paper-spine-audit
Audits PaperSpine outputs for missing artifacts, shallow revisions, logic transfer, unsupported claims, and translation coverage. (internal /paperspine step)
- Installs
- 355
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/wubing2023/paperspine --skill paper-spine-audit- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads paper-spine-audit automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
PaperSpine Audit
Use this skill before calling a PaperSpine rewrite or build complete.
Required Checks
- Artifact completeness.
- Reference material workspace exists and has a source index.
- Motivation was confirmed by the user after research, not invented before research.
writing_rationale_matrix.mdexists, is ordered, and covers the whole-work framework plus the task-specific writing units for the selected scene. It should split the paper/report into paragraph-sized, claim-sized, evidence, model, synthesis, heading, caption, or competition-solution units as needed; it must not be a fixed IMRaD checklist when the task is not an IMRaD paper. The first row must deeply justify the whole-work framework, and each row must include concrete motivation, reference/SOTA, target-scene, evidence, and planned text-move anchors rather than short labels.- No append-only or shallow revision for substantive rewrite tasks.
- Logic transfer from original draft or materials to final manuscript.
- Claim support from user evidence.
- LaTeX citation, label, and figure safety when a LaTeX project exists.
citation_support_bank.mdcount, recency, and per-paper support-sentence quality before citations are selected for Introduction/Discussion.- Final LaTeX source exists; compiled PDF exists when a TeX engine is available.
- Word output is structurally valid when a
.docxis requested or generated. - Translation coverage is complete when
translation_packageiszh, includingfull_paper_translation.zh.mdfor the complete final paper text and row-by-row translation of large intermediate artifacts such aswriting_rationale_matrix.md.
Scripts
Run when available:
python scripts/integrity_audit.py paper_rewriting_output --markdown --write
python scripts/artifact_check.py paper_rewriting_output --markdown --write
python scripts/revision_audit.py <original> <revised> --markdown
python scripts/structured_review.py paper_rewriting_output --dispatch
# Then: launch three parallel sub-agents per review_prompts/dispatch.md
# After sub-agents complete: python scripts/structured_review.py paper_rewriting_output --validate review_prompts
python scripts/citation_quality_audit.py paper_rewriting_output --write
python scripts/latex_guard.py <main.tex> --bib <references.bib> --markdown
python scripts/word_guard.py paper_rewriting_output/final_paper/paper.docx --markdown --output paper_rewriting_output/word_report.md
Multi-Agent Review Flow
The structured review uses independent sub-agents for genuine reviewer independence:
- Run
structured_review.py --dispatchto generate three isolated reviewer prompts underreview_prompts/. - Read
review_prompts/dispatch.mdand launch three Agent calls in parallel. Each agent reads ONLY its own prompt file and the manuscript. - After all three agents write their output files, run
structured_review.py --validate review_promptsto check independence (cross-contamination detection via text similarity). - Produce Editor Synthesis merging the three independent reviews.
Required Outputs
paper_rewriting_output/integrity_audit.mdpaper_rewriting_output/artifact_check.mdpaper_rewriting_output/revision_audit.mdfor rewrite taskspaper_rewriting_output/structured_review.mdpaper_rewriting_output/citation_quality_audit.mdpaper_rewriting_output/logic_transfer_audit.md- unresolved risks and user decisions
Do not mark the task complete if required artifacts are missing, if the final manuscript contains unsupported claims, if translation is partial, or if the rationale matrix is generic.
FAQ
What does the paper-spine-audit skill do?
Audits PaperSpine outputs for missing artifacts, shallow revisions, logic transfer, unsupported claims, and translation coverage. (internal /paperspine step)
How do I install paper-spine-audit?
Run npx skills add https://github.com/wubing2023/paperspine --skill paper-spine-audit in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/paper-spine-audit/ (personal) or .claude/skills/paper-spine-audit/ (project).
Which AI agents can use paper-spine-audit?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is paper-spine-audit safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains paper-spine-audit?
It is published by wubing2023 in wubing2023/paperspine. It has 355 recorded installs.
More from wubing2023/paperspine
paper-spine
wubing2023/paperspine
Research, write, review and deliver evidence-bound papers in one task, with user choices, real files, editable outputs and same-task revision.
paper-spine-latex
wubing2023/paperspine
Handles LaTeX project assembly, figure placement, citations, labels, and compile-safe cleanup. (internal /paperspine step)
paper-spine-rewrite
wubing2023/paperspine
Rewrites an existing manuscript from confirmed motivation, research, paragraph-level rationale, and evidence. (internal /paperspine step)
paper-spine-build
wubing2023/paperspine
Open the skill to read its SKILL.md instructions.
paper-spine-research
wubing2023/paperspine
Researches target requirements, downloads reference materials, learns strong examples, and prepares motivation options. (internal /paperspine step)
paper-spine-humanize
wubing2023/paperspine
Open the skill to read its SKILL.md instructions.
Popular security skills
azure-compliance
microsoft/azure-skills
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks. WHEN: compliance scan, security audit, BEFORE running azqr (compliance cli tool), Azure best practices, Key Vault expiration check, expired certificates, expiring secrets, orphaned resources, compliance assessment.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized reprooutputs/ files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
seo-audit
coreyhaines31/marketingskills
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking," "Google update hit me," "page speed," "core web vitals," "crawl errors," "indexing issues," "stuck on page 2," "striking distance keywords," "title tag rewrite," "low CTR," "local SEO," "Google Business Profile," or "map pack." Use this even if the user just says something vague like "my SEO is bad" or "help with SEO" — start with an audit. For building pages at scale to target keywords, see programmatic-seo. For adding structured data, see schema. For AI search optimization, see ai-seo.
firebase-security-rules-auditor
firebase/agent-skills
Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks. Use when auditing/reviewing rules, running red-team rule assessments, or scoring against auditor checklists. Don't use for Firebase CLI (login, deploy), Auth, Crashlytics, Remote Config, or database queries.
audit
pbakaus/impeccable
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
competitors
coreyhaines31/marketingskills
When the user wants to create competitor comparison or alternative pages for SEO and buyer-facing use. Also use when the user mentions 'alternative page,' 'vs page,' 'competitor comparison,' 'comparison page,' '[Product] vs [Product],' '[Product] alternative,' 'competitive landing pages,' 'how do we compare to X,' 'competitor teardown,' 'audit our competitor pages,' 'are our comparison pages out of date,' or 'competitive asset audit.' Use this for any content that positions your product against competitors. Covers four formats: singular alternative, plural alternatives, you vs competitor, and competitor vs competitor. For auditing existing claims (not researching competitors from scratch, which is competitor-profiling; not technical SEO on these pages, which is seo-audit), use the asset audit here. For internal battle cards and sales-specific competitor docs, see sales-enablement.