Agent SkillVerified publisher
@spboucher/citation-check
Checks that every in-text citation in a Markdown or LaTeX manuscript has a bibliography entry, and the reverse.
- Latest version
- v1.0.1
- Licence
- MIT
- Updated
- 2 h ago
Agent SkillPublisher identity verifiedNo findings from static checks
@spboucher/manuscript-peer-reviewv1.0.1
Peer-review protocol for LaTeX and Markdown manuscripts: deterministic audit script, five review roles, adversarial verification of findings, anchored rubric, referee report and decision letter templates.
- downloadable
- installable
- executable
- Version
- 1.0.1
- Published
- Nov 10, 2026
- Licence
- MIT
- Archive
- 608 kB
- Files
- 19
- Examples
- 2
Install
Installing only copies or configures. Nothing is executed for you. The Skills CLI verifies the checksum before writing files.
Examples
2 screenshots · from the release archiveClaude Code1 example
Referee-style reading backed by the audit (Claude Code)
The skill runs its audit script on a test manuscript with planted defects, then reports the most serious problems with file and line. Real session, Claude Code 2.1.322 with Fable 5.2, with version 1.0.0 installed from this registry; inputs are test fixtures.
Prompt given to Claude CodeUse the manuscript-peer-review skill on paper.tex: run its audit script, then give me, as a referee would, the 5 most serious problems with file:line and the hygiene score. Do not edit anything. At most 14 lines.
Codex1 example
Referee-style reading backed by the audit (Codex)
The skill runs its audit script on a test manuscript with planted defects, then reports the most serious problems with file and line. Real session, Codex CLI 0.167.1 with GPT-6.1-Sol, with version 1.0.0 installed from this registry; inputs are test fixtures.
Prompt given to CodexUse the manuscript-peer-review skill on paper.tex: run its audit script, then give me, as a referee would, the 5 most serious problems with file:line and the hygiene score. Do not edit anything. At most 14 lines.
Screenshots supplied by the publisher. The registry serves them from the release archive and does not verify what they show.
Documentation
manuscript-peer-review
An Agent Skill for reviewing a scholarly manuscript (LaTeX or Markdown) with a fixed protocol: a deterministic audit first, then five independent role reviews, adversarial verification of every finding, an anchored scoring rubric and an author-facing report.
The protocol exists to prevent the usual failures of machine-assisted review: findings that quote text which is not in the manuscript, references described without being opened, "wrong" where "not shown" was meant, and a long undifferentiated list in place of the two or three comments a decision turns on.
Contents
| Path | Purpose |
|---|---|
SKILL.md | The rules, the eight stages, the finding format, the limits |
references/roles.md | What each of the five roles reads for, and how to delegate them |
references/procedure.md | Each stage in detail, including verification and revision checks |
references/rubric.md | Seven dimensions, anchored levels, weights, caps, how to report scores |
references/templates.md | Intake note, referee report, decision letter, replication checklist, ledger, response table |
references/finding-codes.md | The 67 codes of the audit script and what to check before reporting each |
scripts/manuscript.mjs | Command-line audit tool, JSON or text output |
scripts/lib/ | The audit engine (shared with the manuscript-audit-mcp server) |
No dependencies beyond Node.js 20+. No network access, no API key, no LaTeX installation.
Install
shell
skills install @spboucher/manuscript-peer-review --client claude-code # or codex, cursor, generic-agent-skills
The script
shell
node scripts/manuscript.mjs audit paper.tex --text # every check
node scripts/manuscript.mjs audit paper.tex --root .. --min-severity warning
node scripts/manuscript.mjs citations paper.md --bib refs.bib
node scripts/manuscript.mjs scaffold paper.tex > report.md # report skeleton
node scripts/manuscript.mjs compare v1/paper.tex v2/paper.tex # revision check
node scripts/manuscript.mjs codes # all finding codes
Exit code 0 when no finding reaches the --fail-on level (default error), 2 when one does,
1 on a usage or read error. Files are read only from --root (default: the directory of the
manuscript), symbolic links included.
Tested
node --test skill-tests/ in the source repository: the skill follows the Agent Skills
specification, every referenced file exists, the engine is byte-identical to the MCP package
(whose own suite checks each audit against manuscripts with planted defects), the engine imports
nothing outside Node.js, and the command-line tool is exercised on the same fixtures (output,
exit codes, root confinement).
The protocol itself (roles, rubric, templates) is a method, not a measured instrument: no claim is made that its scores are calibrated against editorial outcomes.
Limits
- The script reads LaTeX and Markdown source only: no PDF, no Word files, no images, no data.
- It compiles nothing and looks nothing up. A complete, well-formed reference can still be wrong or non-existent; opening the source is the reviewer's job.
- About half of its checks are heuristics on English wording and are labelled as such.
- An empty audit never means a manuscript is correct.
Licence
MIT.
Files
19 files · 751 kB unpackedSelect a file to preview it. Files are shown as plain text and never executed.
Security & permissions
Declared permissions
- filesystem:read
Static checks
No advisory findings from static-1.0.0 on Nov 10, 2026. 9 informational notes.
Static checks are advisory. They never certify that a package is safe. Compatibility entries are publisher claims unless marked verified.
Compatibility
- claude-code · claimed
- codex · claimed
- cursor · claimed
- generic-agent-skills · claimed
Versions
2 releases · immutable| Version | Published | Size | SHA-256 | State |
|---|---|---|---|---|
| 1.0.1latest | Nov 10, 2026 | 608 kB | 53816acf4153… | published |
| 1.0.0 | Nov 10, 2026 | 58 kB | 22e3044059e0… | published |
Release notes for v1.0.1
Adds screenshots of real Claude Code and Codex sessions (examples/). No code change.
Publication history
- release.publish@spboucher/manuscript-peer-review@1.0.1by Simon-Pierre Boucher
- release.publish@spboucher/manuscript-peer-review@1.0.0by Simon-Pierre Boucher
- artifact.create@spboucher/manuscript-peer-reviewby Simon-Pierre Boucher
More agent skills
- Agent SkillVerified publisher
@spboucher/hello-skill
Minimal example skill: greets the user and explains how Agent Skills are structured.
- Latest version
- v1.0.1
- Licence
- MIT
- Updated
- 2 h ago
- Agent SkillVerified publisher
@spboucher/excel-model-workbook
Build, audit and grade Excel model workbooks: layout standard, dependency-free command-line auditor (errors, hard-coded numbers, broken patterns, circular references, controls, stale values) and rubric-based grading aid.
- Latest version
- v1.0.1
- Licence
- MIT
- Updated
- 2 h ago