CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-pagerank-analyzer

Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer

60

9.44x
Quality

43%

Does it follow best practices?

Impact

85%

9.44x

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-pagerank-analyzer/SKILL.md

The canonical home for this skill is agent-pagerank-analyzer in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

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

The content is a well-structured, code-rich reference for PageRank analysis with concrete MCP tool examples, but it is long, somewhat repetitive, and monolithic with no progressive disclosure into separate files. Workflows lack validation checkpoints.

Suggestions

Move the bulk of the API/integration-pattern detail into a separate reference file and link to it from SKILL.md, keeping the body as a concise overview.

Deduplicate capability listings (Community Detection, Network Optimization items appear under multiple headings) and trim the repeated bolded bullet sections.

Add validation or convergence-check steps to the Example Workflows so each multi-step process has an explicit checkpoint before proceeding.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not over-explain concepts Claude already knows, but ~300 lines of repeated bulleted capability lists (e.g., 'Community Detection' appears under multiple sections) and several near-duplicate section groupings could be tightened.

3 / 5

Actionability

Concrete, executable MCP tool calls with real parameters (pageRank, analyzeMatrix, sandbox_execute, neural_train) cover the common cases; the minor gap is several examples call undefined helper functions like identifyInfluencers and extractTopRecommendations.

4 / 5

Workflow Clarity

The 'Example Workflows' sections provide clear numbered sequences (e.g., the 5-step Social Media Influence Campaign), but none include validation checkpoints or error-recovery feedback loops, and the steps are analytical rather than verified.

3 / 5

Progressive Disclosure

Section headers organize the content reasonably, but at ~300 lines everything is inlined into SKILL.md with no references to separate files, and material that could live in a reference (API details, integration patterns) is not split out.

3 / 5

Total

13

/

20

Passed

Description

28%Weight 40%Scale 1-5

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 essentially a placeholder: it names the skill and its invocation command but conveys no real capability or usage guidance. It reads as auto-generated boilerplate rather than a meaningful description.

Suggestions

Replace the description with the richer capability summary already present in the body (e.g., 'Expert agent for graph analysis and PageRank calculations using sublinear algorithms...').

Add an explicit 'Use when...' trigger clause naming natural phrases such as PageRank computation, graph/network analysis, influence ranking, or topology optimization.

Drop the 'invoke with $agent-pagerank-analyzer' invocation syntax from the description; that belongs in usage docs, not the discoverability description.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for pagerank-analyzer' names the domain but describes no concrete actions at all — it says nothing about what the skill actually does, only that it is 'an agent skill' for a named tool.

2 / 5

Completeness

It offers only a vague 'what' ('Agent skill for pagerank-analyzer') and entirely lacks any 'Use when...' or equivalent trigger guidance, so it does not answer when Claude should invoke it.

2 / 5

Trigger Term Quality

The only keyword present is the skill's own name 'pagerank-analyzer' plus the invocation syntax 'invoke with $agent-pagerank-analyzer'; natural phrases a user would say (PageRank, graph analysis, network influence) are absent.

2 / 5

Distinctiveness Conflict Risk

'pagerank-analyzer' targets a fairly specific niche with low conflict risk, but the generic 'Agent skill for X' framing does not establish clear distinguishing triggers, leaving moderate overlap ambiguity with other graph/analysis skills.

3 / 5

Total

9

/

20

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.