academic-humanizer
Use when researchers ask to remove generic, templated, or AI-like patterns from Chinese or English academic prose, make an…
Use when researchers need Chinese academic prose translated into publication-oriented English or English manuscript paragraphs and complete sections polished for SCI, SSCI, or interdisciplinary submission.
$ npx -y skills add yila-ai/awesome-research-skills --skill sci-ssci-polishing --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/sci-ssci-polishingContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when researchers need Chinese academic prose translated into publication-oriented English or English manuscript paragraphs and complete sections polished for SCI, SSCI, or interdisciplinary submission.
name: sci-ssci-polishing description: Use when researchers need Chinese academic prose translated into publication-oriented English or English manuscript paragraphs and complete sections polished for SCI, SSCI, or interdisciplinary submission. license: Apache-2.0
Polish the writing, not the science. Improve clarity, precision, coherence, concision, and disciplinary register while treating the author's evidence and claims as immutable unless the author explicitly authorizes a substantive change.
Accept either:
1. Chinese academic prose to translate into English. 2. English academic prose to polish.
The input may be one paragraph or a complete section. Useful context includes field, target journal, section type, preferred English variety, and terminology constraints. Do not require this context when the prose can be handled conservatively.
Identify:
If the field or section is unclear, infer cautiously from the text. State the inference only when it materially affects the revision.
Extract and lock every item listed in `references/invariants.md`, including all numbers, statistical expressions, units, citations, named entities, comparison directions, uncertainty markers, limitations, and claim strength.
Also record the paragraph's claim skeleton:
context/problem -> method/evidence -> finding -> interpretation/qualification
Do not proceed as if two different skeletons were equivalent. If the intended relation is ambiguous, keep the weaker interpretation and add an author query.
Use `references/rhetorical-routing.md` rather than applying one generic “academic style.” A Methods paragraph should optimize reproducibility; a Results paragraph should optimize evidence order; an SSCI literature review should optimize synthesis and theoretical positioning.
For a full section:
1. revise each paragraph locally; 2. label its rhetorical job in a private working outline; 3. repair cross-paragraph progression and transitions; 4. remove redundant setup only when no claim, citation role, or limitation is lost; 5. re-audit the complete section.
Prioritize in this order:
1. factual fidelity; 2. explicit logical relations; 3. correct disciplinary terminology; 4. sentence-level clarity; 5. paragraph coherence; 6. concision and rhythm.
Use the smallest revision that achieves the requested improvement. Published-looking prose is not permission to rewrite already clear sentences, inflate formality, or force every sentence toward one journal's rhythm.
Apply these default practices:
Never invent a citation, mechanism, limitation, rationale, transition, or implication merely to make the prose sound complete.
Compare source and revision item by item. The audit must explicitly check:
If any substantive difference remains, revert it or surface it as an author query. Do not hide it in “key changes.”
When source and revision are available as local text, use `scripts/check_invariants.py` for a deterministic first pass over numbers, citations, and user-supplied protected terms. Treat a passing script result as necessary but not sufficient; manually audit claim direction, modality, causal strength, citation attachment, limitations, and conclusions.
Correct grammar, punctuation, word choice, and local flow. Preserve sentence and paragraph structure whenever possible.
Rewrite sentences and improve paragraph progression while preserving every scientific proposition and citation role.
Reorder sentences or paragraphs for rhetorical clarity, but never add, remove, merge, or strengthen scientific claims without explicit author approval. List every meaningful reordering.
If the user asks to make unsupported findings sound significant, hide limitations, convert association into causation, fabricate citations, or change results without evidence, refuse that part and offer a fidelity-preserving revision.
Follow `references/output-contract.md`. Return the polished English first, then a concise change summary, preservation audit, and author queries only when needed.
The research workflow every AI agent should have. A growing open-source Skill stack for the full research lifecycle—from discovering and understanding papers to writing, reviewing, polishing, and presenting research.
Use when researchers ask to remove generic, templated, or AI-like patterns from Chinese or English academic prose, make an…
Create, revise, and quality-check source-grounded research presentations from papers, research notes, data, or manuscripts. Use…
Use when researchers need to plan, draft, revise, or audit an empirical research paper from their own materials, including…