CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-pagerank-analyzer

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

61

9.44x
Quality

45%

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
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 a long, monolithic feature catalog anchored by a few concrete MCP code examples. It is padded with low-value capability enumerations, has abstract workflows without validation checkpoints, and uses no progressive disclosure to separate files despite its length.

Suggestions

Trim the bullet-list capability enumerations (Application Domains, Integration Patterns, Performance Optimization) to keep the body lean; move exhaustive catalogs into a reference file.

Make code examples fully executable by defining or noting the placeholder inputs (edgeWeights, socialNetworkAdjacency, load_graph_partition), and add convergence/validation checks to the PageRank workflows.

Split detailed usage scenarios and advanced algorithms into references/ files (e.g. EXAMPLES.md, ALGORITHMS.md) and reference them one level deep from a concise overview in SKILL.md.

DimensionReasoningScore

Conciseness

The ~290-line body contains concrete code examples but is heavily padded with capability-enumeration bullet lists (Application Domains, Integration Patterns, Performance Optimization) that add little actionable value, fitting the mostly-efficient-but-could-be-tightened anchor rather than the lean anchor.

2 / 3

Actionability

Several JavaScript examples use real MCP tool calls with concrete parameters, but they rely on undefined placeholders (edgeWeights, socialNetworkAdjacency, load_graph_partition()) and roughly half the sections are non-actionable bullet lists, matching the some-concrete-guidance-but-incomplete anchor.

2 / 3

Workflow Clarity

The Example Workflows sections list numbered 1-5 sequences, but the steps are abstract ("Build social network graph from user interactions") with no validation checkpoints or error-recovery feedback loops, matching the steps-present-but-validation-gaps anchor.

2 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ all absent) and the entire 290-line body is a single monolithic file with clear section headers but no file splitting or signaled references, so content that should be separate (detailed examples, domain catalogs) is all inline.

2 / 3

Total

8

/

12

Passed

Description

40%

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 real frontmatter description is a generic invocation wrapper that names the niche but states no concrete capabilities and gives no usage trigger guidance. Note also the body contains a duplicate, malformed frontmatter block holding a richer description that is not the active frontmatter.

Suggestions

Rewrite the frontmatter description to lead with concrete actions, e.g. "Compute PageRank scores, analyze network influence, and optimize graph/topology structures for large-scale networks."

Add an explicit "Use when..." clause naming natural trigger terms users would say: "Use when analyzing social/web graphs, computing PageRank, or optimizing network and swarm topologies."

Remove the duplicate frontmatter block embedded in the body so there is a single, well-formed description.

DimensionReasoningScore

Specificity

The frontmatter description is "Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer", which names only the domain and an invocation token but lists zero concrete actions (no mention of computing PageRank, graph analysis, or network optimization), matching the vague/no-actions anchor.

1 / 3

Completeness

It weakly states what the skill is ("agent skill for pagerank-analyzer") but provides no "Use when..." trigger guidance, so per the missing-trigger clause completeness is capped at 2.

2 / 3

Trigger Term Quality

It contains the relevant keyword "pagerank" but phrases it as the jargon token "$agent-pagerank-analyzer" and omits natural variations a user would say ("graph analysis", "network analysis", "PageRank computation"), fitting the some-relevant-keywords-but-missing-common-variations anchor.

2 / 3

Distinctiveness Conflict Risk

The explicit "$agent-pagerank-analyzer" invocation token and PageRank niche give it some distinctiveness, but the generic wrapper phrasing could still overlap with other graph-analysis skills, matching the somewhat-specific-but-could-overlap anchor.

2 / 3

Total

7

/

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.