agent-agent
Agent skill for agent - invoke with $agent-agent
37
6%
Does it follow best practices?
Impact
93%
4.65xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-agent/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely poor skill description that provides essentially no useful information. It fails on every dimension: it describes no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is completely indistinguishable from any other agent-related skill.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Spawns sub-agents to handle parallel tasks, delegates work, and coordinates multi-step workflows').
Add an explicit 'Use when...' clause with natural trigger terms describing the situations where this skill should be selected.
Include domain-specific keywords that distinguish this skill from other agent-related skills to reduce conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for agent' is entirely vague and abstract, providing no information about what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of functionality. | 1 / 3 |
Trigger Term Quality | The only keyword is 'agent', which is overly generic and not a natural term a user would say when needing a specific capability. The invocation syntax '$agent-agent' is not a natural trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'agent' is extremely generic and would conflict with virtually any agent-related skill. There is nothing distinctive about this description. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose, marketing-heavy document that reads more like a product brochure than actionable instructions for Claude. The extensive code examples are largely non-executable pseudocode with undefined dependencies and inconsistent tool naming. The content would benefit enormously from being reduced to ~50 lines of core workflow with references to detailed files, removing explanatory fluff, and ensuring code examples are actually executable.
Suggestions
Reduce the main SKILL.md to a concise overview (~50-80 lines) with the core workflow steps and tool list, moving detailed code examples into separate referenced files (e.g., EXAMPLES.md, ADVANCED.md)
Make code examples actually executable by defining all referenced helper functions or replacing pseudocode with real, complete snippets that demonstrate actual MCP tool calls
Fix inconsistent MCP tool naming (mcp__claude_flow__ vs mcp__flow_nexus__, underscores vs hyphens) and verify tool names match the actual available tools
Remove marketing language and concept explanations (what GOAP is, what A* search is, what behavior trees are) - Claude already knows these concepts
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines. Massive amounts of code that are essentially pseudocode/illustrative rather than executable. Explains concepts Claude already knows (what GOAP is, what A* search is, what behavior trees are). The marketing-style language ('cutting edge of AI-driven objective achievement') wastes tokens. Much of the content is aspirational description rather than actionable instruction. | 1 / 3 |
Actionability | Despite the volume of code, almost none of it is executable. Functions reference undefined helpers (buildConsensusMatrix, generatePreferenceVector, stateKey, canTransition, etc.), classes extend undefined base classes (GOAPAgent), and MCP tool calls use inconsistent naming (mcp__claude_flow__ vs mcp__flow_nexus__ vs mcp__sublinear_time_solver__ with underscores vs hyphens). The code is elaborate pseudocode dressed up as real implementations. | 1 / 3 |
Workflow Clarity | There is a numbered workflow (steps 1-5) that provides a logical sequence from state modeling through optimization. However, there are no validation checkpoints, no error recovery feedback loops in the main workflow, and the steps blur together with massive code blocks. The dynamic replanning section mentions monitoring but lacks concrete validation gates. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Everything is inlined in one massive document - core capabilities, workflow, multi-agent coordination, gaming AI, usage examples, best practices, advanced configuration, and advanced features. This content desperately needs to be split across multiple files with a concise overview in the main skill file. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (821 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/claude-flow
- Commit
01070ed
- 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.