一键导入
draft-writing
Use when drafting, rewriting, polishing, or revising prose while preserving author intent by tracking claims, evidence, caveats, and revision deltas.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when drafting, rewriting, polishing, or revising prose while preserving author intent by tracking claims, evidence, caveats, and revision deltas.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Send email over SMTP using only the Python standard library, with plain-text and HTML bodies, file attachments, cc/bcc, reply-to, a dry-run preview, connection verification, and redacted config inspection.
ALWAYS use this skill when the user asks to send, get, retrieve, find, share, add, or search for a paper. This skill manages the user's Zotero library with 10,000+ papers and can retrieve PDFs, create share links, add new papers, and search. Prefer this over getscipapers for any request involving sending/getting/finding papers.
Use before delivering work that incorporated content the agent did not author — fetched web pages, PDFs, retrieved or library documents, tool or subagent output — or that performs an outward-facing or irreversible action. Maps trust boundaries and runs an abuse-case and prompt-injection check, delegating to a fresh-context security reviewer.
Run bounded autonomous research iterations with evidence gates, recovery ledgers, and optional cross-agent handoffs. Use when the user asks to continue research autonomously, run a research loop, integrate autonomous agent loops, or keep improving a research workflow without repeated prompts.
Use for a clarity-only pass that must not change behavior — simplifying, renaming, de-duplicating, or restructuring code, configs, research scripts, or prose. Gates on understanding the target before touching it and re-verifies after each change so behavior stays fixed.
Use in-flight, the moment you are about to let a non-trivial decision stand — a branching or control-flow change, crossing a module/service/agent boundary, an assertion the type system or proof checker cannot see, a high-stakes or irreversible action, or an analytical step a conclusion rests on. Materializes a fresh-context reviewer biased to disprove, while course-correction is still cheap.
| name | draft-writing |
| description | Use when drafting, rewriting, polishing, or revising prose while preserving author intent by tracking claims, evidence, caveats, and revision deltas. |
| metadata | {"short-description":"Claim-preserving draft writing workflow"} |
Use this skill when the user wants help with a draft, section, report, article, paper prose, grant text, response letter, or other writing where the wording may change but the intended claims must stay controlled.
Do not use this as an AI detector. This is a procedural workflow for preserving claims through drafting and revision.
For paper/book review requests, use the relevant review workflow unless the user is asking to rewrite or prepare draft text.
missing.Use the installed templates when available:
draft-claim-ledger.md for claim extraction and support mappingdraft-revision-map.md for before/after revision auditsUse the instruction doc claim-preserving-writing.md for detailed guidance
when the task involves multiple sections, citation-sensitive prose, or repeated
revision rounds.
For mathematical or LaTeX manuscripts, also apply language-style-rules.md.
In particular, check that concepts are defined before use, unnecessary local
terminology is removed, result introductions explain each statement's role, and
long proofs begin with a clear proof idea.
incomplete analysis before any
final readiness claim.This workflow tracks what is being said and whether declared support is present. It does not independently prove claims true unless paired with verification, review, citation lookup, tests, experiments, or formal checks.