agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Review long-horizon obligations, stable cores, dependencies, replacement paths, stewardship, degradation, evidence, and meaning preservation
$ npx -y skills add jmagly/aiwg --skill century-readiness-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/century-readiness-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Review long-horizon obligations, stable cores, dependencies, replacement paths, stewardship, degradation, evidence, and meaning preservation
namespace: aiwg name: century-readiness-review platforms: [all] description: Review long-horizon obligations, stable cores, dependencies, replacement paths, stewardship, degradation, evidence, and meaning preservation
Assess all nine required dimensions and produce concrete migration rehearsal candidates. Preserve missing external evidence as `NOT RUN` with a reason.
Use `aiwg century-readiness review <review.json>` for the deterministic report. Do not present the result as certification or a guarantee of archival service. Keep public local review separate from enterprise governance and board reporting.
@implements #2044
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