executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
nature-polishingPolish, restructure, or translate academic prose into Nature-leaning English using writing-strategy principles, curated Nature/Nature Communications article patterns, and phrase-level support from Academic Phrasebank. Use whenever the user asks to polish a manuscript paragraph, abstract, introduction, results, discussion, conclusion, title, methods section,…
Independent GitHub snapshot · Automated classification · Original documentation governs
This skill is split into two layers:
static/ that holds versioned, reusable content fragments (core principles, paper-type playbooks, per-section guidance, language-specific rules, per-journal style).manifest.yaml) that detects the request's axes and loads only the fragments needed for the current job.Do not try to apply the polishing logic from memory or from this router. Always load fragments from disk as described below.
Follow these five steps every time the skill is invoked.
Read manifest.yaml. It declares the axes (paper_type, section, language, journal), the allowed values, and the file paths each value maps to.
Also read every file listed under always_load. These hold the default stance, failure-mode diagnosis, ethics, and output format that apply to every polish job.
For each axis in the manifest, decide the value using the manifest's detect: hint and the user's input:
paper_type — research / methods / hypothesis / algorithmic / review. Default: research.section — abstract / intro / results / discussion / conclusion / title / methods. May be multiple. Ask the user if it is ambiguous and matters for the polish.language — en or zh-to-en. Detect from the draft itself.journal — nature / nat-comms / generic. Default: generic. If the user names a Nature subjournal, treat it as nature.State the detected axis values in one short line to the user before proceeding, so they can correct you cheaply.
For each axis value, Read the file mapped in the manifest. Skip the section axis only if the user has supplied free-floating prose with no section context.
Do not read every fragment in static/. Load only what step 2 selected.
Apply the loaded fragments in this priority order, matching the paper type -> section job -> paragraph logic -> claim/evidence/boundary -> sentence polish rule from core/failure-modes.md:
If a paragraph's structural problem cannot be fixed without inventing content, flag it instead of papering over it.
The files under references/ are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest, for example when the user explicitly asks for phrasebank-style alternatives or a stricter style audit.
Layout/typesetting (排版) requests are different. If the user asks to fix
placement rather than wording — loose/sparse pages, stranded headings, figures
that don't fill the page or split across pages, "Float too large", multi-panel
arrangement, sparse Supplementary Information — skip the prose axes (paper_type,
section, language, journal) and load references/latex-layout.md directly. That
file is self-contained: it carries the diagnosis workflow (render → contact-sheet →
read the log), the float-glue and [H]/\clearpage/placeins patterns, and the
"regenerate wide figures taller at the source" rule. Always compile and visually
inspect rendered pages before and after — never judge layout from the .tex alone.