agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
$ npx -y skills add jmagly/aiwg --skill editorial-correction-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/editorial-correction-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
namespace: aiwg platforms: [all] name: editorial-correction-review description: Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence. triggers: - correct an unsupported civic claim - prepare a correction notice and reindex plan - review a public information takedown request
1. Freeze silent edits and preserve the challenged version/hash. 2. Collect the complaint, original sources, contrary evidence, response, safety concerns, retention holds, and all downstream locations. 3. Create a linked new version and correction note. Use `withheld` during review and `canceled` only for permanent withdrawal from public reuse. 4. Update owned caches, feeds, APIs, indexes, and exports; record third-party reindex/removal as requested or observed, never guaranteed global deletion. 5. Re-run source, citation, privacy, freshness, accessibility, and publish gates; a named human approves release.
A `correction-record` artifact and completion evidence per downstream target.
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