docs-writer
撰写或修订中文学术论文、docx 短汇报和演示文稿时使用。核心是分阶段核对结构、数据与一手来源，并统一处理引用规范、查重、AI 标注和配图。
Skill by TMYTiMidlY
Chalk Labs
Need help deploying docs-writer?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tmytimidly-docs-writer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/docs-writer
What's inside
- Skill name
docs-writer- Description
- 撰写或修订中文学术论文、docx 短汇报和演示文稿时使用。核心是分阶段核对结构、数据与一手来源，并统一处理引用规范、查重、AI 标注和配图。
- License
- unknown
- Instructions
- 520 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions call the network
Agent Skills spec issues
- body: 520 lines (spec recommends under 500)
- files: referenced but missing: references/mineru.md
Files (15)
- LICENSE.txt
- SKILL.md
- GBT7714-2015.md · assets/
- GBT7714-2015.pdf · assets/
- bf9da0185db48917c8bbdd30a0633dee91753a61c4b6c961d82c67f32343652e.jpg · assets/images/
- doc-report.md · references/
- figures.md · references/
- gpt-image.md · references/
- presentation.md · references/
- similarity-report-parsing.md · references/
- thesis.md · references/
- similarity_report_html.py · scripts/
- similarity_report_pdf.py · scripts/
- thesis_to_chapters.py · scripts/
- thesis_toc_pages.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from TMYTiMidlY/skills
- 0.584score
harness
TMYTiMidlY
需要理解、比较或排查 Copilot、Claude Code、Codex、DeepSeek Harness、Hermes、pi 等 coding agent 编排框架（harness）时使用。重点介绍这些框架如何组织 agent loop、工具注入、配置发现、会话、权限与进程/SDK 接口，以及…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
network
TMYTiMidlY
配置或排查 Caddy 反向代理与 caddy-security、OpenWrt、外部 Wi-Fi、客户端代理、WireGuard / EasyTier 组网、远程接入及 WSL/远端网络管道时使用。核心是还原 TLS、认证、DNS、路由和隧道的实际数据路径，再分层处理。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
manage-skills
TMYTiMidlY
创建、安装、重构、审查或合并本地 skill 时使用。核心是维护清晰的能力边界、渐进式文档结构、可追踪的安装链接与一致的仓库规范。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
mess
TMYTiMidlY
遇到疑难杂症、相似报错或想回顾既有排障经验时使用。按症状和关键词检索已记录案例，并把新问题的复现、根因和可靠解法沉淀下来。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
reversing
TMYTiMidlY
逆向分析已发布的移动端应用、游戏或桌面客户端的规则、数据和保护行为时使用。通过程序、资源、接口及设备或只读运行状态交叉取证，将结论落到可复核证据，并区分功能存在、配置启用与实际执行。
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
software
TMYTiMidlY
本地软件、CLI 工具与自托管服务的配置和排障知识库。用于 SSH/systemd、终端与包管理工具、语言工具链、PostgreSQL、S3 对象存储、Docker/PaaS、Overleaf/OpenList、科大云盘（Seafile WebDAV/分享链接）、文档处理与发布、论文图编辑器 Tavotto，以及…
SkillAFreshness: A★ 1Claude Code +9 - 0.544score
tool
TMYTiMidlY
设计、封装、接入、审查或排查供 AI agent 调用的 tool 时使用。核心是把函数、CLI、API 或 MCP operation 收敛成边界清楚、可校验、可授权、可观察的执行契约；整个 agent runtime 与会话编排归 harness skill。
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
wechat-clawbot
TMYTiMidlY
使用 OpeniLink Hub 收发微信消息、接收事件或管理 Bot/App 权限时使用。核心是区分 Bot API 与管理 API，并通过安全注入的凭据完成消息、授权和令牌操作；服务端部署转用 vps-maintenance skill。
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
ax
TMYTiMidlY
Use the ax CLI instead of curl + throwaway parsing scripts whenever you fetch a URL, explore an unknown web page, or extract structured data from HTML.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
git
TMYTiMidlY
处理 Git/jj 提交与历史、隔离工作区、受限网络获取、身份认证、发版 CI 或自建 forge/静态站时使用。核心是先分清 HEAD、暂存区和工作区，再选择可回滚且不污染长期配置的操作。
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
io
TMYTiMidlY
定位内存、文件系统、挂载、存储介质或网络块存储造成的 I/O 与换页瓶颈时使用。核心是沿实际数据路径分层测量延迟和 IOPS，避免被缓存或顺序带宽误导。
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
vps-maintenance
TMYTiMidlY
初始化或维护 VPS/服务器时使用，涵盖安全加固、网络与 IP 质量检查和基础服务部署。远程操作优先使用 portal；Caddy 与客户端网络转用 network，微信 Bot 操作转用 wechat-clawbot skill。
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 21, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/TMYTiMidlY/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TMYTiMidlY
- 0.584score
harness
TMYTiMidlY
需要理解、比较或排查 Copilot、Claude Code、Codex、DeepSeek Harness、Hermes、pi 等 coding agent 编排框架（harness）时使用。重点介绍这些框架如何组织 agent loop、工具注入、配置发现、会话、权限与进程/SDK 接口，以及…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
network
TMYTiMidlY
配置或排查 Caddy 反向代理与 caddy-security、OpenWrt、外部 Wi-Fi、客户端代理、WireGuard / EasyTier 组网、远程接入及 WSL/远端网络管道时使用。核心是还原 TLS、认证、DNS、路由和隧道的实际数据路径，再分层处理。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
reversing
TMYTiMidlY
逆向分析已发布的移动端应用、游戏或桌面客户端的规则、数据和保护行为时使用。通过程序、资源、接口及设备或只读运行状态交叉取证，将结论落到可复核证据，并区分功能存在、配置启用与实际执行。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
mess
TMYTiMidlY
遇到疑难杂症、相似报错或想回顾既有排障经验时使用。按症状和关键词检索已记录案例，并把新问题的复现、根因和可靠解法沉淀下来。
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
manage-skills
TMYTiMidlY
创建、安装、重构、审查或合并本地 skill 时使用。核心是维护清晰的能力边界、渐进式文档结构、可追踪的安装链接与一致的仓库规范。
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
software
TMYTiMidlY
本地软件、CLI 工具与自托管服务的配置和排障知识库。用于 SSH/systemd、终端与包管理工具、语言工具链、PostgreSQL、S3 对象存储、Docker/PaaS、Overleaf/OpenList、科大云盘（Seafile WebDAV/分享链接）、文档处理与发布、论文图编辑器 Tavotto，以及…
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get docs-writer running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
docs-writer skill. Agent Mart. https://agentmart.dev/skills/tmytimidly-docs-writer (last updated 2026-10-24)