Skills for Real Engineers. Straight from my .agents directory.
nature-reviewer
Agent skill fromYuan1z0825/nature-skills
Provide evidence-grounded mock peer review of scientific manuscripts or excerpts, covering significance, validity, and major/minor concerns. Use for 模拟审稿、投稿前自审、审稿人视角评估; not author rebuttal drafting.
How to install nature-reviewer
npx skills add Yuan1z0825/nature-skills# or add only this skill to Claude Code: copy the folder
skills/nature-reviewer/
# into
~/.claude/skills/nature-reviewer/ (all projects)
.claude/skills/nature-reviewer/ (one project)
1# Nature Reviewer Assessment Skill23Use this skill to simulate a `Nature`-style reviewer assessment package from the referee4side.56This skill is for reviewer-style manuscript evaluation, not for drafting the authors'7response. If the user wants rebuttal writing, route to `nature-response`.89## Default stance1011- Ground the review only in the local source basis plus manuscript facts supplied by the user.12- Evaluate the manuscript against source-grounded axes: `originality`, `scientific importance`, `interdisciplinary readership`, `technical soundness`, and `readability for nonspecialists`.13- Use the 12-axis technical concern taxonomy only as an internal coverage checklist; it supplements but never replaces the five source-grounded axes.14- Return exactly `3 mutually blind reviewer reports + 1 post-review synthesis` unless the user explicitly asks for another structure.15- Give every reviewer only the same immutable manuscript/source packet, the same journal criteria, and that reviewer's preassigned emphasis. Never provide another review, a shared concern ledger, a draft synthesis, or hints about what another reviewer noticed.16- Run each reviewer in a genuinely separate context, subagent, process, or invocation. If the environment cannot isolate contexts, generate one reviewer report per invocation or explicitly state that mutual blindness cannot be guaranteed; never present shared-context drafting as independent peer review.17…
Excerpt shown under the repository's Apache-2.0 license.
More skills in nature-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
