This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.
43
42%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/multi-agent-patterns/SKILL.mdQuality
Discovery
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 focuses almost entirely on when to use the skill (trigger conditions) but fails to explain what the skill actually does — what concrete outputs or actions it performs. The domain terms are reasonably specific to multi-agent design but could benefit from broader keyword coverage. The absence of explicit capability statements (the 'what') is the primary weakness.
Suggestions
Add explicit capability statements describing what the skill produces, e.g., 'Designs multi-agent architectures, defines agent roles and communication patterns, and evaluates whether a multi-agent approach is warranted.'
Expand trigger terms to include common variations like 'orchestration', 'agentic workflow', 'LLM agents', 'agent framework', 'tool delegation'.
Restructure to lead with concrete actions (what it does) followed by a 'Use when...' clause, matching the pattern of strong descriptions in the rubric.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (multi-agent systems) and lists several concepts (context isolation, supervisor/swarm coordination, handoffs, parallel execution), but these read more as architectural concerns than concrete actions. It doesn't specify what the skill actually does (e.g., 'designs architectures', 'generates agent configs', 'produces diagrams'). | 2 / 3 |
Completeness | The description has a 'Use when' clause ('should be used when designing multi-agent systems that need...'), which addresses the 'when'. However, the 'what does this do' part is essentially absent — it never states what actions or outputs the skill produces, only when to invoke it. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'multi-agent systems', 'handoffs', 'parallel execution', 'swarm coordination', and 'supervisor' which users in this domain might use. However, it misses common variations like 'orchestration', 'agent framework', 'LLM agents', 'agentic workflow', or 'tool use delegation'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on multi-agent systems with specific coordination patterns (supervisor, swarm, handoffs) provides some distinctiveness, but the lack of concrete actions means it could overlap with general architecture or system design skills. The phrase 'decision on whether multiple agents are justified' is somewhat distinctive. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill covers multi-agent architecture comprehensively but suffers from significant verbosity, restating concepts Claude already understands (context windows, parallelization benefits, specialization) and repeating key points across multiple sections. The actionability is moderate — some code examples exist but most are incomplete or illustrative rather than executable. The skill would benefit greatly from aggressive trimming, consolidation of repeated concepts, and moving detailed pattern descriptions into reference files.
Suggestions
Cut 50%+ of the content by removing explanations of concepts Claude already knows (what context windows are, why parallelization helps, what specialization means) and eliminating repeated points (telephone game, context isolation benefits appear 3+ times each).
Replace the vague token economics table with concrete numbers or remove it entirely — 'Higher than baseline' and 'Much higher than baseline' provide no actionable information.
Add a concrete step-by-step workflow for designing a multi-agent system (e.g., '1. Identify context isolation boundaries → 2. Choose pattern → 3. Define handoff protocol → 4. Validate with single-agent baseline → 5. Implement coordination') with explicit validation checkpoints.
Move detailed pattern descriptions, consensus mechanisms, and failure modes into separate reference files (e.g., references/patterns.md, references/failure-modes.md) and keep only concise summaries with decision criteria in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, explaining many concepts Claude already knows (what context windows are, what parallelization means, basic voting theory, what supervisors do). Sections like 'The Parallelization Argument' and 'The Specialization Argument' explain obvious concepts at length. The token economics table uses vague placeholders ('Higher than baseline', 'Much higher than baseline') that add no value. Multiple sections repeat the same points (telephone game mentioned in at least 3 places, context isolation restated repeatedly). | 1 / 3 |
Actionability | There are some concrete code examples (forward_message function, handoff protocol, transfer_to_agent_b), but most are incomplete or pseudocode-level. The research team architecture is just a text diagram. The framework considerations section mentions LangGraph, AutoGen, and CrewAI but provides zero executable code for any of them. Many sections describe what to do conceptually rather than showing how to do it with copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | The skill describes patterns and failure modes but lacks explicit step-by-step workflows with validation checkpoints. There's no clear 'do step 1, validate, then step 2' sequence for actually building a multi-agent system. The failure modes section lists mitigations but doesn't integrate them into a workflow. The Guidelines section is a flat list without sequencing. For a skill involving complex coordination with error propagation risks, the absence of validation checkpoints and feedback loops is notable. | 2 / 3 |
Progressive Disclosure | The skill references a frameworks.md file and several related skills, which is good progressive disclosure structure. However, the main file itself is monolithic with extensive inline content that could be split (e.g., the detailed pattern descriptions, consensus mechanisms, failure modes could each be separate reference files). The references section is well-structured with 'Read when' annotations, but the body carries too much detail that should be delegated to sub-files. No bundle files were provided to verify the referenced frameworks.md exists. | 2 / 3 |
Total | 7 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
25e1fa7
Table of Contents
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.