Schema Normalizer (NO PROSE)

Triggers & routing

• Trigger: schema normalize, jsonl contract, interface drift, join drift, 字段不一致, schema 规范化.
• Use when: you have generated C2-C4 JSONL artifacts (outline/briefs/bindings/packs/anchors) and want deterministic, stable fields before self-loops/writing.

Purpose: close a common failure mode in skills-first pipelines: schema drift across JSONL artifacts.

When fields are inconsistent (missing ids/titles, mixed citation-key formats), downstream skills start doing best-effort joins and fragile parsing. This skill makes the interface explicit and deterministic.

Inputs

• outline/outline.yml (source of truth for section/subsection ids + titles)
• Optional (for citation-key sanity): citations/ref.bib
• Default JSONL artifacts to normalize (arxiv-survey(-latex) C4 bridge):

- outline/subsectionbriefs.jsonl - outline/chapterbriefs.jsonl - outline/evidencebindings.jsonl - outline/evidencedrafts.jsonl - outline/anchor_sheet.jsonl

• Optional (run after writer packs are generated):

- outline/writercontextpacks.jsonl

Outputs

• output/SCHEMANORMALIZATIONREPORT.md (always written; PASS/FAIL + what changed)
• The processed JSONL files are normalized in place (a .bak.* is created if changes are applied).

What gets normalized

1) IDs + titles (join keys)

For any record with sub_id: "<H2>.<H3>":

• Ensure section_id exists (derived from the prefix before the dot)
• Ensure title, section_title exist (filled from outline/outline.yml)

For any record with section_id: "<H2>":

• Ensure section_title exists (filled from outline/outline.yml)

2) Citation key format (reduce parsing drift)

Within these C2-C4 JSONL artifacts, normalize citation keys so they are raw BibTeX keys (no @ prefix):

• "citations": ["smith2023", "jones2024"]

Notes:

• Final prose still uses Markdown citations: [@smith2023].
• This skill does not add/remove citations; it only normalizes formatting.

When to run

Recommended placement in arxiv-survey(-latex):

• Run after evidence-draft + anchor-sheet and before writer-context-pack + evidence-selfloop.
• This ensures outline/evidencedrafts.jsonl and outline/anchorsheet.jsonl are schema-stable before drafting packs are built.

Failure modes

• If outline/outline.yml is missing or cannot be parsed, the skill FAILs.
• If any target JSONL contains invalid JSON lines, the skill reports them and FAILs (do not proceed on corrupted artifacts).

Script (optional)

Quick Start

• uv run python .codex/skills/schema-normalizer/scripts/run.py --help
• Normalize the C4 bridge artifacts:

- uv run python .codex/skills/schema-normalizer/scripts/run.py --workspace <workspace>

All Options

• --workspace <dir>
• --unit-id <U###>
• --inputs <semicolon-separated>
• --outputs <semicolon-separated>
• --checkpoint <C#>

Examples

• Normalize the default C4 artifacts (ids/titles + citations format):

- uv run python .codex/skills/schema-normalizer/scripts/run.py --workspace <workspace> --inputs outline/outline.yml;citations/ref.bib;outline/subsectionbriefs.jsonl;outline/chapterbriefs.jsonl;outline/evidencebindings.jsonl;outline/evidencedrafts.jsonl;outline/anchorsheet.jsonl --outputs output/SCHEMANORMALIZATION_REPORT.md

• Normalize writer packs too (if you are running this after writer-context-pack):

- uv run python .codex/skills/schema-normalizer/scripts/run.py --workspace <workspace> --inputs outline/outline.yml;citations/ref.bib;outline/writercontextpacks.jsonl --outputs output/SCHEMANORMALIZATIONREPORT.md