# Template Manuscript Cross References

> |

- **Type:** Skill
- **Install:** `agentstack add skill-docxology-template-manuscript-cross-references`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [docxology](https://agentstack.voostack.com/s/docxology)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [docxology](https://github.com/docxology)
- **Source:** https://github.com/docxology/template/tree/main/docs/prompts/manuscript-cross-references
- **Website:** https://doi.org/10.5281/zenodo.19139090

## Install

```sh
agentstack add skill-docxology-template-manuscript-cross-references
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Manuscript cross-references (registry tokens)

For Pandoc-crossref `@fig:` / `[@key]` exemplars, see [`docs/guides/manuscript-semantics.md`](../../guides/manuscript-semantics.md). This skill is for **YAML registry + inline tokens**.

## Natural invoke

- "Audit [[FIG:]] tokens in actinf_policy_entanglement_lean manuscript"
- "Hard-coded section numbers in prose — tokenize them"
- "labels.yaml has orphan keys"

## Inputs to confirm

- **Scope** — `projects//manuscript/` path or project name.
- **Style** — confirm registry/token vs pure Pandoc-crossref (do not mix styles in repairs).

## Workflow

1. **Registry truth** — `refs/labels.yaml` (figures, equations, sections, theorems) and `refs/citations.yaml` or hybrid `references.bib`. Every token label must exist; every `[@citekey]` must resolve.

2. **No hard-coded numbers** — prefer `[[THMREF:…]]`, `[[SECREF:…]]`, `[[FIGREF:…]]`, `[[EQREF:…]]` over "Theorem 7.3", "§8", "Figure 2" in body prose.

3. **Captions** — YAML-stored captions may not expand `[[…]]` unless renderer documents second pass.

4. **Sync** — subsection headings and `labels.yaml` section/theorem numbers aligned; grep for stale numbers after renumbering.

5. **Bibliography** — if `99_*` uses `[[CITELIST:all]]`, do not hand-maintain a parallel list.

6. **Report** — missing/orphan/duplicate keys; hard-coded numbers to tokenize; concrete edits (file + snippet).

## Verification commands

```bash
uv run python -m infrastructure.validation.cli markdown projects//manuscript/
uv run python -m infrastructure.validation.cli prerender projects//manuscript --repo-root .
```

## When NOT to use

- **Full manuscript scaffold** → [manuscript-creation](../manuscript-creation/SKILL.md)
- **Triple-check every factual claim** → [manuscript-claim-verification](../manuscript-claim-verification/SKILL.md)

## References

- [`docs/rules/manuscript_style.md`](../../rules/manuscript_style.md)
- Project-local `manuscript/refs/README.md` when present

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [docxology](https://github.com/docxology)
- **Source:** [docxology/template](https://github.com/docxology/template)
- **License:** Apache-2.0
- **Homepage:** https://doi.org/10.5281/zenodo.19139090

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-docxology-template-manuscript-cross-references
- Seller: https://agentstack.voostack.com/s/docxology
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.