archive-index-builder - Build tiered retrieval indexes for large archives
Design, scaffold, or extend large-document retrieval indexes with tiered acquisition, deterministic extraction, provenance, and coverage expansion.
Tags
Updated: 2026-10-07Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Inspect seed URLs
- Infer corpus structure
- Ask adaptive intake questions
- Define corpus registries
- Acquire agreed source slices
- Persist raw source metadata
- Extract deterministic evidence units
- Build navigation indexes
- Promote documents across tiers
- Track undownloaded archive items
- Expand missing coverage safely
- Write archive usage guidance
Inputs
- Seed URLs
- Corpus objectives
- Output location
- Retrieval unit
- Operating mode
- Evidence contract
- Autonomy policy
- Minimum confidence
- Canonical source files
Outputs
- Archive workspace
- Raw source artifacts
- Markdown evidence artifacts
- Navigation index
- Source-chain metadata
- Archive policy configuration
- Retrieval answers with provenance