agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Explain dataset, record, field, index, graph, and export lineage using evidence-bearing bounded queries.
$ npx -y skills add jmagly/aiwg --skill dataset-trace --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/dataset-traceContext preview
The summary Claude sees to decide when to auto-load this skill.
Explain dataset, record, field, index, graph, and export lineage using evidence-bearing bounded queries.
namespace: aiwg name: dataset-trace description: Explain dataset, record, field, index, graph, and export lineage using evidence-bearing bounded queries. version: 1.0.0 platforms: [all] aliases: [dataset lineage, provenance explain, trace record] triggers: [where did this record come from, explain this result, trace this field, show dataset lineage, prove this index source]
Delegate to `aiwg dataset lineage <dataset-or-record-ref> --json`; use `aiwg dataset show <ref> --json` for referenced contracts. Report stable logical and revision identities, run and schema bindings, assertion basis, method, confidence, privacy, and evidence locators. Clearly label gaps and bounded-query limits.
Do not infer provenance from graph adjacency or search success. Never expose source values or credentials. Identify indexes, embeddings, graphs, caches, and Fortemi shards as derived/regenerable and hand questionable evidence to Dataset Provenance Reviewer.
Reusable project context and specialist workflows for the AI tools you already use. Plan software, coordinate specialist reviews, prepare campaigns, investigate incidents, organize research, curate media, and maintain operational knowledge.
Repo: jmagly/aiwg
Crash-resilient external agent loop with state persistence and CI/CD integration
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Enable agent loops to learn from similar past tasks and share patterns across loops
Query and manage the executable feedback debug memory
Execute tests on generated code and iterate until passing