skills/authors-journal/SKILL.md
Capture a session journal entry in the project bible. Usage - /authors-journal. Writes .great-authors/journal/YYYY-MM-DD.md with what was worked on, decisions made, what's unresolved, and where the user left off. Use at the end of a writing session so the next session's author personas know what's in flux vs. settled. If an entry already exists for today, offers to append rather than overwrite.
npx skillsauth add sethshoultes/great-authors-plugin authors-journalInstall 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.
Capture a session journal entry.
Not for: daily life journaling. This is a project bible artifact, not a personal diary.
When this skill is invoked:
Verify .great-authors/ exists in the current working directory. If not, tell the user to run /authors-project-init first and stop.
Ensure .great-authors/journal/ exists. Create it if missing (mkdir -p). If the user's bible predates journal support, this is the first-use case.
Determine today's date. Use the format YYYY-MM-DD (local time).
Check for an existing entry at .great-authors/journal/YYYY-MM-DD.md. If it exists, ask: "A journal entry already exists for today. Append to it, or start a new section? (append/new/cancel)" — default append. If cancel, exit.
Interview the user with seven questions, one at a time. The structured fields support /authors-consolidate, which scans journal entries for repeated decisions and offers to promote them to the permanent bible.
a. Worked on — which chapter, scene, or section did you work on today? One line. b. Decisions made — list any choices that affect the project going forward (character detail confirmed, timeline shifted, scene cut or moved, voice rule adjusted). Up to 3-5 bullets. "None" is a valid answer. c. Characters introduced — any new on-page characters today, or significant new detail about an existing character? Up to 3 bullets. "None" is valid. d. Plants laid — any audience-vs-character knowledge plants this session (foreshadowing, withheld information, a detail the audience now knows that the protagonist does not)? Up to 3 bullets. "None" is valid. e. Plants paid off — any earlier plants that paid off in today's work? Up to 3 bullets. "None" is valid. f. Continuity flags — anything you noticed that may contradict the bible or earlier chapters and that you want a future continuity pass to look at? Up to 3 bullets. "None" is valid. g. Unresolved — what's in flux? Questions you haven't answered, threads you haven't followed, character motivations you're still deciding. Up to 3 bullets. h. Where you left off — one sentence. Literal — what's the very next thing to work on when you return.
Write the entry. Format:
# YYYY-MM-DD
## Worked on
<answer from question a>
## Decisions made
- <bullet>
- <bullet>
<...or "None."...>
## Characters introduced
- <bullet>
<...or "None."...>
## Plants laid
- <bullet>
<...or "None."...>
## Plants paid off
- <bullet>
<...or "None."...>
## Continuity flags
- <bullet>
<...or "None."...>
## Unresolved
- <bullet>
<...or "Nothing new today."...>
## Next session
<answer from question h>
If appending, add a new section ## Session N (increment from existing session count) above the standard sections, or re-open the most recent session's content for append. Default to adding a new ## Session 2 style header so each session remains distinct.
Confirm:
Wrote .great-authors/journal/YYYY-MM-DD.md
Next session: <the "where you left off" line>
When you resume, any author persona you invoke will read this entry first to reorient.
## Before you edit protocol. Be concise — personas only read the most recent entry./authors-consolidate, which periodically scans journals for recurring decisions and offers to promote them to the permanent bible. Free-form journal entries don't support consolidation as well; the structure is what makes the long-arc accounting tractable.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.