semantica

Semantica full-stack knowledge graph skill for context graphs, decision intelligence, explainability, extraction, reasoning, visualization, ontology, provenance, policy, and export workflows.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/semantica/SKILL.md

Quality

Content

53%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 body is a well-structured, concise task-selection overview with useful prompt patterns, but it offers little executable workflow detail, repeats domain coverage across two lists, and references bundle files that are not present.

Suggestions

Collapse the overlapping 'When to use' and 'What this Skill contains' lists into a single consolidated section to remove redundancy.

Add at least one concrete, executable workflow (e.g., a sample SPARQL query or extraction snippet) for the most common task type.

Either supply the referenced reference/script files or remove the 'read additional files or scripts' guidance so navigation is not dangling.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows, but the 'When to use this Skill' and 'What this Skill contains' lists restate the same domain coverage, so it could be tightened; this sits at 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	It provides concrete prompt-pattern examples and a 3-step usage process, but gives no executable workflow detail for the actual extraction/analysis/reasoning tasks, so guidance is incomplete rather than fully actionable.	3 / 5
Workflow Clarity	The 'How Claude should use this Skill' section lists a clear 3-step sequence but has no validation checkpoints or feedback loops; since no destructive/batch operations are described, the cap does not apply, leaving it at 'steps listed but checkpoints missing'.	3 / 5
Progressive Disclosure	The body is well-organized into clear sections and behaves as a concise overview, but it references 'additional files or scripts' that do not exist in any bundle directory, a minor organization gap that keeps it just below 5.	4 / 5
	Total	13 / 20 Passed

Description

56%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 description covers a broad, well-branded knowledge-graph niche with good natural trigger terms, but relies on a list of domain nouns rather than concrete actions and omits any explicit 'when to use' guidance.

Suggestions

Lead with concrete action verbs (e.g., 'Build, analyze, and export knowledge graphs...') instead of a noun list.

Add an explicit 'Use when...' clause naming user-facing triggers like knowledge graphs, entities/relations, or decision intelligence.

Include common synonyms or file extensions (e.g., .json, .rdf, GraphML) to strengthen trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description is a noun-heavy list of domains ('context graphs, decision intelligence, explainability, extraction, reasoning...') with no concrete action verbs, matching the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because it lacks even 1-2 explicit concrete actions.	2 / 5
Completeness	It clearly states what the skill does ('full-stack knowledge graph skill for ... workflows') but provides no 'Use when...' clause or explicit trigger guidance, so per the guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	It includes natural terms users would say ('knowledge graph', 'context graphs', 'decision intelligence', 'explainability', 'reasoning', 'extraction'), giving good keyword coverage; it stops short of 5 because it omits common synonyms and file extensions like .json, .rdf, or graphml.	4 / 5
Distinctiveness Conflict Risk	The 'Semantica full-stack knowledge graph skill' framing carves a clear, distinct niche with minor overlap risk against general data/ML skills; it is not a 5 because several broad terms (extraction, reasoning, policy) could overlap with adjacent skills.	4 / 5
	Total	13 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: semantica-agi/semantica
Path: .claude/skills/semantica/SKILL.md
Commit: 2a303cf

Reviewed: 1 day 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.