Scientific Peer Review
暂无简介
- License 许可
- MIT
- 所属仓库
- rhCat/skillChip
- 最近更新
- 2026-07-31
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- Scientific Peer Review
- perks
- [ "schematic" ]
- skill
- peer-review
02 资源文件 15
- 其他blueprint.drawio2.7 KB
- 参考文档blueprint.json3.5 KB
- 资产文件blueprint.svg8.9 KB
- 参考文档index.json1.6 KB
- 参考文档ledger.json551 B
- 许可证LICENSE.txt1.0 KB
- 参考文档perks.json338 B
- 参考文档perks/schematic/manifesto.json499 B
- 参考文档perks/schematic/metadata.json1.3 KB
- 参考文档perks/schematic/src/contracts.json563 B
- 脚本perks/schematic/src/generate_schematic_ai.py31.9 KB
- 脚本perks/schematic/src/generate_schematic.py5.0 KB
- 脚本perks/schematic/src/generate_schematic.sh1.7 KB
- 参考文档perks/schematic/test/case.json282 B
- 参考文档perks/schematic/test/fixture/prompt.txt33 B
03 SKILL.md 正文
peer-review — Scientific Peer Review
Generate a publication-quality scientific schematic via AI to support manuscript/grant peer review.
What to look out for
Each tool emits one line of structured JSON (the audit + debug log) and writes its
artifacts under record_store. LOGS TO CHECK: that line + the named report + the executor run-ledger.
Perks
| perk | tool | nature |
|---|---|---|
schematic |
generate_schematic |
read-only / generative (AI diagram generation + iterative quality review) |
The schematic perk takes a natural-language PROMPT and renders a publication-quality scientific
diagram: it calls Nano Banana 2 (google/gemini-3.1-flash-image-preview) to generate the image, then
reviews it with Gemini 3.1 Pro Preview against a document-type quality threshold, regenerating only if
the score is below threshold (max 2 iterations). It writes the image plus a *_review_log.json audit
trail under record_store. The op needs OPENROUTER_API_KEY and network access; offline (or without a
key) the porter degrades gracefully, emitting an empty artifact and a structured audit line — it never
mutates any remote/live service, so it is declared destructive: false.
How to use it
Pick the schematic perk, copy ledger.json → task-ledger.json, fill its vars (PROMPT, OUTPUT,
DOC_TYPE, OPENROUTER_API_KEY) + record_store, then validate → compose → compile → oversight → executor.
Localized from K-Dense-AI/scientific-agent-skills
peer-review— MIT (see LICENSE.txt).
04 同仓库更多 Skills
Vercel Deploy
暂无简介
Audio Transcribe
暂无简介
Speech (OpenAI TTS)
暂无简介
Skill Installer
暂无简介
demo-skill
A demo skill used as a test fixture for the validate perk. Use when checking that quick_validate.py accepts a well-formed SKILL.md.
demo-skill
A demo skill used as a test fixture for generating agents/openai.yaml. Use when validating the gen_openai_yaml perk.