agent-pagerank-analyzer

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

9.44x

Quality

17%

Does it follow best practices?

Impact

85%

9.44x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-pagerank-analyzer/SKILL.md

Quality

Discovery

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 description is critically underdeveloped, providing only invocation syntax without any explanation of capabilities or usage context. It fails to help Claude understand when to select this skill, as it contains no functional description, trigger terms, or 'Use when...' guidance. The description would be nearly useless for skill selection among multiple options.

Suggestions

Add specific capabilities describing what the tool does, e.g., 'Analyzes link structures to calculate PageRank scores, identifies influential pages, and visualizes graph connectivity'

Include a 'Use when...' clause with natural trigger terms like 'page rank', 'link analysis', 'website authority', 'SEO ranking', 'graph centrality', or 'influential pages'

Remove the invocation syntax from the description (this belongs elsewhere) and replace with functional content that helps Claude understand the skill's purpose

Dimension	Reasoning	Score
Specificity	The description only mentions 'pagerank-analyzer' without explaining what concrete actions it performs. No specific capabilities like 'analyze link structures', 'calculate page rankings', or 'identify influential nodes' are listed.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides invocation syntax without any functional description or usage triggers.	1 / 3
Trigger Term Quality	The only keyword is 'pagerank-analyzer' which is a technical tool name, not natural language users would say. Missing terms like 'page rank', 'link analysis', 'SEO', 'graph analysis', or 'website ranking'.	1 / 3
Distinctiveness Conflict Risk	The tool name 'pagerank-analyzer' is somewhat specific to PageRank analysis, which provides some distinctiveness. However, without clear scope definition, it could conflict with other SEO, graph analysis, or web analytics skills.	2 / 3
	Total	5 / 12 Passed

Implementation

27%

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

This skill suffers from severe verbosity, explaining many concepts Claude already understands while burying actionable guidance in walls of descriptive text. The code examples are partially useful but often incomplete with undefined helper functions. The content would benefit greatly from aggressive trimming and restructuring into a concise overview with references to detailed documentation.

Suggestions

Reduce content by 70%+ by removing explanations of basic concepts (PageRank, community detection, graph theory) and focusing only on the specific MCP tool interfaces and their parameters

Make code examples fully executable by defining all helper functions or using concrete inline data structures instead of undefined placeholders like `load_graph_partition()`

Split content into separate files: keep SKILL.md as a brief overview with tool signatures, move detailed examples to EXAMPLES.md, integration patterns to INTEGRATIONS.md

Add explicit validation steps to workflows, especially for distributed computing operations (e.g., 'Verify partition loaded correctly before proceeding')

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (what PageRank is, what community detection is, basic graph concepts). Contains massive amounts of descriptive text that could be condensed significantly - the skill is over 300 lines when the core actionable content could fit in under 50.	1 / 3
Actionability	Contains code examples that appear executable, but many are pseudocode-like with undefined functions (e.g., `load_graph_partition()`, `identifyInfluencers()`, `extractTopRecommendations()`). The MCP tool calls show concrete syntax but lack complete, copy-paste ready examples with real data structures.	2 / 3
Workflow Clarity	Example workflows at the end list steps but lack validation checkpoints and error handling. For operations involving distributed computing and large-scale graph processing, there are no feedback loops for error recovery or explicit validation steps between stages.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline including detailed API examples, integration patterns, and application domains that should be split into separate reference documents. No clear navigation structure for finding specific information.	1 / 3
	Total	6 / 12 Passed

Validation

100%

Warnings & errors only

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: b2618f9

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.