CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-scout-explorer

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

50

5.41x
Quality

25%

Does it follow best practices?

Impact

92%

5.41x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-scout-explorer/SKILL.md
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 is well-structured and assumes Claude's intelligence, but it relies on repetitive pseudocode tool-call blocks with placeholders rather than executable code, and offers generic step lists without validation checkpoints. It is a competent but improvable monolithic skill.

Suggestions

Show the memory_usage wrapper once and then only the differing value payloads to cut the repetitive boilerplate.

Replace the pseudocode 'mcp__claude-flow__memory_usage { ... }' blocks with executable tool-call syntax or clearly justify the pseudocode format.

Add explicit validation/verification steps (e.g. confirm a discovery before alerting, deduplicate against existing keys) to the scouting workflows.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence without explaining known concepts, but the 'mcp__claude-flow__memory_usage { action: "store", key, namespace, value: JSON.stringify(...) }' wrapper is repeated ~6 times with identical boilerplate that could be shown once and then condensed to just the value payloads.

2 / 3

Actionability

The code blocks give concrete structure (specific keys, namespaces, value shapes) but use a pseudocode tool-call syntax ('mcp__claude-flow__memory_usage { ... }', not valid JS) with placeholder values like 'scout-[ID]', 'what was found', and 'codebase|documentation|dependencies', so they are not copy-paste executable.

2 / 3

Workflow Clarity

'Scouting Strategies' lists numbered sequences (Breadth-First, Depth-First, Continuous Patrol) but they are generic step lists with no validation checkpoints or error-recovery feedback loops, matching the 'steps listed but checkpoints missing' anchor.

2 / 3

Progressive Disclosure

It is a single monolithic ~240-line file with no bundle files or external references; sections are well-organized via headers, but the repetitive code blocks are inline content that could be condensed or externalized, fitting the 'some structure but could be better organized' anchor.

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 templated string that conveys no real capability information and no usage triggers, scoring at the floor across all dimensions. It should be replaced with concrete actions and explicit 'Use when...' guidance.

Suggestions

Replace the template with concrete actions, e.g. 'Explores unknown codebases, gathers intelligence on dependencies and performance, and reports findings to shared memory'.

Add an explicit trigger clause such as 'Use when reconnaissance, codebase mapping, dependency analysis, or threat/opportunity detection is needed'.

Use third-person voice and natural trigger terms instead of the 'invoke with $...' invocation syntax.

DimensionReasoningScore

Specificity

The description 'Agent skill for scout-explorer - invoke with $agent-scout-explorer' only names the skill domain and gives invocation syntax; it names no concrete actions or capabilities, matching the vague/abstract anchor rather than the 'names some actions' level 2.

1 / 3

Completeness

It answers neither 'what does this do' (only the generic 'Agent skill for scout-explorer') nor 'when should Claude use it' (no 'Use when...' clause), and the guideline caps completeness at 2 for a missing trigger clause — here 'what' is also weak.

1 / 3

Trigger Term Quality

'invoke with $agent-scout-explorer' is technical invocation syntax, not natural keywords a user would actually say; there are no natural trigger terms like 'reconnaissance', 'explore', or 'intelligence gathering'.

1 / 3

Distinctiveness Conflict Risk

The generic template phrasing 'Agent skill for X - invoke with $X' is indistinguishable from many other similarly-templated skills and would conflict with them; it lacks a clear niche.

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/ruflo
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.