Skill

ingest-production

Ingests processed litigation or eDiscovery productions like DAT/OPT/TEXT/IMAGES sets or Bates-numbered volumes into Retriever workspaces using Python tools and SQLite.

Python

SQLite

data-engineering

database

npx claudepluginhub sdemyanov/retriever

Tool Access

This skill uses the workspace's default tool permissions.

Preview

> Operates under `retriever:routing`. If the user's intent actually fits a different tier — another `retriever:*` skill, a Tier 2 slash, a Tier 3 `tools.py` subcommand, or (last resort) direct DB access — stop and re-route against the ladder before continuing.

SKILL.md

Similar Skills

ingest

Ingests, indexes, imports, loads, or refreshes files and folders into Retriever workspaces. Bootstraps if needed, chooses ingest mode, and summarizes results.

retriever

Ingest Docs

Ingests PDF datasheets or reference manuals into the embedded docs search index via ingest_docs tool. Reports chunks ingested and tables found.

bitwise-embedded-docs

create-vault

Creates Ampi-ready SQLite vaults from document folders (md, txt, docx, doc) or tables, with FTS5 keyword search, optional sparse semantic search, search_schema, and amplify_search_manifest for Ampi tools.

1 file

amplify

Stats

Stars10

Forks0

Last CommitMay 7, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Retriever Production Ingest

Use this skill when the user says things like:

"ingest this production"

"load this DAT/OPT set"

"index this Bates production"

"run ingest-production"

Load order

Execution rules

Confirm or infer both the workspace root and the candidate production root.

For a newly selected workspace, always run python3 skills/tool-template/tools.py workspace status --quick <workspace> before the first ingest. For already-known workspaces, run it whenever runtime state is unclear.

If workspace init or the first ingest fails with SQLite WAL, journal-mode, mount, or sandbox wording, stop normal production-ingest execution and follow the mounted/sandboxed SQLite bootstrap troubleshooting.

Do not conclude the workspace is unsupported from df, mount, or host filesystem labels alone.

Existing DB writes do not prove fresh bootstrap will succeed; distinguish existing-DB behavior from fresh-create behavior on the exact target .retriever/retriever.db path.

Follow the shared ingest preflight in ../workspace/workspace.md before running workspace-local commands. That contract handles missing tools, clean-but-stale auto-upgrades, user-modified tool protection, and mounted-path bootstrap troubleshooting without changing the chosen production-ingest intent.

Validate that the target looks like a supported processed production root, not just a loose folder of files.

For normal Cowork execution, prefer the bounded plain ingest facade and pass the production root as a scoped path:

python3 skills/tool-template/tools.py ingest <workspace> --recursive --path <production-root-relative-path> --budget-seconds 35

Continue with next_recommended_commands while more_work_remaining: true; stop only on completed, failed, or canceled.

Run ingest-production only when the user explicitly asks for that command, when running outside the Cowork time limit, or when debugging production-only parity.

Do not fall back to loose-file-only ingest. Plain ingest without --file-types should detect and route the production through the production pipeline.

Summarize created, updated, unchanged, and retired logical documents.

Call out family reconstruction, linked page images, docs missing linked text, docs missing linked images, and docs missing linked natives.

Note that produced Bates values become control_number and that linked TEXT/, IMAGES/, and NATIVES/ files remain source parts rather than top-level documents.