How do I install the Ingest L0 skill?

Run npx skillmds@latest add williamcorrea23/ingest-l0 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ingest L0 safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ingest L0?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ingest L0 free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ingest L0?

williamcorrea23 (@williamcorrea23) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ingest L0 by williamcorrea23 — Agent Skill

Name: Ingest L0
Author: williamcorrea23

Ingest L0

L0 bootstrap of the abap_wiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.

File contents

Ingest L0 - stub bootstrap from TADIR

Creates (or updates) the L0 stub for every custom object in the TADIR. Everything is deterministic: no sub-agents, parallelism via devclass partitioning. State lives in state/abap_wiki.db (see core/docs/01-pipeline-l0-l1.md).

When to use it

First-time initialization of the repo (empty DB).
Arrival of a new export raw/tadir/TADIR_Z_<YYYYMMDD>.XLSX.

Procedure

Shortcut: python core/src/tools/pipeline.py l0-run runs steps 1-6 as a single deterministic command (newest TADIR in raw/tadir/ or --file). The step-by-step procedure below remains the reference for diagnostics.

All commands must be run from the repo root with the venv active.

Initialize the schema (idempotent):

python core/src/tools/pipeline.py init-db

Import the TADIR (dtype=str, excludes objects already removed from the L1 queue):

python core/src/tools/pipeline.py import-tadir --file raw/tadir/<most recent TADIR>.XLSX

Resolve sources (unique in-memory index, deterministic hash):
```
python core/src/tools/pipeline.py resolve-sources
```
Create L0 stubs (all, or by devclass partition in parallel across multiple sessions):
```
python core/src/tools/pipeline.py ingest-l0            # all
python core/src/tools/pipeline.py ingest-l0 --partition ZPACKAGE   # one package
```
Idempotent: re-running on an already-processed package is a no-op.
Enqueue L1 (only analyzable types with available source):
```
python core/src/tools/pipeline.py enqueue-l1
```

Verify and commit:

python core/src/tools/pipeline.py progress
python core/src/tools/pipeline.py export-excel
python core/src/tools/pipeline.py git-commit --message "ingest L0: <export>"

Rules

Never modify raw/ (only the user stages it when updating the export).
Indexes (abap_wiki/_packages/, abap_wiki/index.md) are regenerated from queries: do not edit them manually.
If unknown TADIR types appear they are mapped to tadir-<x> and listed in output/reports/unknown-tadir-types.md (non-blocking).

---name: ingest-l0description: L0 bootstrap of the abap_wiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.---# Ingest L0 - stub bootstrap from TADIRCreates (or updates) the L0 stub for every custom object in the TADIR. Everything isdeterministic: no sub-agents, parallelism via devclass partitioning.State lives in `state/abap_wiki.db` (see `core/docs/01-pipeline-l0-l1.md`).## When to use it- First-time initialization of the repo (empty DB).- Arrival of a new export `raw/tadir/TADIR_Z_<YYYYMMDD>.XLSX`.## Procedure> Shortcut: `python core/src/tools/pipeline.py l0-run` runs steps 1-6 as a> single deterministic command (newest TADIR in `raw/tadir/` or `--file`).> The step-by-step procedure below remains the reference for diagnostics.All commands must be run from the repo root with the venv active.1. **Initialize the schema** (idempotent): ``` python core/src/tools/pipeline.py init-db ```2. **Import the TADIR** (dtype=str, excludes objects already removed from the L1 queue): ``` python core/src/tools/pipeline.py import-tadir --file raw/tadir/<most recent TADIR>.XLSX ```3. **Resolve sources** (unique in-memory index, deterministic hash): ``` python core/src/tools/pipeline.py resolve-sources ```4. **Create L0 stubs** (all, or by devclass partition in parallel across multiple sessions): ``` python core/src/tools/pipeline.py ingest-l0 # all python core/src/tools/pipeline.py ingest-l0 --partition ZPACKAGE # one package ``` Idempotent: re-running on an already-processed package is a no-op.5. **Enqueue L1** (only analyzable types with available source): ``` python core/src/tools/pipeline.py enqueue-l1 ```6. **Verify and commit**: ``` python core/src/tools/pipeline.py progress python core/src/tools/pipeline.py export-excel python core/src/tools/pipeline.py git-commit --message "ingest L0: <export>" ```## Rules- Never modify `raw/` (only the user stages it when updating the export).- Indexes (`abap_wiki/_packages/`, `abap_wiki/index.md`) are regenerated from queries: do not edit them manually.- If unknown TADIR types appear they are mapped to `tadir-<x>` and listed in `output/reports/unknown-tadir-types.md` (non-blocking).

Frequently asked questions