back
loading skill details...
fiction-workshop — an installable skill for AI agents, published by rhavekost/author-toolkit.
Fiction Workshop Editorial workflow for collaborative fiction writing in three stages: Story Bible Building, Chapter Development, and Reader Testing. When to Use This skill is for: ✅ Long-form fiction (novels, novellas, short story collections) ✅ Multi-chapter manuscripts requiring character/plot consistency ✅ Fiction projects needing developmental or line editing ✅ Stories with complex worldbuilding or multiple POV characters When NOT to Use This skill is NOT for: ❌ Flash fiction or single scenes (< 2000 words) - too lightweight for the workflow ❌ Poetry or experimental prose - needs different editorial approach ❌ Screenplays or stage plays - different format conventions ❌ Technical writing, documentation, or academic papers ❌ Business writing or marketing copy For narrative nonfiction (memoir, self-help with story elements), use the narrative-nonfiction skill instead. Editorial Personas Switch between these roles during Chapter Development by requesting a specific lens: Role Invocation Focus Developmental Editor "As developmental editor..." Plot, pacing, structure, stakes, theme Line Editor "As line editor..." Prose rhythm, word choice, "show don't tell" Character Consultant "As character consultant..." Voice consistency, motivation, arc, relationships Continuity Tracker "As continuity tracker..." Timeline, world facts, internal consistency Brainstorm Partner "Brainstorm mode..." "What if" exploration, problem-solving, unsticking See references/ for detailed guidance on each role. Stage 1: Story Bible Building Goal: Establish shared story foundation before drafting or editing. Initial Questions Genre and target reader? Core premise/logline? Protagonist: who they are, what they want? Central conflict? Reader's intended emotional journey? How much written vs. planned? Story Bible Components Plot: Premise, three-act structure/beat sheet, major turns, ending (even if rough) Characters: Protagonist (want/need/wound/arc), antagonist (motivation/threat), supporting cast (function/relationships), POV voice notes World: Setting (time/place/rules), tech/magic systems, social structures, sensory palette Theme: Central question, moral argument, recurring motifs If a Story Bible document exists, review it. If not, offer to create one using assets/story-bible-template.md. Example Story Bible entry (character): ALEX CHEN - Protagonist Want: Expose the conspiracy and clear her name Need: Learn to trust her instincts over institutional authority Wound: Mentor betrayed her at previous agency, causing career setback Arc: Lone wolf → realizes she needs allies → builds trust with team Voice notes: Analytical, dry humor when stressed, avoids emotional language Key relationship: Tension with Handler (wants to trust, can't fully) Exit condition: Confident grasp of story fundamentals. Can discuss character motivations, predict plot implications, and identify thematic threads without asking basic questions. Stage 2: Chapter Development Goal: Draft or refine chapters through brainstorm → curate → draft → refine cycles. Drafting new? → Creation workflow | Editing existing? → Editing workflow Creation Workflow Scene Planning What must happen (plot)? Whose POV? Chapter's emotional arc? What reader learns/feels by end? Brainstorm Beats (5-15 options): Opening hooks, key moments, dialogue, sensory details, closing Example (thriller scene): Same car outside coffee shop three days running | Phone buzzing at 3am with blocked caller | Surveillance photo under door | Colleague mentions detail only surveillance would know | Camera lens reflection in window | Dead drop cleaned out | Safe house key doesn't fit | Contact misses first check-in Then curate: "Which create immediate tension? Combine any?" Curate: Ask which to keep, combine, or discard. Reasons help calibrate. Draft: Write chapter. Use str_replace for revisions, never reprint. Refine: Iterate on feedback. After 3 passes with minimal changes, ask: "What could be cut?" Editing Workflow Read and Diagnose: What chapter tries to do, where it succeeds, where it loses energy/clarity Invoke Persona: Structure/pacing → Developmental | Prose → Line | Voice → Character | Facts → Continuity Propose Changes: Specific, surgical edits with brief "why" Implement: Use str_replace. Link to file after changes. Iterate: Until chapter achieves purpose Role-Specific Guidance When a specific editorial persona is invoked, load the corresponding reference file: Developmental editing → references/developmental-editing.md Line editing → references/line-editing.md Character work → references/character-work.md Continuity → references/continuity-tracking.md Brainstorming → references/brainstorming.md Thriller-specific craft → references/thriller-craft.md Sci-fi worldbuilding → references/scifi-worldbuilding.md Stage 3: Reader Testing Goal: Verify manuscript works without author context. Using fresh sub-agent (no story bible): Comprehension: Can they summarize plot, understand motivations, identify stakes? Engagement: Where did they lose interest, have questions, feel confused? Emotional: Did