

Suggestions

Replace the boilerplate with a concrete capability summary, e.g. 'Dynamically switches swarm topology (hierarchical/mesh/ring/hybrid) based on real-time performance metrics; handles agent allocation, predictive scaling, and topology rollback.'

Add an explicit 'when' clause: 'Use when coordinating multi-agent swarms where workload characteristics are unknown or change mid-task, or when static topology choice is unclear.'

Include natural trigger terms users would actually say (swarm, multi-agent, orchestration, topology, load balancing, scaling) instead of the '$agent-adaptive-coordinator' invocation token.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for adaptive-coordinator' names the domain but lists no concrete actions or capabilities whatsoever, sitting between the vague (1) and minimal-actions (2) anchors; it names a domain, so it is not entirely abstract, but it has even less action content than the anchor-2 example 'Processes PDF files'.	2 / 5
Completeness	The 'what' is vague ('Agent skill for adaptive-coordinator' says nothing about what it actually does) and the 'when' is entirely absent — no 'Use when...' clause or equivalent, matching anchor 2 ('vague what and no when') and below anchor 3, which requires a clear 'what'.	2 / 5
Trigger Term Quality	The only content is boilerplate ('Agent skill for ...') and a technical invocation token ('invoke with $agent-adaptive-coordinator'); there are no natural keywords a user would actually say, matching the 'no natural keywords; only technical jargon or entirely generic language' anchor.	1 / 5
Distinctiveness Conflict Risk	Naming a specific niche (adaptive swarm coordination) keeps it from being generic (anchors 1-2), but with no trigger terms or distinguishing capabilities stated, it could still overlap with other coordinator/orchestration skills, so it does not reach 'mostly distinct'.	3 / 5
	Total	8 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-adaptive-coordinator/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.