CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
aktsmm avatar

Book Writing Workspace

aktsmm/agent-skills
203 installs25 stars
Summary

If you're writing a technical book and need more than a folder full of Markdown files, this sets up a complete manuscript workspace with per-section files, writing and review agents, page allocation docs, and character counting scripts. It defaults to a clean Markdown workflow but can scaffold Re:VIEW and PDF build tooling when you pass the flag. The agent setup is nice: a dedicated writing agent and a separate reviewer that flags P1/P2/P3 issues. Built by someone who clearly writes technical books in Japanese and English, so the bilingual triggers and attention to manuscript structure feel lived-in. It won't manage your Git commits, which is the right call.

Install to Claude Code

npx -y skills add aktsmm/agent-skills --skill book-writing-workspace --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Files
SKILL.mdView on GitHub

Book Writing Workspace

Create and maintain a reusable manuscript workspace with folders, writing agents, instructions, review rules, and optional Markdown -> Re:VIEW -> PDF support.

When to use

  • Book writing, technical writing, 執筆プロジェクト, Re:VIEW
  • Assessing or standardizing an existing book manuscript repository
  • Creating a new technical writing project from templates when needed
  • Setting up Markdown → Re:VIEW → PDF workflow
  • Upgrading an existing manuscript workspace so it can generate Re:VIEW output and printable PDFs
  • Standardizing chapter/section file layout, writing rules, review workflow, and page allocation
  • Adding optional Re:VIEW/PDF support without turning the writing workspace into a general Git or publishing operations toolkit

Quick Start

Start by assessing the manuscript workspace, even when creating a new project:

  1. Confirm the main manuscript lives in sections/ and uses one file per section.
  2. Confirm outlines or key points live separately from final manuscript files.
  3. Confirm chapter intro files use kebab-case naming (e.g. 00-introduction/00-introduction.md).
  4. Locate the workspace's declared reader-persona SSOT; do not force a new file when an existing overview or planning document already owns it.
  5. For a new workspace, use docs/reader-personas.md to define the primary persona, secondary personas, prior knowledge, and completion outcomes.
  6. Confirm writing, heading, notation, page allocation, and review rules are available.
  7. Decide whether Re:VIEW/PDF output is needed for this project; keep it optional unless the workflow requires it.

Operating Workflow

When the workspace already exists, do not stop at setup-oriented advice. This skill should also support:

  1. Normalizing manuscript folders and section naming.
  2. Keeping outlines, drafts, final manuscript, and images aligned by chapter.
  3. Running focused writing and review loops until P1/P2 issues are resolved.
  4. Applying reviewer fixes without leaving outlines, chapter maps, question digests, and progress trackers out of sync.
  5. Reviewing each chapter against the book-specific reader persona and expected outcome.
  6. Checking word count targets and source confidence before finalizing text.
  7. Measuring the built page count before treating a page-budget overrun as a structural problem; character-count estimates run high, and an author-side build is not the publisher's printed page count.
  8. Ruling on external issues, pull requests, and publisher proof comments point by point, first confirming which revision the proof was typeset from, then verifying each factual claim against its source of truth.
  9. Giving typeset-only elements such as chapter frontispieces a source of truth in the manuscript, marked so the converter can emit them, once it is settled that the author writes them.
  10. Enabling Re:VIEW/PDF support only when the project needs reproducible output.
  11. Freezing a release candidate and running the release-readiness gates before delivery or publication.

Bootstrap Workflow

Use the setup script only when creating a new workspace or adding missing structure deliberately.

python scripts/setup_workspace.py `
  --name "project-name" `
  --title "Book Title" `
  --path "D:\target\path" `
  --chapters 8

# Include Re:VIEW/PDF scaffolding only when needed.
python scripts/setup_workspace.py `
  --name "project-name" `
  --title "Book Title" `
  --path "D:\target\path" `
  --chapters 8 `
  --with-review
  1. Gather info: Project name, title, location, chapter count
  2. Run script: scripts/setup_workspace.py
  3. Review output: Confirm README, agents, instructions, and docs were created
  4. Customize: Edit docs/reader-personas.md, docs/page-allocation.md, docs/schedule.md, and .github/copilot-instructions.md. If --with-review is used, also customize config/review-metadata/project.yml.

Git workflows are project-specific. Do not add generic commit/push prompts here; follow the repository's existing version-control conventions.

