kdp/skills/kdp-listing/SKILL.md
Craft the four marketing artifacts for an Amazon KDP listing: blurb (with HTML formatting), keywords, BISAC categories, and author bio. Reads manuscript context to generate variants, then saves outputs to the user config. These four artifacts determine discoverability and conversion on Amazon.
npx skillsauth add queelius/claude-anvil kdp-listingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate the four marketing artifacts for an Amazon KDP listing: blurb (book description), keywords, BISAC categories, and author bio. This skill gathers just enough context about the book to write effective marketing copy, then saves all artifacts to the user's project config.
Read .claude/kdp.local.md if it exists (Read tool). Extract the kdp section and author metadata from YAML frontmatter. Key fields to look for:
kdp.blurb — existing blurb draft (if any)kdp.keywords — existing keyword listkdp.categories — existing BISAC categorieskdp.author_bio — existing biokdp.pen_name — pen name (if different from author.name)kdp.series — series name and volume numberkdp.genre — declared genreauthor.name — author's real nameauthor.bio — general bio textIf the config file is missing, offer to create one from the template at ${CLAUDE_PLUGIN_ROOT}/docs/user-config-template.md.
Gather enough context to write marketing copy. This skill does not read or analyze the full manuscript — it collects what it needs to sell the book.
Scan for existing context docs (Glob tool): Search for files that summarize the book's content and intent:
outline*, synopsis*, summary*, pitch*worldbuild*, blurb*, logline*README*, CONCEPT*, PREMISE*Read found docs (Read tool): Read any matching files. These often contain the clearest distillation of what the book is about — more useful for marketing copy than the manuscript itself.
Read the opening (Read tool): Find and read the first chapter or opening section to understand tone, voice, and genre register. Look for the first chapter file, or the first 100 lines of the main manuscript file. The opening establishes the voice that the blurb should echo.
Ask the user to fill gaps: After reading available context, ask for anything still missing:
The blurb is the single most important marketing asset. It appears on the Amazon product page and its first two sentences appear in search results.
Check existing blurb: If kdp.blurb is non-empty in the config, present it and ask: refine the existing blurb, or start fresh?
Consult exemplars (Read tool): Reference the exemplar blurb patterns for genre-appropriate structures, anti-patterns, and annotated examples.
Structure by book type:
Fiction: Hook sentence (concrete, visual, specific) -> escalation of conflict -> stakes (both personal and external) -> NO spoilers past the first act -> comp-title call to action.
Nonfiction: Problem the reader faces -> promise of what the book delivers -> author's authority to deliver it -> what the reader will gain or be able to do.
Technical: What the book covers and why it matters -> who it is for (specific audience) -> what makes it different from other books on the topic.
Generate 2-3 variants for the user to pick from or combine. Each variant should take a different angle on the hook or emphasize different stakes.
Apply HTML formatting for Amazon display:
<b> for emphasis on hook lines or key phrases<i> for comp-title CTAs and book titles<br> for paragraph breaks (Amazon strips standard line breaks)Validate:
Iterate with the user until they are satisfied with the blurb. Offer specific revisions: tighten the hook, raise the stakes, adjust tone, add or remove comp titles.
Each keyword slot can hold a phrase up to 50 characters. Keywords supplement the title, subtitle, and categories — they help readers find the book through Amazon search but do not appear on the listing page.
Consult exemplars (Read tool): Consult the exemplars reference doc for effective keyword patterns and TOS boundaries.
Generate keyword candidates using these strategies:
Rules:
Present recommendations with reasoning for each keyword. Explain what search behavior each phrase targets. Let the user adjust, swap, or reorder.
Amazon uses BISAC (Book Industry Standards and Advisory Committee) codes for browse classification. Select 2 categories at setup (3 for print books). After publication, request up to 10 total via KDP support.
Consult exemplars (Read tool): Consult the exemplars reference doc for example BISAC paths and the niche-vs-broad trade-off.
Recommend specific subcategories over broad top-level categories. Choosing "Fiction > Fantasy > Epic" places the book in three browse paths (Epic, Fantasy, Fiction), while choosing just "Fiction > Fantasy" gives only two.
Explain the niche-vs-broad trade-off: Narrow categories have fewer competitors but also fewer browsers. The goal is to rank in a category where the book can reach the top 20, which earns visibility on the category page.
Present 2-3 primary recommendations plus 2-3 post-publish expansion candidates. For each, explain why the book fits and what the competitive landscape looks like.
The author bio appears on the Amazon product page and the Author Central page. Maximum 2000 characters.
Pull existing data: Use author.name (or kdp.pen_name if set) and author.bio from the config as a starting point.
Consult exemplars (Read tool): Consult the exemplars reference doc for genre conventions and annotated bio examples.
Adapt for genre context:
Draft the bio following these principles:
Check config: Look for kdp.series in the user config.
If not set, ask whether the book is part of a series. If yes, capture:
If part of a series, note that all books in the series should share at least one BISAC category to keep them grouped in browse results and strengthen the series page.
Write all outputs back to .claude/kdp.local.md under the kdp section (Edit tool). Fields to populate:
kdp:
blurb: |
[full blurb with HTML formatting]
keywords:
- "keyword phrase 1"
- "keyword phrase 2"
- "keyword phrase 3"
- "keyword phrase 4"
- "keyword phrase 5"
- "keyword phrase 6"
- "keyword phrase 7"
categories:
- "Fiction > Fantasy > Epic"
- "Fiction > Fantasy > Action & Adventure"
author_bio: |
[author bio text]
series:
name: "Series Name"
volume: 1
Confirm the save with the user. Summarize what was written and where.
For KDP listing best practices, exemplar blurbs, and metadata requirements, consult:
${CLAUDE_PLUGIN_ROOT}/docs/kdp-exemplars.md — Blurb examples by genre, keyword strategies, category selection tactics, author bio conventions, and anti-patterns${CLAUDE_PLUGIN_ROOT}/docs/kdp-reference.md — Full KDP metadata requirements, content guidelines, pricing, and submission workflow/kdp-publish — the publish workflow reads these artifacts from the config and checks for completeness..claude/kdp.local.md in the user's project, not to the plugin repo.tools
This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.
testing
Discover latent themes in the metafunctor corpus. Use when the user wants to find implicit through-lines across their blog posts, surface recurring ideas they have not consciously framed as a series, or get candidate themes for a synthesis post. Reads titles, descriptions, and tags; proposes 3 themes that connect 4+ posts each, each with a single-sentence through-line. Output is a proposal, not a draft. Trigger phrases include "find themes in my posts", "what threads connect my writing", "latent themes in my corpus", "scribe".
development
Use when drafting prose sections for a bookwright (technical non-fiction) project. Encodes the Bernoulli-textbook workflow: atom-outward design, deferral discipline, running threads, page budgets, Path A subagent pattern, header comment block convention.
testing
Use when drafting or executing a paired notebook for a bookwright chapter. Covers when notebooks are required vs optional, numerical-sanity-target convention, exec-from-fresh-kernel requirement, and stack-specific execution commands (Jupyter/R Markdown/Quarto).