agentic/code/frameworks/sdlc-complete/skills/auto-provenance/SKILL.md
Generate W3C PROV-compliant provenance records automatically when agents create or modify artifacts
npx skillsauth add jmagly/aiwg auto-provenanceInstall 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.
Automatically generates W3C PROV-compliant provenance records when agents create or modify artifacts.
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
Ensures every artifact created by AIWG agents has a provenance record, maintaining an auditable chain of derivation from requirements through implementation. Implements the W3C PROV-DM Entity-Activity-Agent model automatically, without requiring agents to manually create records.
This skill activates when:
.aiwg/ or src/ directories.aiwg/working/ (temporary files).aiwg/ralph/ (loop state, not artifacts).aiwg/research/provenance/records/ (provenance about provenance would be circular)node_modules/, .git/, or build output.prov.yaml)When a tracked artifact is created or modified:
Detect artifact event
Extract derivation sources
@implements -> derivation_type: implements@tests -> derivation_type: tests@extends -> derivation_type: extends@depends -> derivation_type: depends@path -> derivation_type: derives_fromGenerate provenance record
Validate and save
@$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/schemas/provenance/prov-record.yaml.aiwg/research/provenance/records/<artifact-name>.prov.yamlReport
@-mentions serve as the primary source of derivation relationships:
integration:
mention_wiring:
source: "@-mentions in artifact content"
target: "wasDerivedFrom relationships in provenance record"
mapping:
"@implements": "implements"
"@tests": "tests"
"@extends": "extends"
"@depends": "depends"
"@source": "derives_from"
Qualified @-mentions provide relationship type information:
integration:
qualified_references:
source: "qualified @-mentions (@implements @path)"
target: "typed derivation relationships"
Phase transitions trigger provenance completeness checks:
integration:
hitl_gates:
action: validate_provenance_coverage
trigger: phase_transition
skill:
name: auto-provenance
type: passive
always_active_for:
- provenance-manager
- software-implementer
- test-engineer
- requirements-analyst
- architecture-designer
- technical-writer
- documentation-synthesizer
- security-auditor
- api-designer
file_triggers:
- pattern: ".aiwg/**/*.md"
- pattern: ".aiwg/**/*.yaml"
- pattern: "src/**/*.ts"
- pattern: "src/**/*.js"
- pattern: "test/**/*.ts"
- pattern: "test/**/*.js"
exclude:
- pattern: ".aiwg/working/**"
- pattern: ".aiwg/ralph/**"
- pattern: ".aiwg/research/provenance/records/**"
- pattern: "**/*.prov.yaml"
auto_create: true
auto_update: true
validate_on_create: true
.aiwg/research/provenance/records/<name>.prov.yaml.aiwg/research/provenance/index.yaml.aiwg/reports/provenance-report.mddata-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`.