skills/authors-edit/SKILL.md
Mark up a draft with editorial feedback from one or more author personas. Usage - /authors-edit <file> [author1 author2 ...]. If no authors named, inspects the file and picks 1-2 based on genre (marketing copy → Hemingway + Orwell; fiction → King + Vonnegut; essay → Didion + Baldwin; long-form nonfiction → McPhee). Returns a consolidated marked-up view, not N separate critiques. Use when you want a real editorial pass on a piece of writing.
npx skillsauth add sethshoultes/great-authors-plugin authors-editInstall 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.
The core editorial command. Fans out to selected authors, consolidates their markup.
Not for: real-time collaborative drafting (use /authors-channel); fast gut-check opinions (use /authors-critique); resolving a specific craft dispute (use /authors-debate).
When this skill is invoked:
Parse arguments:
hemingway, orwell, didion, mcphee, king, vonnegut, baldwin, mccarthy, wallace, le-guin. Short forms accepted (e.g., papa for Hemingway, dfw for Wallace).Verify the file exists. If not, tell the user the path isn't valid and stop.
If no authors were named, auto-select 1–2 based on genre signals:
Announce your selection to the user in one line: "No authors specified — picking <A> and <B> based on <signal>. Ok, or override?" Accept "ok" or a new list.
If .great-authors/ exists in the file's parent directory, note this in your dispatch prompts — the sub-agents will read bible files as part of the persona's ## Before you edit protocol.
Fan out via the Agent tool. For each selected author, dispatch a sub-agent in parallel (use multiple Agent calls in a single message):
subagent_type: <author>-persona~~strikethrough~~ for cuts and [→ replacement] for substitutions.Consolidate the results. After all sub-agents return, produce a single consolidated view:
# /authors-edit on <filename> — <author A> + <author B>
**<Author A>'s verdict:** <one sentence>
**<Author B>'s verdict:** <one sentence>
## Where they agree
(list 1-3 concrete points both authors made)
## Where they disagree
(list 1-2 concrete points they diverge on, or "No significant disagreement" if so)
## Highest-leverage change
(pick ONE change that would most improve the draft. Name it in one sentence.)
## Marked passages
(Show the marked-up passages, combining both authors' edits when they overlap. If they conflict on the same passage, show both versions labeled.)
## Start here (if any author flagged it)
<first sentence after the cut line>
## Handoffs
(Any cross-reference suggestions from individual authors, listed here. E.g., "McCarthy suggests Baldwin for the moral stakes in paragraph 3 — consider /authors-edit <file> baldwin.")
Output to stdout. Do not write to the manuscript. The human applies the edits.
.great-authors/ exists, they will read it automatically per each persona's ## Before you edit protocol. You do not need to explicitly pass bible context.documentation
Dispatch a named author persona as a sub-agent to rewrite an existing manuscript file from scratch with full bible context. Usage - /authors-rewrite <file> <author>. Use when an existing chapter or scene needs more than a critique pass — when the prose itself isn't working and a clean rewrite by the named author is required. The skill assembles a self-contained brief (bible files, prior/next chapters, architecture beats, voice rules), dispatches the author, and confirms save.
tools
Top-level autonomous workflow for writing a novel end-to-end with the great-authors plugin. Composes existing skills (project-init, build-character, build-place, build-relationship, draft, channel, rewrite, continuity, critique, edit, debate, journal, consolidate) into a multi-phase pipeline with human checkpoints. The human provides direction (premise, genre, characters, voice); the AI orchestrator dispatches author personas as sub-agents to do the work. Use when a user wants the full great-authors pipeline run for them with minimal hand-holding — analogous to great-minds-plugin's agency-* workflows. Usage - /authors-orchestrate-novel, optionally with --phase <N> to run a single phase or --resume to continue from the last checkpoint.
data-ai
Run ONE editor across MULTIPLE files in parallel, then consolidate into a corpus-level pattern report. Surfaces patterns no per-file critique catches — voice drift, recurring tics, structural failures that only become visible across multiple pieces. Usage - /authors-corpus-critique <author> <path-or-glob> [<path-or-glob>...]. Different from /authors-critique (N authors on 1 file). This is 1 author on N files.
tools
Initialize the per-project memory bible (.great-authors/) in the current working directory. Creates project.md, voice.md, timeline.md, glossary.md, and empty characters/, places/, scenes/ directories. Use when the user is starting a new writing project (novel, essay collection, long-form nonfiction) and wants author personas to have persistent context across sessions.