agent-scout-explorer

Agent skill for scout-explorer - invoke with $agent-scout-explorer

5.41x

Quality

Does it follow best practices?

Impact

92%

5.41x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-scout-explorer/SKILL.md

Quality

Content

14%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is heavily padded with repetitive JSON template blocks that all demonstrate the same pattern (storing data via MCP memory tool) with minor field variations. It lacks actual exploration logic — it only defines reporting formats, not how to perform reconnaissance. The abstract strategy sections and integration points add little actionable value and consume significant token budget.

Suggestions

Consolidate all the JSON memory store examples into one canonical template with a field reference table, reducing the body by ~60%.

Add concrete, executable workflow steps for at least one exploration type (e.g., codebase scouting: which tools to use, what commands to run, how to traverse directories).

Include validation checkpoints in the workflow — e.g., verify a discovery exists before storing a threat alert, or confirm file paths before reporting locations.

Move the repetitive per-category JSON templates to a separate reference file (e.g., TEMPLATES.md) and keep only the core protocol and one example in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with repetitive JSON blocks that all follow the same pattern (memory store calls). The skill could convey the same information in a fraction of the space. Many sections (Codebase Scout, Dependency Scout, Performance Scout, etc.) are essentially the same template with different field values. The 'Scouting Strategies' and 'Integration Points' sections describe abstract concepts Claude already understands.	1 / 3
Actionability	The memory store call patterns are concrete and show the exact MCP tool invocations with specific key/namespace structures, which is useful. However, the actual exploration logic (how to scan a codebase, how to detect vulnerabilities, how to measure performance) is entirely absent — only the reporting format is specified. The code blocks are templates with placeholder values rather than executable examples.	2 / 3
Workflow Clarity	There is no clear sequential workflow for how to conduct a scouting mission end-to-end. The 'Scouting Strategies' section lists abstract steps like 'Survey entire landscape quickly' without concrete actions. There are no validation checkpoints, no error handling, and no feedback loops for verifying discoveries before reporting them, despite the 'verify findings before alerting' instruction 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 template variations are inline when they could be in a reference file, with the SKILL.md providing just the core protocol and one representative example.	1 / 3
	Total	5 / 12 Passed

Description

0%Scale 1-3

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 to use it, 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 and symbols, maps project dependencies').

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to explore a project, find files, understand code structure, or navigate a repository').

Replace the invocation syntax instruction with functional description — Claude needs to know *what* the skill does and *when* to use it, not just how to invoke it.

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' with an invocation command, 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 generic ('agent skill') that it provides no distinguishing characteristics. Without knowing what it does, it could conflict with any other skill, and Claude would have no basis for selecting it appropriately.	1 / 3
	Total	4 / 12 Passed

Validation

100%

Warnings & errors only

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
Path: .agents/skills/agent-scout-explorer/SKILL.md
Commit: 913f9ea

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.