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 fails on every dimension. It provides no information about what the skill does, when it should be used, or what domain it operates in. It reads as a placeholder rather than a functional description that could help Claude select the right skill.
Suggestions
Add concrete actions describing what scout-explorer actually does (e.g., 'Explores codebase structure, searches for files, analyzes directory layouts').
Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when the user asks to explore a project, find files, or understand codebase organization').
Replace the generic 'Agent skill for scout-explorer' framing with a domain-specific description that distinguishes this skill from others.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for scout-explorer' is entirely vague and abstract, giving no indication of 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 it's an agent skill and how to invoke it, with no explanation of purpose or trigger conditions. | 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 only actionable content is the invocation command. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic that it provides no distinguishing characteristics. 'Agent skill' could apply to virtually any skill, and 'scout-explorer' is meaningless without context about what domain or actions it covers. | 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 payload fields. It lacks a concrete workflow for how to actually perform reconnaissance (e.g., which tools to use to scan files, how to detect vulnerabilities) and instead provides only the reporting/storage templates. The scouting strategies section describes abstract concepts Claude already understands without adding actionable specificity.
Suggestions
Consolidate the repetitive memory storage examples into a single template with a table showing the different key patterns and payload fields for each discovery type (threat, opportunity, performance, etc.)
Add concrete, executable steps for how to actually perform exploration—e.g., specific file system commands, grep patterns, or tool invocations to discover code structure, vulnerabilities, and performance issues
Define a clear sequential workflow with validation checkpoints: e.g., 1) Check assignment from coordinator, 2) Explore target area using specific tools, 3) Validate findings, 4) Store to memory, 5) Report completion
Remove the generic 'Scouting Strategies' section (breadth-first, depth-first, continuous patrol) as these are abstract concepts Claude already knows, and replace with specific decision criteria for when to use each approach
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with repetitive JSON blocks that all follow the same pattern (store to memory with slightly different payloads). The skill could convey the same information in a fraction of the space. Multiple exploration patterns (codebase, dependency, performance, environment) are essentially the same template with different field names. The 'Scouting Strategies' section describes generic concepts (breadth-first, depth-first) that Claude already knows. | 1 / 3 |
Actionability | The MCP tool call patterns are concrete and show specific key/value structures, which is useful. However, the code blocks are illustrative templates rather than truly executable—they use placeholder values like '[ID]', '[timestamp]', and generic descriptions. The actual exploration logic (how to find vulnerabilities, how to map codebases) is never specified. | 2 / 3 |
Workflow Clarity | There is no clear sequenced workflow for how a scout should actually conduct reconnaissance. The 'Scouting Strategies' section lists generic steps like 'Survey entire landscape quickly' and 'Identify high-level patterns' without any concrete actions, validation checkpoints, or error recovery. There's no guidance on what to do when exploration fails or findings conflict. | 1 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of repetitive JSON examples with no references to external files and no layered structure. Content that could be templated or referenced (e.g., the common memory storage pattern) is repeated verbatim multiple times. No bundle files exist to support progressive disclosure. | 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/claude-flow
- Commit
0aac1e1
- 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.