agent-scout-explorer
Agent skill for scout-explorer - invoke with $agent-scout-explorer
39
7%
Does it follow best practices?
Impact
92%
5.41xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-scout-explorer/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely weak description that provides essentially no useful information for skill selection. It only names the skill and its invocation command without describing any capabilities, use cases, or trigger conditions. It is functionally equivalent to having no description at all.
Suggestions
Add concrete actions describing what scout-explorer actually does (e.g., 'Explores directory structures, searches for files by pattern, and maps project layouts').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user wants to explore a codebase, find files, understand project structure, or navigate directories').
Remove the invocation syntax from the description—it's operational detail, not selection criteria—and replace it with functional information that helps Claude distinguish this skill from others.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for scout-explorer' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation method, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'scout-explorer' is an internal tool name, not a term users would naturally use in requests. The invocation syntax '$agent-scout-explorer' is technical jargon. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from any other skill. Without knowing what it does, it could conflict with anything or nothing—Claude has no basis for selection. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose, repeating the same memory-store pattern six or more times with minor variations in JSON payload. It tells the scout how to report findings but never explains how to actually perform reconnaissance (which tools to use for reading files, analyzing code, checking dependencies). The workflow is abstract and lacks validation steps, making it more of a role description than an actionable skill.
Suggestions
Consolidate the repetitive MCP memory_usage examples into one canonical pattern with a table or brief list showing how the JSON payload varies by scout type (codebase, dependency, performance, etc.).
Add concrete, executable guidance on how to actually perform reconnaissance—e.g., which tools to use to list files, read code, check package.json for outdated dependencies—not just how to store results.
Define a clear sequential workflow with validation checkpoints, such as: 1) Read task assignment from memory, 2) Use file tools to explore target area, 3) Validate findings, 4) Store verified discoveries to memory, 5) Update status.
Extract the detailed JSON schemas for each scout type into a separate reference file (e.g., SCHEMAS.md) and keep SKILL.md as a concise overview with one example and links to details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~200 lines with highly repetitive JSON blocks that all follow the same pattern (store to memory with slightly different payloads). The core concept could be conveyed in a fraction of the space. Multiple exploration patterns (codebase, dependency, performance, environment) are essentially the same MCP call with different JSON schemas—one example with a note about varying the payload would suffice. | 1 / 3 |
Actionability | The MCP tool call patterns are concrete and show specific JSON schemas, which is useful. However, the code blocks are illustrative templates with placeholders (e.g., 'scout-[ID]', 'dep1', 'dep2') rather than truly executable examples, and there's no guidance on how to actually perform the reconnaissance (e.g., which tools to use to read files, analyze dependencies, or measure performance)—only how to report findings to memory. | 2 / 3 |
Workflow Clarity | There is no clear sequential workflow for conducting a scouting mission. The 'Scouting Strategies' section lists abstract steps like 'Survey entire landscape quickly' and 'Identify high-level patterns' without concrete instructions on how to do these things. No validation checkpoints exist—there's no step to verify discoveries before storing them, despite the 'Verify findings before alerting' note in Quality Standards. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of repetitive JSON examples with no references to external files and no bundle files to support it. All the detailed JSON schemas for every scout type are inlined when they could be in a reference file, and the document lacks a concise overview section that would help orient the reader. | 1 / 3 |
Total | 5 / 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.
- 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.