Skip to content
Back to skills

Method Submission Package

ASecurity

Assembles a journal submission package from the SAP, outputs, tables, figures, reporting checklist, and provenance. Use when the user needs a submission bundle.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 17, 2026
datapythonbash

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned October 17, 2026

npx -y skills add sajor2000/methodsmith --skill method-submission-package --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Method Submission Package?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Method Submission Package
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sajor2000-method-submission-package/badge)](https://www.skillsdirectory.com/skills/sajor2000-method-submission-package)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: method-submission-package
description: "Assembles a journal submission package from the SAP, outputs, tables, figures, reporting checklist, and provenance. Use when the user needs a submission bundle."
argument-hint: "[optional: --out-dir manuscript --format quarto]"
---

# Manuscript Package Builder

> **Run the commands below from the user's project root.** The `SKILL_DIR` anchor locates the bundled script; `--project-root` and `--out-dir` stay project-relative.


## Skill Value

- **Problem it solves:** Manuscript submission packages fail when required outputs, checklist items, and provenance are scattered.
- **Use when:** The user needs a journal/manuscript package, submission bundle, or final report handoff.
- **Output:** A manuscript package manifest with included artifacts, missing items, and readiness notes.
- **Ask only if:** Only when target journal, package scope, or required artifacts are unclear.
- **Do not do:** Do not invent missing tables, figures, or manuscript claims.
- **Interaction:** Check repo/config/chat evidence first. Ask one decision-changing question at a time; use the current harness's blocking question UI when available, otherwise present numbered choices and wait.

Build a traceable manuscript package manifest. The skill wires known study artifacts together; it does not invent manuscript prose or scientific claims.

## Workflow

1. Confirm the SAP exists and is the correct study contract.
2. Confirm Table 1 and figure manifests exist, or surface them as blockers.
3. Include selected reporting checklist files from the guideline registry.
4. Include preregistration and model-card artifacts when applicable.
5. If the deliverable is a Word manuscript, run `method-citations` before
   final packaging and include the field-bearing DOCX master plus its citation
   ledger; a flattened DOCX or static bibliography is not the editable master.
6. **Number gate.** Load the `method-numbers` skill and run its `check` on the manuscript sources, rendered copies, and tables (it reads `analysis/numbers/registry.json`). A `FAIL` exit, or a gate that could not run, blocks readiness: quote its `file:line: reason: token` lines as printed, and never add a result to the allowlist or edit the registry to make it pass.
7. Run:

```bash
SKILL_DIR="<absolute path of the directory containing this SKILL.md>";
python3 "$SKILL_DIR/scripts/build_package_manifest.py" --project-root . --out-dir manuscript --format quarto
```

The builder independently runs the number gate and records its status in the manifest. It defaults to the project-local `analysis/numbers/method_numbers.py` installed by `method-numbers`; if that helper is absent, pass `--number-gate` with the absolute script path obtained by loading that skill. Use repeated `--number-input` arguments for an explicitly scoped set of manuscript/table files. Missing tooling, no reportable occurrences or a failing gate produces blocked readiness, even when all publication artifacts exist.

8. The script writes `checklists`, `registry_packages`, and `reproducibility` as empty lists and rewrites the manifest on every run; after the final run, add the artifacts from steps 3-4 to those lists. For a Word deliverable, also set the optional `word_master` and `citation_ledger` paths from the step 5 `__CE_CITATION_LEDGER__` handoff (`docx=` and `path=`).
9. Review `manuscript/package-readiness-report.md` before calling the package submission-ready.
10. The script never sets `ready-for-signoff`. The agent sets `readiness: ready-for-signoff` only after step 8, when the script result is `ready-with-review`, the step 6 number gate printed `PASS`, and the user names the human reviewer who reviewed the readiness report; record that name in `signoff_reviewer`. Never set it from a `blocked` result or without a named reviewer. A rerun resets readiness, so repeat steps 6-10 after any rerun.

## Quarto Path

Load the `method-notebook-standards` skill before creating or materially extending executable Quarto analysis notebooks that feed the manuscript package.

For Quarto projects, create or update a package manifest that expects:

- `manuscript/manuscript.qmd`
- `manuscript/package-manifest.json`
- `manuscript/tables/`
- `manuscript/figures/`
- `manuscript/supplement/`
- `manuscript/checklists/`

For non-Quarto projects, generate the same package manifest without forcing a conversion; the script writes the `manuscript.qmd` section stub only for `--format quarto`.

## References

@./references/package-manifest-schema.yaml

@./references/quarto-manuscript-template.md

@./references/journal-package-checklist.md

Files in this skill

  • SKILL.md4.5 KB
  • references/journal-package-checklist.md396 B
  • references/package-manifest-schema.yaml1 KB
  • references/quarto-manuscript-template.md446 B
  • scripts/build_package_manifest.py6.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.