agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Index cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls.
$ npx -y skills add jmagly/aiwg --skill local-resource-index --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/local-resource-indexContext preview
The summary Claude sees to decide when to auto-load this skill.
Index cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls.
namespace: aiwg platforms: [all] name: local-resource-index description: Index cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls. triggers: - index local public resources with citations - build a local emergency transit or services index - publish structured local resource data
1. Register and gate every source before acquisition. 2. Select `cap`, `gtfs`, or `hsds`; retain the original payload/hash, publisher, profile/version, per-vertical required fields, selectors, mappings, and validation result. 3. Never infer absent availability, accessibility, cancellations, contacts, or eligibility. Keep `not_provided` distinct from `none`. 4. Apply domain expiry/freshness and public-scope rules. Expired active alerts, unverified publishers, fabricated contacts, and sensitive client data block. 5. Provide correction/takedown intake and retain an append-only audit chain. 6. Record the structured-data mapping and pass the record through the civic publication gate before any local publishing handoff.
A `local-resource-index` record plus `block|warn|record` findings.
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