Metadata, migration, converter verification, and sync-back rules live in references. Keep the main SKILL focused on manuscript structure and writing workflow.

Generated Workspace

  • Manuscript folders under keypoints/, sections/, and images/
  • AI workflow files under .github/agents/ and .github/instructions/
  • Project docs such as README.md, docs/reader-personas.md, docs/page-allocation.md, docs/schedule.md, and docs/release-readiness-record.md
  • Helper scripts such as scripts/count_chars.py
  • Optional Re:VIEW scripts and metadata when --with-review is used

Recommended Writing Unit

  • Use 1 file = 1 section as the default manuscript unit.
  • Keep chapter intro in {NN}-{slug}/{NN}-{slug}.md and section files alongside it.
  • For PDF/Re:VIEW output, heading levels define hierarchy, while file split mainly improves authoring and review workflow.

Agents Overview

AgentRoleDefault
@writingWrite and edit manuscriptsYes
@writing-reviewerReview manuscripts (P1/P2/P3)Yes
@converterConvert Markdown to Re:VIEWOnly with --with-review

Dependencies

ToolPurposeRequired
Python 3.8+ScriptsYes
GitVersion controlYes
DockerRe:VIEW PDF buildOptional, only with --with-review

Reference Map

TopicReference
Folder structurereferences/folder-structure.md
Setup workflowreferences/setup-workflow.md
Customization pointsreferences/customization-points.md
External reviewreferences/external-review-handling.md
Re:VIEW / PDF tipsreferences/review-pdf-tips.md
Screenshot capturereferences/screenshot-capture.md
Release readinessreferences/release-readiness-review.md

Optional Build Pipeline

For workspaces that add conversion or PDF rendering, apply build pipeline gates. Keep project-specific commands, dependency versions, and formatter rules in the generated workspace.

Done Criteria

  • Workspace folder structure created
  • Writing and review agents deployed to .github/agents/
  • One reader-persona SSOT is selected; new workspaces use docs/reader-personas.md without placeholders
  • docs/page-allocation.md configured
  • docs/release-readiness-record.md is available for release candidates
  • README.md and docs/schedule.md customized
  • Manuscript files follow the chapter/section naming convention
  • scripts/count_chars.py works for target manuscript files
  • Setup fails before mutation when a required template, script, or asset is missing
  • A clean temporary-directory smoke test generates docs/reader-personas.md and exits successfully
  • The smoke test also generates docs/release-readiness-record.md, expands the title, and includes the Gate 8 row and manifest lock fields
  • Re:VIEW/PDF output is either explicitly out of scope or enabled and verified
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
Git & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingAutomation & WorkflowsOffice & Documents
First SeenJun 3, 2026
View on GitHub

More from aktsmm/agent-skills

All 5 skills →
  • Vscode Extension Guide182
  • Powerpoint Automation1.9k
  • Skill Finder608
  • Ocr Super Surya547

Recommended

More Git & Pull Requests →
easychen avatar
opc-orchestrator

easychen/opc-methodology

Orchestrate the full one-person company workflow across all OPC skills. Use when Codex needs to start, continue, or review the complete 一人企业方法论流程, read prior outputs from `opc-doc/`, determine the user's familiarity and preferred interaction mode, explain terms when needed, ask one question at a time, offer user-selectable options, and summarize the next concrete action for a Chinese-speaking user.
201
16.6k
vincentkoc avatar
technical-documentation

vincentkoc/dotskills

Build and review high-quality technical docs as well as agent instruction files in your repository.
201
99
gentleman-programming avatar
jira-task

gentleman-programming/gentleman-skills

Creates Jira tasks following Prowler's standard format. Trigger: When user asks to create a Jira task, ticket, or issue.
200
618
jorgealves avatar
python-async-advisor

jorgealves/agent_skills

Review asynchronous Python code to identify race conditions, deadlocks, and inefficient patterns. Use when working with asyncio, aiohttp, or FastAPI.
200
2
factory-ai avatar
simplify

factory-ai/factory-plugins

Review changed code for reuse, quality, and efficiency, then fix any issues found.
199
101
pproenca avatar
rust-write-tests

pproenca/dot-skills

Expert-level Rust testing — the "What Could Break?" framework, five transformations from superficial to expert tests, flake hunting protocol, intent-based assertions, naming conventions, and a mandatory self-review checklist. Triggers on writing Rust tests, designing test cases, improving test quality, or reviewing test coverage.
198
192