paper-spine

Build, rewrite, audit, submit, revise, or transfer scholarly papers end to end, producing verified LaTeX/PDF/Word and target-specific publication packages.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./paperspine5/core/01_PaperSpine4/src/skill/SKILL.md

Quality

Content

71%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 content is highly actionable and workflow-clear, with explicit gates and copy-paste commands across all 12 stages plus verified one-level-deep reference playbooks. Its weakness is verbosity: editorial philosophy and policy language are restated across stages and could be offloaded to reference files.

Suggestions

Move the repeated editorial/provenance philosophy ('Operating Principle', 'Editorial North Star', restated Chinese-language rules) into a dedicated reference file and keep the body to routing + stage gates.

Consolidate the duplicated Word/pandoc guard commands (which appear in Stages 8, 10, and 12) into a single referenced snippet to reduce token cost.

Tighten the 'Required Configuration' and 'Standard Artifacts' tables by referencing `references/intake.md` for the long field list rather than inlining it fully.

Dimension	Reasoning	Score
Conciseness	The ~725-line body reiterates policy philosophy and re-explains internal model concepts ("research-writing workflow, not a prose patcher", repeated provenance/Chinese-language rules restated in multiple stages) that pad the file well beyond what an intelligent agent needs, though each section is individually coherent.	2 / 5
Actionability	It provides concrete, copy-paste-ready bash commands and gate scripts for every stage (e.g. exact `progress_check.py --gate <stage>`, pandoc invocations, `publication_cycle.py assemble` with full argument signatures), covering the common execution cases.	5 / 5
Workflow Clarity	A clear 12-stage sequence with explicit per-stage validation gates, resume/anti-skip rules, and feedback loops (gate fails -> route back to stage, re-run gate) gives robust error-recovery checkpoints for these batch/destructive publication operations.	5 / 5
Progressive Disclosure	The body is an orchestrator overview with a routing table and stage table pointing to real one-level-deep `references/*.md` playbooks (all verified to exist); structure is good, but several policy/philosophy sections are inlined that could live in their own reference files.	4 / 5
	Total	16 / 20 Passed

Description

63%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 is specific, action-oriented, and clearly scoped to scholarly publication, with strong concrete verbs and deliverables. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers, e.g. 'Use when the user asks to write, rewrite, submit, revise, rebut, or transfer a scholarly paper, or to build a LaTeX/PDF/Word publication package.'

Include a few more natural synonyms and file extensions (e.g. 'manuscript', '.tex', 'rebuttal', 'journal transfer') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Build, rewrite, audit, submit, revise, or transfer") plus concrete deliverables ("verified LaTeX/PDF/Word and target-specific publication packages"), with minor gaps in coverage rather than comprehensive enumeration of every sub-action.	4 / 5
Completeness	The "what" is clear and concrete, but there is no explicit "Use when..." clause or equivalent trigger guidance stating when Claude should invoke this skill; the guideline caps completeness at 3 when explicit trigger guidance is absent.	3 / 5
Trigger Term Quality	Natural scholarly verbs and nouns users would say ("rewrite", "audit", "submit", "revise", "transfer", "scholarly papers", "LaTeX", "PDF", "Word") are present and relevant, missing only a few common synonyms/extensions like ".tex" or "manuscript".	4 / 5
Distinctiveness Conflict Risk	The scholarly-publication niche with named verbs (audit, submit, revise, transfer) and LaTeX/PDF/Word deliverables is mostly distinct from other skills, with only minor overlap risk against generic writing or citation skills.	4 / 5
	Total	15 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (725 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 39 missing	Warning

	Total	14 / 16 Passed

Repository: WUBING2023/PaperSpine
Path: paperspine5/core/01_PaperSpine4/src/skill/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.