kdp-publish
Orchestrate the full Amazon KDP publishing workflow: audit, listing craft, manuscript prep, cover generation, dashboard submission, pricing, publish. Phases gate each other. Handles both eBook and paperback. Manages MCP-driven cover generation or falls back to manual prep.
What this skill does
# KDP Book Publishing Workflow
Orchestrate the full workflow for publishing a book through Amazon KDP (Kindle Direct Publishing): audit the manuscript, craft the listing, prepare files, and submit. This skill coordinates `/kdp-audit` and `/kdp-listing` into a phased pipeline, then walks through the mechanical submission steps on the KDP dashboard.
## Strategy
The recommended publication sequence:
1. **Audit** -- Verify the manuscript meets KDP formatting and content requirements
2. **Listing** -- Craft blurb, keywords, categories, and author bio (the marketing artifacts that determine discoverability)
3. **Prepare** -- Convert manuscript to final format, verify cover specs
4. **Submit** -- Walk through the KDP dashboard, upload files, set pricing, publish
Each phase gates the next. Do not submit a manuscript that fails audit. Do not fill in listing fields without the artifacts from `/kdp-listing`. Present the phase map, confirm the plan, and proceed one phase at a time.
## Workflow
### Phase 1: Assess Current State
Determine where the book stands in the pipeline to skip completed phases.
**Load user config** (Read tool): Read `.claude/kdp.local.md` if it exists. Extract the `kdp` section and `author` metadata from YAML frontmatter. If the file is missing, offer to create one from the template at `${CLAUDE_PLUGIN_ROOT}/docs/user-config-template.md`.
**Detect manuscript files** (Glob tool): Search for manuscript files in the project:
- `.tex` files (LaTeX -- technical books)
- `.docx` files (Word -- fiction/nonfiction)
- `.epub` files (eBook source)
- `.md` files (Markdown manuscripts)
- `.pdf` files (final output)
- `.kpf` files (Kindle Create project)
Classify the manuscript type: Technical (LaTeX, math, code), Fiction (chapters, dialog), or General nonfiction.
**Check what already exists** (Glob/Read tools):
- Cover files? (`cover*.jpg`, `cover*.pdf`, `paperback-cover.*`, `full-cover.*`)
- Audit already done? (Look for recent audit report in conversation history or notes)
- Listing artifacts in config? (`kdp.blurb`, `kdp.keywords`, `kdp.categories` populated?)
- Manuscript in final format? (compiled PDF, validated EPUB)
**Present status table** to the user summarizing findings.
**Decision matrix** -- determine where to enter the pipeline:
| State | Next Phase |
|-------|------------|
| No manuscript found | Cannot proceed -- ask user for manuscript location |
| Manuscript exists, no audit done | Phase 2: Audit |
| Audit passed, no listing artifacts in config | Phase 3: Listing |
| Listing artifacts ready, manuscript not in final format | Phase 5: Manuscript Preparation |
| Everything ready, not yet submitted | Phase 6: Cover Preparation or Phase 7: Submit |
| Published, not verified | Phase 10: Post-Publish |
Present the recommended plan and confirm with the user before proceeding.
### Phase 2: Audit
Run `/kdp-audit` to evaluate the manuscript against KDP requirements.
The audit checks interior formatting, cover specs, metadata completeness, and genre-specific requirements. It produces a structured gap report with Critical / Warnings / Passed sections.
If critical gaps are found:
1. Present the gap report to the user
2. Offer to fix automatable issues (margins, missing front matter, scene break markers)
3. Guide manual fixes (cover creation, content revisions)
4. Re-audit after fixes
**Gate**: The manuscript must pass audit (no critical gaps) before proceeding to Phase 3. Warnings are acceptable but should be noted for later attention.
### Phase 3: Craft Listing
Run `/kdp-listing` to generate the four marketing artifacts:
- Blurb (book description, max 4000 characters with HTML formatting)
- Keywords (7 keyword phrases for Amazon search)
- BISAC categories (2-3 browse categories)
- Author bio (for the product page and Author Central)
The listing skill reads manuscript context, generates drafts, iterates with the user, and saves all artifacts to `.claude/kdp.local.md`.
