Name: paper-spine
Rating: 63.2 (1 reviews)
Author: WUBING2023

paper-spine

Write, rewrite, or build a paper or report (journal, conference, report, review, competition) end to end, then output LaTeX/PDF/Word. The main PaperSpine entry point that orchestrates every step.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./dist/codex/skills/paper-spine/SKILL.md

The canonical home for this skill is paper-spine in WUBING2023/PaperSpine

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exceptionally actionable, well-gated orchestrator with concrete commands and explicit validation feedback loops at every stage, and its references/ and scripts/ bundles back the cited paths. Its main weakness is conciseness — routing and hard rules are stated in multiple places, inlining detail that could live entirely in the playbooks.

Suggestions

Consolidate the duplicate command-routing tables and the Word/citation hard rules to a single canonical location; reference playbooks instead of restating in Stage 8, Stage 10, and the Final Audit.

Move the full pandoc command lines and citation-mechanism detail into references/latex.md, keeping only the gate invocation inline.

Trim repeated prose restatements of the anti-skip and resume-first rules to a single authoritative Non-Negotiable Route section.

Dimension	Reasoning	Score
Conciseness	The ~480-line body re-explains routing rules twice (two command-routing tables plus per-stage repetition), restates the Word/citation hard rules across Stage 8, Stage 10, and the Final Audit, and inlines substantial detail that the rubric says belongs in references — noticeable padding even though most content is relevant.	2 / 5
Actionability	Every stage gives concrete, copy-paste-ready bash commands (progress_check.py --gate, integrity_audit.py, pandoc invocations, word_guard.py) and names exact artifact paths and config fields, covering the common cases with executable specificity.	5 / 5
Workflow Clarity	The Non-Negotiable Route lays out a clear 12-stage sequence with an explicit gate after each stage, anti-skip and resume-first rules, feedback loops (gate fails -> route back to the stage), and a final hard-gate checklist with named PASS/FAIL criteria.	5 / 5
Progressive Disclosure	Structure is good: an overview with a one-level-deep references/ playbook per stage and confirmed that all referenced files and scripts actually exist in the bundle, but some detail (full pandoc command flags, citation-mechanism rules) is inlined in SKILL.md rather than kept purely in the playbooks.	4 / 5
	Total	16 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description conveys a clear, fairly specific niche (research paper/report orchestration across named scenes with LaTeX/PDF/Word output) but omits an explicit 'Use when...' trigger clause and could itemize concrete actions more granularly. It is strong but not maximal.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g. 'Use when the user wants to write, rewrite, or build an academic paper or report for a journal, conference, review, or competition, then export to LaTeX/PDF/Word').

List concrete producing actions more granularly (draft sections, assemble bibliography, compile PDF, generate Word) rather than clustering them under 'Write, rewrite, or build'.

Clarify distinctiveness from generic document skills by foregrounding the academic/research-paper framing first.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Write, rewrite, or build a paper or report', 'output LaTeX/PDF/Word') and enumerates scenes (journal, conference, report, review, competition), but the writing actions are clustered rather than individually itemized like the score-5 anchor.	4 / 5
Completeness	Has a clear 'what' (orchestrates every step of writing/rewriting/building a paper and outputs LaTeX/PDF/Word), but the 'when' is only weakly implied — there is no explicit 'Use when...' clause, which the guidelines cap at 4 and lean toward 3-4.	4 / 5
Trigger Term Quality	Includes natural terms users say ('paper', 'report', 'journal', 'conference', 'review', 'competition', 'rewrite', 'build') with good synonym coverage, but lacks the most generic lay phrasings and file-extension triggers a user might type.	4 / 5
Distinctiveness Conflict Risk	The research-paper-writing niche plus enumerated scenes make it mostly distinct from generic document skills, though 'report' and 'review' carry some overlap risk with general document or code-review skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: WUBING2023/PaperSpine
Path: dist/codex/skills/paper-spine/SKILL.md
Commit: 1fe46f0

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.