Awesome Research Skills
Four skills for research text: drafting a paper from data, English polishing, removing templated phrasing and slides from a paper
- 157 ★ on the repository
- Last commit
- Apache-2.0
Minimal access
Why this level
- The skills edit manuscript text and without comparing with the original an edit may distort meaning
- An uploaded manuscript goes to the agent model provider
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/awesome-research-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skills edit manuscript text and without comparing with the original an edit may distort meaning
- An uploaded manuscript goes to the agent model provider
This is third-party code. Review the repository files before installing.
What it does
Awesome Research Skills is a set of skills from Yila.ai for the full research lifecycle. Four are ready today. `science-research-writing` turns ideas, notes, data and references into a paper: a plan, a section draft, a revision or a manuscript audit, with every claim tied to confirmed data. `sci-ssci-polishing` edits English academic text for publication and adds an audit of meaning preservation. `academic-humanizer` removes templated AI traces from Chinese and English scholarly prose while keeping claims, numbers, equations, citations, limitations and uncertainty. `research-presentation` turns a paper into slides. The authors principle: the agent shows sources, checks, uncertainty and changes instead of silently rewriting research. The repository has a corpus of 60 selected papers, blind retention checks and synthetic cases in `benchmarks/`, ready examples and a lean download build. The set targets Codex, Claude Code and other skill systems. Install with `npx skills add Yila-AI/awesome-research-skills --global --agent codex --skill science-research-writing --yes --copy`; instead of a skill name, install all with `"*"`.
Who it is for. Researchers, postgraduates and editors of scholarly manuscripts who prepare papers in English or Chinese and want edits that do not distort results.
Good fit when
- Notes, tables and references need to become a plan and a section draft grounded in data
- English manuscript text has to reach publication level without changing meaning
- Scientific prose sounds templated, as if written by AI, and needs polishing without losing numbers or citations
- A finished paper has to become conference talk slides
Not a fit when
- You need to detect whether text was written by AI: `academic-humanizer` edits style and is not a detector
- You need a full literature database search: the set covers writing and editing while discovery and reading remain planned
- You need plagiarism protection or falsification: the skills preserve claims and do not create data
Example request
Polish this paper section with academic-humanizer: remove templated phrasing but keep all numbers, equations and citationsLimitations
Not every stage of the lifecycle is ready: paper discovery and reading are listed as future stages. The skills assume the user provides claims, numbers and citations, and the agent must not invent data and must flag uncertainty. Compare every edit with the original manuscript, since the preservation audit lowers but does not eliminate the chance of distortion.
Installation runs through `npx skills`, and the `--copy` flag copies files instead of linking. The repository has `scripts/validate_skills.py` to check structure. The license is Apache-2.0, and when using the materials in publications the authors ask for citation through `CITATION.cff`.
How to disable. Delete the installed skill folders from the agent directory, for example `~/.codex/skills/science-research-writing`, `sci-ssci-polishing`, `academic-humanizer` and `research-presentation`.
FAQ
How do I install all skills at once?
Run `npx skills add Yila-AI/awesome-research-skills --global --agent codex --skill "*" --yes --copy`. For Claude Code use the matching `--agent` value.
What does academic-humanizer do?
Removes templated AI traces from Chinese and English scholarly prose while preserving claims, numbers, equations, citations and caveats. It is not an AI detector.
Which languages are supported?
Texts and skills target English and Chinese, and the README is also available in Japanese and Korean.
Are there quality checks?
Yes, `benchmarks/` has blind retention checks and synthetic cases, and `corpus/` has a list of 60 selected papers.
Does the set work with Claude Code?
The authors name Codex, Claude Code and other skill systems. README install examples are given for Codex.
Discussion
No questions or reviews yet.
Related
SkillsA library of 280+ research skills: literature search, experiment design, analysis, reference checks and paper preparation
A skill for master and PhD students that runs research through novelty and reality gates, from review to claim checks
Research Skills gives Claude Code, Codex and Copilot CLI plugins for research: literature, grants, papers, figures, slides.
A skill turns an ML research repository into a conference paper draft in LaTeX with a claim-evidence map.
A skill set for academic work: paper review, pre-analysis plan check, grant proposal review, code audit and slide decks.
Three skills for academic writing: a paper schema for image generation, rewriting text to sound less machine-made, and drafting from scratch
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Awesome Research Skills (this card) | no | 157 | |
| Research Writing Skill | no | 553 | a single skill for research writing, with no stack with editing and slides |
| Academic Automation Skill | no | 104 | automates research routine without meaning edits or a preservation audit |
README in short
The repository contains a skill stack for the entire research cycle from discovery to presentation, of which writing, careful editing, de-templating and slides are ready today. The authors provide a corpus, examples, a lean build and citation details.
README badge
Original SKILL.md
--- name: academic-humanizer description: Use when researchers ask to remove generic, templated, or AI-like patterns from Chinese or English academic prose, make an AI-assisted draft sound more like the author's own scholarly voice, or audit a paper for “AI味”. Preserve every scientific claim, number, equation, citation, limitation, and uncertainty. Not for detector evasion or ordinary translation and grammar-only editing. license: Apache-2.0 --- # Academic Humanizer Remove the template voice, not the scholarship. Make academic prose more specific, natural, and recognizably the author's while preserving the research exactly. This Skill improves writing quality. It does not certify that text is human-written, optimize for an AI detector, or remove an author's obligation to disclose AI assistance under the relevant journal, institution, or funder policy. ## Load only what is needed - Always read `references/preservation-and-evidence.md`, `references/pattern-catalog.md`, and `references/output-contract.md`. - Read `references/voice-calibration.md` only when the author provides writing samples or explicitly asks to match their voice. - When source and revision are available as local text, use `scripts/check_invariants.py` as a deterministic first check. A passing result never replaces the semantic audit. ## Use this Skill when The user asks to: - remove “AI味”, AI-like phrasing, template language, or generic LLM prose from academic text; - make a paper sound less mechanical, less inflated, or more like the author; - audit an abstract, paper section, thesis passage, rebuttal, or reviewer response for recurring AI-writing patterns; - calibrate a draft against the author's prior academic writing. For ordinary Chinese-to-English translation, grammar correction, or general publication polishing without a de-templating or voice-matching goal, `sci-ssci-polishing` is the better entry point. ## Inputs Required: - the passage or document to audit or revise. Useful but optional: - language, field, section type, and target venue; - one or more genuine writing samples from the author; - protected terminology or phrases; - desired intensity: audit only, standard, or strong. Do not block on optional context. Without author samples, use a neutral, precise, venue-appropriate academic voice and state that personal voice matching was not performed. ## Workflow