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 description that essentially only names the skill and its invocation command. It provides no information about what the skill does, what actions it performs, or when it should be used. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills based on user intent.
Suggestions
Add concrete actions describing what the skill does, 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, or web page importance.'
Remove the invocation instruction ('invoke with $agent-pagerank-analyzer') from the description and replace it with capability-focused language that helps Claude decide when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for pagerank-analyzer' is 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'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially relevant keyword is 'pagerank' which is buried in a tool name rather than presented as a natural trigger term. No user-facing keywords like 'rank pages', 'link analysis', 'graph analysis', or 'SEO' are included. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'pagerank' provides some niche specificity that would prevent conflicts with most other skills, but the description is so vague that it's unclear what exactly it does, which could lead to it being incorrectly selected or missed. | 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 excessively verbose, spending most of its token budget on abstract capability descriptions, domain overviews, and integration patterns that provide no actionable guidance. The few concrete code examples are partially useful but rely on undefined helper functions. The skill reads more like a marketing document or README than an actionable instruction set for Claude.
Suggestions
Cut the content by 70%+: remove sections like 'Application Domains', 'Performance Optimization', 'Advanced Graph Algorithms', and 'Integration Patterns' which are abstract bullet lists Claude already understands conceptually.
Make code examples fully executable by replacing undefined helper functions with actual implementations or concrete MCP tool calls with realistic parameters.
Add validation checkpoints to workflows: after PageRank computation, verify convergence, check score distributions, and handle error cases explicitly.
Either move detailed integration examples (Flow Nexus, Claude Flow) to separate referenced files, or remove them if they aren't core to the skill's purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive sections that describe concepts Claude already knows (community detection, graph ML, performance optimization techniques, application domains). Bullet-point lists of abstract capabilities like 'Viral Marketing: Optimize viral marketing campaign targeting' add no actionable value. The content is heavily padded with unnecessary context and could be reduced by 70%+. | 1 / 3 |
Actionability | Contains some concrete code examples with MCP tool calls and parameter structures, which is useful. However, many examples use undefined helper functions (extractTopRecommendations, identifyInfluencers, load_graph_partition) making them non-executable pseudocode. The distributed PageRank Python example won't run as written. Many sections are purely descriptive bullet lists with no concrete guidance. | 2 / 3 |
Workflow Clarity | The 'Example Workflows' section lists high-level steps like 'Build social network graph from user interactions' and 'Compute PageRank scores to identify influencers' without any concrete commands, validation checkpoints, or error recovery. No workflow includes verification steps. The multi-step processes are abstract descriptions rather than actionable sequences. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text at ~250+ lines with no references to external files. All content is inline regardless of depth or relevance. Sections like 'Application Domains', 'Performance Optimization', and 'Integration Patterns' are shallow bullet lists that either should be removed or linked to detailed external documents. No navigation structure or clear hierarchy. | 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/ruflo
- Commit
398f7c2
- 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.