provenance

Trace data lineage, source attribution, audit trails, and W3C PROV-O export in Semantica graphs. Uses ProvenanceManager.

Quality

81%

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

Quality

Content

87%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 lean and highly actionable with executable code for each subcommand, and it is well-structured for a self-contained skill. Its main weakness is the absence of any validation feedback loop connecting the supersede/export operations to the integrity check.

Suggestions

Add an explicit feedback loop, e.g. after 'invalidate' or 'export', recommend running 'check --strict' to verify the provenance store integrity.

For the export workflow, sequence the steps: build/export, then validate with 'check', then surface errors before delivering the regulator-facing artifact.

Dimension	Reasoning	Score
Conciseness	Lean code snippets with terse, load-bearing inline comments and no concept-explanation padding; assumes Claude's competence and every token earns its place.	5 / 5
Actionability	Every subcommand ships executable, copy-paste Python with real imports, constructor args, and method calls covering the common cases.	5 / 5
Workflow Clarity	Subcommands are independently clear one-liners but there is no multi-step sequence or validation feedback loop tying supersede/export to the 'check' integrity command.	3 / 5
Progressive Disclosure	No bundle files exist; the body is cleanly organized by one-level '## subcommand' headers with no nesting and no need for external references.	5 / 5
	Total	18 / 20 Passed

Description

75%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 is specific and clearly niche-scoped but omits any 'when to use' trigger guidance, which caps its completeness. Trigger-term coverage is good though missing the natural 'provenance' synonym.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when tracing where data came from, auditing changes, or producing regulator-facing provenance exports.'

Include the natural term 'provenance' and synonyms like 'data origin' or 'history' alongside the technical 'W3C PROV-O'.

Dimension	Reasoning	Score
Specificity	Lists four distinct concrete actions — 'Trace data lineage, source attribution, audit trails, and W3C PROV-O export' — giving comprehensive coverage of provenance tasks.	5 / 5
Completeness	Clearly states what the skill does but lacks any 'Use when...' trigger clause; the rubric caps completeness at 3 when explicit trigger guidance is absent.	3 / 5
Trigger Term Quality	'data lineage', 'source attribution', and 'audit trails' are natural user terms, but 'W3C PROV-O' is jargon and the common synonym 'provenance'/'data origin' is missing.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to 'Semantica graphs' provenance, a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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: plugins/skills/provenance/SKILL.md
Commit: 05aec19

Reviewed: 3 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.