agent-scout-explorer
Agent skill for scout-explorer - invoke with $agent-scout-explorer
39
7%
Does it follow best practices?
Impact
92%
5.41xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-scout-explorer/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a label with an invocation command and provides zero useful information about the skill's purpose, capabilities, or appropriate usage context. It fails on every dimension because it neither describes what the skill does nor when it should be selected. Claude would have no basis for choosing this skill from a list of available options.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Explores and scouts codebases to map file structures, identify dependencies, and summarize module purposes').
Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when the user asks to explore a repository, understand project structure, or navigate unfamiliar code').
Remove the invocation syntax ('$agent-scout-explorer') from the description—this is implementation detail, not selection criteria—and instead focus on the skill's unique value proposition to distinguish it from other skills.
| 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 mcp__claude-flow__memory_usage pattern with minor variations across 7+ code blocks. It lacks a coherent workflow—there's no sequenced process for how a scout should actually conduct exploration, just isolated templates. The scouting strategies sections are abstract bullet lists that don't provide actionable guidance, and the entire document could be condensed significantly by showing one template pattern and a table of different discovery types/schemas.
Suggestions
Consolidate all memory store examples into one template with a table showing different key patterns, categories, and required fields instead of repeating the full JSON block 7+ times.
Add a concrete end-to-end workflow: e.g., 1) Read task assignment from memory, 2) List directory structure, 3) Store codebase map, 4) Verify stored data by retrieving it, 5) Report completion—with actual tool calls sequenced.
Replace the abstract 'Scouting Strategies' bullet lists with concrete decision criteria (e.g., 'If target_area is a full codebase, use breadth-first: run `find . -type f | head -50` first, then...').
Move the detailed JSON schemas for each discovery type (threat, opportunity, performance, etc.) into a separate SCHEMAS.md reference file, keeping only the core reconnaissance protocol inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with repetitive JSON templates that all follow the same pattern (store to memory with slightly different payloads). The skill could be reduced to 1/3 its size by showing one template and listing the different key/value schemas. Many sections (Environmental Scanning, Performance Metrics, Scouting Strategies) add bulk without adding unique actionable information. | 1 / 3 |
Actionability | Provides concrete MCP tool call patterns with specific JSON schemas, which is useful. However, the examples use placeholder values (scout-[ID], [timestamp]) and aren't truly executable—they're JavaScript-style pseudocode for what are actually MCP tool calls, not real JavaScript. The exploration strategies (breadth-first, depth-first) are vague numbered lists without concrete commands. | 2 / 3 |
Workflow Clarity | No clear end-to-end workflow is defined. The skill presents isolated templates for different discovery types but never sequences them into a coherent exploration process. There are no validation checkpoints, no feedback loops for verifying findings, and no clear decision points for when to escalate vs. continue exploring. The 'Scouting Strategies' section lists abstract steps without concrete implementation. | 1 / 3 |
Progressive Disclosure | Monolithic wall of repetitive JSON templates with no references to external files and no clear hierarchy. All content is inline at the same level of detail. The document is over 150 lines of nearly identical memory store patterns that could be organized into a compact overview with a separate reference for schemas. | 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
f547cec
- 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.