agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer
39
11%
Does it follow best practices?
Impact
85%
9.44xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-pagerank-analyzer/SKILL.mdQuality
Discovery
7%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 skill description that essentially only names the skill and provides an invocation command. It fails to describe any concrete capabilities, lacks natural trigger terms, and provides no guidance on when Claude should select this skill. It is barely functional as a description.
Suggestions
Add concrete actions the skill performs, e.g., 'Analyzes link structures and computes PageRank scores for web pages or graph nodes, identifies most influential nodes, and visualizes ranking distributions.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about page ranking, link analysis, graph centrality, SEO ranking, web page importance, or network influence analysis.'
Remove the invocation instruction ('invoke with $agent-pagerank-analyzer') from the description field, as this is operational detail that doesn't help Claude decide when to select the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for pagerank-analyzer' is extremely vague and does not describe what the skill actually does beyond naming itself. | 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 explanation of capabilities or usage triggers. | 1 / 3 |
Trigger Term Quality | The only potentially relevant keyword is 'pagerank' which is a technical term. There are no natural user-facing trigger terms like 'rank pages', 'link analysis', 'SEO', 'graph analysis', or similar terms a user would naturally say. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'pagerank-analyzer' is at least somewhat distinctive as a niche topic, which reduces conflict risk with other skills. However, the lack of detail means it's unclear what exactly distinguishes it from other potential analysis or graph-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
14%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 descriptive content that reads more like a marketing document or capability overview than actionable instructions. While it does include some useful MCP tool call examples with parameter structures, the majority of the content consists of vague bullet-point lists of capabilities and application domains that provide no concrete guidance. The skill would benefit enormously from aggressive trimming and focusing on the actual MCP tool interfaces with executable examples.
Suggestions
Remove all descriptive bullet-point sections (Application Domains, Advanced Graph Algorithms, Performance Optimization, Integration Patterns) that describe concepts rather than provide actionable instructions—these waste tokens on things Claude already knows.
Make code examples fully executable by replacing undefined helper functions with actual implementations or concrete MCP tool calls, and ensure examples use realistic, complete parameter values.
Add explicit validation checkpoints to workflows—e.g., check convergence after PageRank computation, validate graph input format before processing, verify output score distributions.
Consolidate the skill to focus on the 4 MCP tools available, with one clear executable example per tool and a brief workflow showing how they compose together.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive bullet-point lists of capabilities, application domains, and integration patterns that Claude already understands conceptually. Sections like 'Application Domains', 'Performance Optimization', and 'Advanced Graph Algorithms' are largely descriptive padding with no actionable content. The skill could be reduced to ~25% of its length without losing useful information. | 1 / 3 |
Actionability | Provides several code examples with MCP tool calls that show concrete parameter structures, which is useful. However, many examples use undefined helper functions (e.g., `extractTopRecommendations`, `identifyInfluencers`, `load_graph_partition`) making them not truly executable. The distributed computing and GNN examples appear aspirational rather than grounded in actual available tool capabilities. | 2 / 3 |
Workflow Clarity | The 'Example Workflows' section lists high-level steps (e.g., 'Build social network graph from user interactions') without any concrete commands, validation checkpoints, or error recovery. These are abstract process descriptions, not actionable workflows. No validation or verification steps are present anywhere despite dealing with large-scale computations where convergence checks and data validation are critical. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files and no bundle files provided. All content—from basic usage to advanced algorithms to integration patterns—is dumped into a single file with no clear navigation hierarchy. Much of the descriptive content (application domains, integration patterns) could be separated or simply removed. | 1 / 3 |
Total | 5 / 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.
- Repository
- ruvnet/claude-flow
- Commit
9d4a9ea
- 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.