**Gate**: All four artifacts must be saved to the config before proceeding. Phase 7 reads them during dashboard submission.
### Phase 4: Pre-Order Setup (Optional)
Ask the user whether they want to set up a pre-order before the book is finalized.
**When pre-orders make sense**: Fiction launches where Day 1 ranking matters (pre-orders count toward release-day sales rank), books with an existing audience, or series releases.
**Pre-order mechanics**:
- Available up to 90 days before publication date
- Upload a placeholder or final manuscript; set publication date and price
- Final manuscript must be uploaded at least 72 hours before publication date
- Missing the 72-hour deadline may result in KDP blocking pre-order privileges for one year
**How to set up**: Create the title on KDP dashboard (see Phase 7), choose "Make this book available for pre-order," set the release date, upload manuscript, and complete pricing (Phase 8).
If not using pre-orders, skip to Phase 5.
### Phase 5: Manuscript Preparation
Ensure the manuscript is in final publishable form.
**Format conversion** (Bash tool):
- *LaTeX to PDF*: Run `pdflatex` (multiple passes for cross-references; add `bibtex` pass if bibliography exists). Verify fonts embedded, margins correct, page numbers start after front matter.
- *Markdown to EPUB*: Use `pandoc manuscript.md -o manuscript.epub --toc`. Validate with `epubcheck` if available.
- *DOCX to PDF*: Use `libreoffice --headless --convert-to pdf` or Word's built-in PDF export with fonts embedded.
**Final proofread checklist**:
- [ ] Front matter complete (title page, copyright, dedication, TOC)
- [ ] Chapter headings consistent in style
- [ ] Page numbers start after front matter
- [ ] All images/figures embedded and captioned
- [ ] Bibliography/references formatted correctly (if applicable)
- [ ] Back matter complete (acknowledgments, About the Author)
- [ ] No orphan blank pages
### Phase 6: Cover Preparation
Generate or verify cover files for the book. See `${CLAUDE_PLUGIN_ROOT}/docs/kdp-reference.md` for full cover requirements (dimensions, DPI, spine width calculation, bleed).
**Fallback note**: This phase uses the `kdp-cover` MCP server for AI cover generation. If the MCP tools are not available (Node.js not installed, `OPENAI_API_KEY` not set, or the server is not configured), fall back to manual cover preparation: verify existing cover dimensions with `identify` or `file` (Bash tool), direct the user to the KDP Cover Calculator at https://kdp.amazon.com/en_US/cover-calculator, and recommend hiring a designer or using KDP Cover Creator if no cover exists.
1. **Check for existing cover** (Read tool, Glob tool): Look for an existing cover path in `kdp.cover.front` from the config. If not set, glob for `cover*`, `front-cover*`, and `*-cover.*` files in the project. If a cover file exists, show it to the user (Read tool on the image file) and ask whether to use it or generate a new one.
2. **Gather art direction**: If no cover exists (or user wants a new one), ask the user for art direction preferences: visual style, mood, color palette, imagery. If the user has no strong preference, suggest a direction based on the genre from `kdp.genre` and the book title. Check `kdp.cover.art_direction` in the config for any previously saved preferences.
3. **Inform about cost**: Tell the user that each cover generation costs approximately $0.04-$0.08 via OpenAI image generation. Multiple iterations are normal (2-4 attempts to get a cover the user likes).
4. **Generate front cover** (kdp_generate_cover MCP tool): Call `kdp_generate_cover` with:
- `title`: from the book title
- `subtitle`: if applicable
- `author_name`: from `kdp.pen_name` or `author.name`
- `genre`: from `kdp.genre`
- `art_direction`: from the user's preferences or suggested direction
- `width`: 1600 (default)
- `height`: 2560 (default)
5. **Show the cover** (Read tool): Read the generated image file to display it inline. Ask the user to verify:
- Is the titRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.