change

Inspect graph changes over time and ontology version diffs in Semantica. Uses ContextGraph.state_at for point-in-time graph state and change_management.VersionManager for ontology versioning.

Quality

71%

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 ./plugins/skills/change/SKILL.md

Quality

Content

83%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, actionable, and surfaces genuinely non-obvious API quirks, but it omits validation/verification steps around the destructive migrate and version-create operations.

Suggestions

Add an explicit validation checkpoint after migrate_ontology (e.g. re-run compare_versions or verify expected node count) before treating the migration as complete.

Show a verify step for create_version (e.g. confirm via list_versions/get_latest_version) so the write path has a feedback loop.

If the provenance sqlite path is created fresh, note a quick existence/consistency check so batch provenance writes are verifiable.

Dimension	Reasoning	Score
Conciseness	Lean and efficient: it assumes competence and spends tokens only on non-obvious API gotchas ('load_from_file does not expand ~', 'compare the id fields, not the dicts', 'storage_path is passed to sqlite3.connect() unexpanded') with no concept padding.	5 / 5
Actionability	Fully executable, copy-paste-ready Python blocks with imports cover the common cases (state_at, id-set diffing, version list/compare/diff/migrate, provenance history).	5 / 5
Workflow Clarity	Subcommands are cleanly sectioned, but write/migrate operations (migrate_ontology, create_version) and the sqlite provenance store are shown with no validation or verification checkpoint, which caps workflow clarity at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	Good structure with a clear disambiguating overview table and sectioned subcommands, plus a one-level cross-reference to /semantica:temporal; not a 5 because nothing is actually split into reference files and the doc is a single flat layout.	4 / 5
	Total	17 / 20 Passed

Description

58%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 well-scoped to a distinct Semantica niche, but it lacks an explicit 'when to use' trigger clause and leans on API jargon over natural user phrases.

Suggestions

Add a 'Use when ...' clause naming natural trigger phrases (e.g. 'Use when the user asks what changed in the graph since a date, or to compare ontology versions').

Soften API jargon in the trigger portion by including synonyms users actually say ('graph history', 'what changed between versions', 'diff ontologies').

Optionally surface the core actions (create, compare, migrate versions) so capability coverage reads as comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete mechanisms ('Inspect graph changes over time', 'ontology version diffs', 'ContextGraph.state_at', 'change_management.VersionManager'); not a 5 because it does not enumerate the underlying actions (create/compare/migrate versions).	4 / 5
Completeness	A clear 'what' is present but there is no 'Use when...' or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('graph changes', 'version diffs', 'point-in-time graph state') but they lean toward API jargon (state_at, VersionManager) and miss the natural synonyms/variations a user would actually say.	3 / 5
Distinctiveness Conflict Risk	A clear Semantica niche (graph changes vs ontology version diffs) with distinct triggers; not a 5 because of plausible overlap with closely related Semantica skills such as temporal/provenance.	4 / 5
	Total	14 / 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/change/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.