plugins/sdlc/skills/provenance-create/SKILL.md
Create a W3C PROV-compliant provenance record for an artifact
npx skillsauth add jmagly/aiwg provenance-createInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create a provenance record for a new or existing artifact, establishing its Entity-Activity-Agent chain.
When invoked, create provenance record:
Read artifact
Determine metadata
--agent flag or infer from context--derived-from flagsGenerate URN identifiers
urn:aiwg:artifact:<relative-path>urn:aiwg:activity:<type>:<name>:<sequence>urn:aiwg:agent:<agent-name>Create provenance record
@$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/provenance/prov-record.yamlValidate record
Save record
.aiwg/research/provenance/records/<artifact-name>.prov.yamlReport
[artifact-path] - Path to artifact (required)--derived-from [paths...] - Explicit derivation sources--activity [type] - Activity type: generation, modification, refactoring, testing, review, derivation (default: generation)--agent [name] - Agent that created the artifact (default: inferred)--output [path] - Custom output path for provenance record--no-validate - Skip schema validationThis skill's persistence flows through resolveStorage('provenance'). On the default fs backend provenance records live at .aiwg/provenance/. To redirect into Obsidian, Logseq, Fortemi, or another backend, configure roots.provenance or backends.provenance in .aiwg/storage.config (#934).
aiwg provenance path # resolved root
aiwg provenance list --prefix activities/
aiwg provenance get activities/2026-04-28-deploy.json
echo '{"@context":"...","activity":"..."}' | aiwg provenance put activities/x.json
data-ai
Report which research-corpus radar sidecars are overdue for refresh. Computes staleness (days since last refresh vs the cadence window) for every radar, sorted most-overdue-first. Runs via `aiwg corpus radar-status`.
data-ai
Aggregate research-corpus radar sidecars into a corpus or per-cluster freshness report — totals, overdue count, per-cluster / per-GRADE / per-trajectory breakdowns, an overdue table, and per-radar rationale snippets. Runs via `aiwg corpus radar-report`.
testing
Scaffold radar/freshness sidecars for research-corpus REFs. Pulls title/authors from the citation sidecar and GRADE from the analysis doc, defaults the refresh cadence from GRADE and the cluster from a corpus-local map, and stamps documentation/radar/REF-XXX-radar.md. Runs via `aiwg corpus radar-init`.
data-ai
Compute an entity's publication trajectory — per-year paper counts, topic drift, hot-streak detection (≥3 consecutive A-grade years), and career phase. Runs via `aiwg corpus profile-temporal`.