agent-agent
Agent skill for agent - invoke with $agent-agent
33
0%
Does it follow best practices?
Impact
93%
4.65xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-agent/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely poor skill description that provides essentially no useful information. It fails on every dimension: it describes no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is completely indistinguishable from any other agent-related skill.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Delegates subtasks to a sub-agent for parallel execution, manages agent coordination, and aggregates results').
Add an explicit 'Use when...' clause with natural trigger terms that describe the scenarios where this skill should be selected (e.g., 'Use when the user needs to break a complex task into subtasks, run parallel operations, or coordinate multiple agents').
Make the description distinctive by specifying the unique niche this skill fills compared to other skills, including what types of tasks or domains it handles.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for agent' is entirely vague and abstract, providing no information about what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'agent', which is overly generic and not a natural term a user would say when needing a specific capability. The invocation syntax '$agent-agent' is not a natural trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is maximally generic — 'agent skill for agent' could conflict with virtually any other agent-related skill and provides no distinguishing characteristics. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%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 conceptual whitepaper or product brochure than actionable instructions for Claude. The extensive code examples are non-executable pseudocode with undefined dependencies, inconsistent tool naming, and no validation steps. At 500+ lines it massively wastes token budget while providing almost no concrete, copy-paste-ready guidance.
Suggestions
Reduce to under 100 lines by removing conceptual explanations (GOAP, A*, PageRank, behavior trees) that Claude already understands, and eliminate marketing language entirely.
Make code examples executable by defining all referenced helper functions, using consistent MCP tool names, and providing complete minimal examples that can actually run.
Add explicit validation checkpoints to the workflow (e.g., 'Verify matrix analysis returned valid properties before proceeding to PageRank step').
Split advanced topics (multi-agent coordination, gaming AI, learning from execution) into separate referenced files and keep SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines with massive amounts of illustrative but non-executable pseudocode. Explains concepts Claude already knows (what GOAP is, what A* search is, what behavior trees are, what PageRank does). The marketing-style descriptions ('cutting edge of AI-driven objective achievement') and emoji-laden headers add no value. Much of the content is conceptual padding rather than actionable instruction. | 1 / 3 |
Actionability | Despite containing extensive code blocks, virtually none of it is executable. Functions reference undefined helpers (buildConsensusMatrix, generatePreferenceVector, canTransition, stateKey, etc.), classes extend undefined base classes (GOAPAgent), and the MCP tool calls use inconsistent naming (mcp__sublinear_time_solver vs mcp__claude_flow vs mcp__flow_nexus). The code is elaborate pseudocode dressed up as real implementations. | 1 / 3 |
Workflow Clarity | While numbered steps exist (1-5 in the Workflow section), they describe abstract algorithmic concepts rather than a clear operational workflow. There are no validation checkpoints, no error recovery feedback loops in the main workflow, and no clear sequence of 'do this, then verify, then proceed.' The dynamic replanning section describes monitoring conceptually but provides no concrete validation steps. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no external references or file structure. Everything is inlined into a single massive document with no bundle files to support it. Content that could be separated (gaming AI integration, multi-agent coordination, advanced configuration) is all crammed into one file with no navigation aids beyond markdown headers. | 1 / 3 |
Total | 4 / 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/ruflo
- Commit
619b263
- 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.