Runtime index cache design

Skill jukrap/ai-agent-playbook/skills/ai-harness/runtime-index-cache-design

Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.

Install

npx -y skills add jukrap/ai-agent-playbook --skill runtime-index-cache-design

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when designing or reviewing runtime reports, indexes, graphs, caches, artifact schemas, invalidation, canon promotion, generated evidence, or local-only runtime storage.

SKILL.md

1.1 KB, as published. Nobody here has run it

Runtime Index Cache Design

Use this as the primary AI harness skill for generated runtime evidence, cache/index design, and artifact contracts.

Workflow

Define the artifact purpose, schema, target scope, freshness signal, storage location, and whether it is preview-only or applied.
Keep runtime output local-only and separate from durable memory until reviewed.
Add invalidation, stale evidence, source file, and target path rules before relying on a cache or index.
Verify with schema checks, no-write previews, apply behavior when needed, public-doc hygiene, and canon promotion boundaries.

Reference

Read references/runtime-artifact-contracts.md for generated report, index, graph, schema, and evidence envelope checks.