CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-scout-explorer

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

50

5.41x
Quality

Does it follow best practices?

Impact

92%

5.41x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

50%

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

The body delivers concrete, on-topic MCP memory-call templates for a scout agent, but it is padded with repetitive near-duplicate blocks, relies on placeholder values, and lacks validation checkpoints in its workflows. It is a reasonable single-file draft that would benefit from consolidation and verification steps.

Suggestions

Consolidate the five near-identical memory_usage blocks into one parameterized example plus a short table of distinct keys, removing repetitive boilerplate.

Replace placeholder field values ('what was found', 'mission', 'reconnaissance type') with concrete examples or clear field-spec notes so the code is copy-paste-ready.

Add an explicit validation/verification checkpoint after discovery reports (e.g., re-read the stored memory key to confirm it persisted before alerting) to satisfy the workflow-clarity bar for these operations.

DimensionReasoningScore

Conciseness

The body is mostly efficient code templates, but the ~240 lines repeat nearly identical mcp__claude-flow__memory_usage blocks across five sections with placeholder values, adding repetition rather than novel guidance.

2 / 3

Actionability

Concrete mcp__claude-flow__memory_usage call templates with specific keys and JSON field shapes are provided, but the field values are placeholders ('what was found', 'mission') rather than copy-paste-ready executable instructions.

2 / 3

Workflow Clarity

Scouting strategies are listed as numbered sequences, yet the memory-store operations that drive the whole skill have no explicit validation checkpoints; the Do/Don't list mentions verifying findings but provides no concrete validate->fix->retry loop.

2 / 3

Progressive Disclosure

Content is a single monolithic file with no bundle files or external references, but it is organized under clear headers (Reconnaissance, Exploration Patterns, Threat Detection), giving some navigable structure.

2 / 3

Total

8

/

12

Passed

Description

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.

The frontmatter description is a generic boilerplate placeholder that conveys no real capabilities, trigger conditions, or distinctiveness. It fails to tell Claude when to invoke the skill or what it actually does.

Suggestions

Replace the templated text with a concrete capability statement, e.g. 'Explores unknown codebases and territories, gathers intelligence, and reports findings via memory coordination'.

Add an explicit 'Use when...' trigger clause naming natural user phrases like 'explore a codebase', 'reconnoiter dependencies', or 'identify threats and opportunities'.

Remove the '$agent-scout-explorer' invocation token from the description and reserve it for usage instructions, keeping the description in third person.

DimensionReasoningScore

Specificity

The description is 'Agent skill for scout-explorer - invoke with $agent-scout-explorer', which names only the skill and an invocation token without describing any concrete actions the skill performs.

1 / 3

Completeness

It answers neither 'what does this do' (no capability statement) nor 'when should Claude use it' (no 'Use when...' guidance); it is a templated placeholder.

1 / 3

Trigger Term Quality

The only keyword is the invocation token '$agent-scout-explorer', which is technical scaffolding a user would never naturally say rather than a real-world trigger term.

1 / 3

Distinctiveness Conflict Risk

The 'Agent skill for X - invoke with $X' template is identical across every such skill and conveys no distinguishing niche, so it would not differentiate this skill from siblings.

1 / 3

Total

4

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/claude-flow
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.