agent-scout-explorer
Agent skill for scout-explorer - invoke with $agent-scout-explorer
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-scout-explorer50
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 92%
↑ 5.41xAgent success when using this skill
Validation for skill structure
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 only a name and invocation command without any explanation of capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Add concrete actions describing what scout-explorer actually does (e.g., 'Explores codebase structure, discovers file relationships, maps project architecture').
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user wants to understand project layout, find files, or explore unfamiliar codebases').
Remove the invocation syntax from the description and replace with functional content - invocation details belong elsewhere, not in the selection-critical description field.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for scout-explorer' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command with no functional information. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'scout-explorer' which is technical jargon, not a natural keyword users would say. No domain-relevant terms are included. | 1 / 3 |
Distinctiveness Conflict Risk | Without any description of capabilities or domain, this could conflict with any other skill. The name 'scout-explorer' provides no meaningful differentiation. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for a scout agent with clear categorization of responsibilities and structured JSON examples for memory coordination. However, it suffers from repetitive patterns that could be consolidated, placeholder syntax instead of executable examples, and missing validation/verification steps for reconnaissance operations. The integration points mention other agents without providing navigation to their documentation.
Suggestions
Replace placeholder syntax ([ID], [timestamp]) with concrete example values to make the JSON patterns copy-paste ready
Consolidate the repetitive memory_usage patterns into a single template with variations, reducing token count
Add validation steps for discoveries - e.g., 'verify file exists before reporting location' or 'confirm threat with secondary check before alerting'
Extract the detailed JSON schemas into a separate SCHEMAS.md reference file and link to it from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy - multiple similar JSON patterns that could be consolidated, and explanatory text like 'the eyes and sensors of the hive mind' that doesn't add actionable value. | 2 / 3 |
Actionability | Provides concrete JSON structures for memory operations, but uses placeholder syntax (scout-[ID], [timestamp]) rather than executable examples. The MCP tool calls appear to be pseudocode format rather than actual invocation syntax. | 2 / 3 |
Workflow Clarity | Lists exploration strategies (breadth-first, depth-first, continuous patrol) with numbered steps, but lacks validation checkpoints. No feedback loops for verifying discoveries or handling failed reconnaissance operations. | 2 / 3 |
Progressive Disclosure | Content is organized into clear sections with headers, but everything is inline in one file. The 'Integration Points' section references other agents but doesn't link to their documentation. Could benefit from separating detailed JSON schemas into reference files. | 2 / 3 |
Total | 8 / 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.
- 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.