paper-spine-humanize
Reduces AI detection rates via tiered stylistic constraints mapped to real AIGC detection dimensions. Produces a teaching humanizematrix.md. (internal /paperspine step)
- Installs
- 243
- 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-humanize- 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-humanize 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 Humanize
Self-contained skill — can be used standalone on any academic text, or as part of the PaperSpine suite. Applies tier-specific writing constraints based on real AIGC detection dimensions and produces a teaching matrix that documents every change.
When To Use
- In PaperSpine: auto-invoked by rewrite/build when
humanize_tieris notnone - Standalone: invoke directly on any academic text that needs AI detection reduction
Configuration
Read paper_spine_config.json for humanize_tier (none/light/medium/heavy)
and output_language (zh/en). When used standalone, default to medium / zh
if no config found.
Required Output: humanize_matrix.md
This is the primary deliverable — produce paper_rewriting_output/humanize_matrix.md.
Every humanization change must be recorded, not applied silently:
| Row ID | Manuscript Unit | AI Pattern Found | Detection Dim | Severity | Applied Change | Expected Effect | Teaching Note |
|---|
- Manuscript Unit: paragraph number or section name
- AI Pattern Found: specific AI feature detected
- Detection Dim: D1-D5 (see reference document)
- Severity: High (>50% contribution to detection) / Medium (20-50%) / Low (<20%)
- Applied Change: what specific change was made
- Expected Effect: which dimension this reduces
- Teaching Note: why detectors flag this pattern
Matrix Rules
- Write rows during writing, one per unit processed — not after the fact
- At least one row per writing unit for D1 (sentence length)
- At least one row per paragraph for D2 (paragraph structure)
- At least one row per connector replaced (D4)
- At least one row per density adjustment (D3, medium+)
- At least one row per term substitution (D5, heavy only)
- Fill all 8 columns for every row — no empty cells
Instructions
Read references/humanize-tiers-{output_language}.md for the complete
tier-specific directives mapped to the 5 detection dimensions:
D1-Sentence Length / D2-Paragraph Structure / D3-Information Density /
D4-Connector Frequency / D5-Term-Context Matching.
Verification
python scripts/humanize_check.py paper_rewriting_output --markdown --write
Produces paper_rewriting_output/humanize_report.md. Checks matrix coverage
against total paragraphs, scans sentence-length distribution and connector
density, and flags remaining AI patterns.
Integration
In PaperSpine: called internally by rewrite and build. Standalone: place this
skill directory under ~/.claude/skills/ and invoke directly.
FAQ
What does the paper-spine-humanize skill do?
Reduces AI detection rates via tiered stylistic constraints mapped to real AIGC detection dimensions. Produces a teaching humanizematrix.md. (internal /paperspine step)
How do I install paper-spine-humanize?
Run npx skills add https://github.com/wubing2023/paperspine --skill paper-spine-humanize 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-humanize/ (personal) or .claude/skills/paper-spine-humanize/ (project).
Which AI agents can use paper-spine-humanize?
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-humanize 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-humanize?
It is published by wubing2023 in wubing2023/paperspine. It has 243 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-audit
wubing2023/paperspine
Audits PaperSpine outputs for missing artifacts, shallow revisions, logic transfer, unsupported claims, and translation coverage. (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)
Popular education & science skills
teach
mattpocock/skills
Teach the user a new skill or concept, within this workspace.
scaffold-exercises
mattpocock/skills
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
caveman-learn
juliusbrussee/caveman
Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.
gsap-plugins
greensock/gsap-skills
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG drawing, or plugin registration.
teach-impeccable
pbakaus/impeccable
DEPRECATED: Use /impeccable teach instead. This command has been folded into the impeccable skill.