agent-agent
Agent skill for agent - invoke with $agent-agent
42
Quality
13%
Does it follow best practices?
Impact
93%
4.65xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-agent/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no meaningful information about capabilities, use cases, or triggers - only a circular reference ('agent skill for agent') and an invocation command. This would be essentially unusable for skill selection among multiple options.
Suggestions
Replace the circular description with specific concrete actions the skill performs (e.g., 'Spawns sub-agents to handle parallel tasks, coordinates multi-step workflows, delegates specialized work')
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user needs to run multiple tasks in parallel, coordinate complex workflows, or delegate subtasks')
Include distinguishing details that separate this from other potential agent-related skills to reduce conflict risk
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for agent' is completely abstract and provides no information about what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. The only guidance is an invocation command '$agent-agent' which doesn't explain functionality or usage context. | 1 / 3 |
Trigger Term Quality | The only keyword is 'agent' repeated twice, which is overly generic and technical jargon. No natural user language or specific trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'agent' is extremely generic and could conflict with any agent-related skill. There are no distinguishing characteristics or specific triggers to differentiate this from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is severely bloated, treating SKILL.md as a comprehensive reference document rather than a concise overview. It explains well-known algorithms (A*, PageRank, behavior trees) that Claude already understands, includes extensive illustrative code that isn't truly executable, and lacks the progressive disclosure structure needed for a skill of this complexity. The content would benefit from being reduced to ~100 lines with clear pointers to separate reference files.
Suggestions
Reduce to a concise overview (~50-100 lines) with a quick-start example, moving detailed code examples to separate reference files (e.g., WORKFLOWS.md, EXAMPLES.md, API.md)
Remove explanations of concepts Claude already knows (GOAP theory, A* algorithm, PageRank, behavior trees) and focus only on project-specific tool usage and patterns
Make code examples truly executable by including all helper functions or replacing with complete, minimal working examples
Add explicit validation checkpoints to workflows, especially for the multi-agent coordination and replanning sections (e.g., 'Verify swarm initialization succeeded before spawning agents')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~800+ lines with extensive explanations of concepts Claude already knows (GOAP, A*, PageRank, behavior trees). Contains massive code blocks that are largely illustrative rather than actionable, and repeats similar patterns multiple times. | 1 / 3 |
Actionability | Provides concrete code examples with specific MCP tool calls, but the code is largely illustrative/pseudocode rather than truly executable. Many functions reference undefined helpers (buildDependencyMatrix, stateKey, etc.) and the examples lack complete context for actual use. | 2 / 3 |
Workflow Clarity | Presents numbered workflow sections (1-5) but lacks explicit validation checkpoints. The 'Dynamic Replanning' section mentions OODA loops but doesn't provide clear verification steps. No explicit 'validate before proceeding' patterns for the complex multi-step operations described. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline despite being far too long for a SKILL.md overview. No clear navigation structure - just endless sections of code examples that should be split into separate reference documents. | 1 / 3 |
Total | 6 / 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
b2618f9
- 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.