菜单
Read and write files in the shared session workspace. Use this to access files created by any skill — code-agent outputs, office documents, images, and more. All within the same isolated session.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/bouclem/skills --skill workspace命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.
12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
基于 SOC 职业分类
正在显示 SKILL.md
| name | workspace |
| description | Read and write files in the shared session workspace. Use this to access files created by any skill — code-agent outputs, office documents, images, and more. All within the same isolated session. |
Provides unified read/write access to all files in the current session. The userId and sessionId are injected automatically — you only specify the logical path.
| Prefix | What it accesses |
|---|---|
code-agent/<file> | Files created by the code agent (auto-synced) |
code-interpreter/<file> | Files saved by code interpreter via output_filename |
documents/powerpoint/<file> | PowerPoint presentations |
documents/word/<file> | Word documents |
documents/excel/<file> | Excel spreadsheets |
documents/image/<file> | Images from other tools |
Note: Code interpreter only saves to workspace when
output_filenameis set inexecute_code. Files fromexecute_commandorfile_operationsstay inside the sandbox.
See everything in the session:
workspace_list()
workspace_list("code-agent/")
Read a file the code agent created:
workspace_read("code-agent/calculator.png") # binary → base64
workspace_read("code-agent/report.md") # text → string
Pass a file from one skill to another:
result = workspace_read("documents/excel/data.xlsx") # encoding: base64
workspace_write("code-agent/data.xlsx", result["content"], encoding="base64")
encoding: "text" with plain string contentencoding: "base64"workspace_write accepts both encodings — use "base64" for binaryPath conventions (userId/sessionId injected automatically):
code-agent/<file> — files from the code agentdocuments/powerpoint/<file> — PowerPointdocuments/word/<file> — Worddocuments/excel/<file> — Exceldocuments/image/<file> — imagesBinary vs text: images/PDFs/Office files are returned base64-encoded (encoding: "base64"); use the same encoding when writing them back.