key moments land? Ending satisfying? Theme clear? Common issues: Unclear motivation | Pacing lags | Unearned moments | Confusion If struggles: Identify gap → Return to Stage 2 → Re-test Exit condition: Reader understands and engages without author explanations. Self-Check: Is This Working? Use these checkpoints to verify you're following the workflow correctly. After Story Bible building: Can you describe the protagonist's want vs. need without re-reading notes? Can you predict how the antagonist would react to a new scenario? Do you understand the thematic question the book explores? Could you summarize the three-act structure in 2-3 sentences? After invoking a persona: Did you explicitly say "As [persona name]..." in your request? Is the feedback focused on that persona's domain (developmental = structure, line = prose)? Did you avoid mixing feedback from multiple personas in one pass? After making edits: Did you use str_replace for surgical changes, not reprinting entire sections? Can you articulate what changed and why it's better? Is the change consistent with the Story Bible (character voice, plot logic, world rules)? After brainstorming: Did you generate 5+ options before selecting one? Did you curate collaboratively rather than taking the first suggestion? Can you explain why the selected option is stronger than alternatives? Before claiming "done": Has a fresh sub-agent (without Story Bible context) read the manuscript? Did the fresh reader understand plot, character motivations, and stakes? Were any gaps or confusion points identified and addressed? If you answered "no" to any checkpoint, return to that stage before proceeding. Common Mistakes Mistake Why It Happens Fix Skipping Story Bible "I know my story well enough" Story Bible isn't for you—it's for Claude. Without shared context, feedback will miss key story elements. Build it. Generic feedback without persona Rushing, forgetting to invoke specific role Explicitly say "As developmental editor..." or "As line editor..." in your prompt. Different lenses catch different issues. Reprinting entire chapters Habit from other editing contexts Use str_replace for surgical edits only. Reprinting burns context and makes changes hard to track. Link to file after edits. Jumping to line edits before structure Wanting to "fix" prose immediately If plot/pacing/character issues exist, line edits are wasted effort. Always developmental pass first. See example below. Skipping Reader Testing "I've read it so many times already" You have author context. Reader Testing uses fresh sub-agent without story bible to catch gaps readers will hit. Too many personas at once Trying to fix everything in one pass Invoke one persona per pass. Developmental → Character → Line → Continuity. Focused feedback is actionable feedback. Brainstorming without curation Taking first idea that sounds good Generate 5-15 options, then curate. First idea is rarely best idea. Quantity enables quality. Example: Developmental vs. Line Editing Same passage, different lenses: Sarah walked into the office. Her boss looked angry. "We need to talk," he said. She sat down nervously. Line Editor feedback (prose-level): "Walked" is weak—try "strode" or "slipped" "Looked angry" tells rather than shows—describe furrowed brow, tight jaw "Nervously" is an adverb crutch—show the nervousness through action Developmental Editor feedback (structure/stakes): What does Sarah want in this scene? What does her boss want? If this is the confrontation, we need setup—what's the conflict history? Stakes feel low—why does this conversation matter to the story? Pacing: Is this the right chapter for this confrontation, or should tension build longer? The difference: Line edits polish sentences. Developmental edits ensure the scene earns its place in the story. Always developmental first. Quick Reference Commands Need Command Start new project "Let's build a story bible for [project]" Developmental pass "As developmental editor, analyze [chapter/section]" Line edit "As line editor, polish [scene/passage]" Character check "As character consultant, is [character]'s [action] in character?" Continuity audit "As continuity tracker, check [chapters X-Y] for inconsistencies" Get unstuck "Brainstorm mode—I need to [solve problem]" Test readability "Run a fresh read on [chapter/section]" Files references/developmental-editing.md - Plot, structure, pacing analysis references/line-editing.md - Prose-level refinement references/character-work.md - Voice, motivation, arc tracking references/continuity-tracking.md - Timeline and fact consistency references/brainstorming.md - Idea generation techniques references/thriller-craft.md - Genre-specific guidance for suspense references/scifi-worldbuilding.md - Technical accuracy, speculation rules assets/story-bible-template.md - Blank story bible structure assets/scene-worksheet.md - Scene-level analysis template
don't have the plugin yet? install it then click "run inline in claude" again.
mapped original workflow into explicit procedure steps with decision branches, documented external sub-agent requirement for stage 3, added edge cases (reprinting prevention, persona mixing, story bible gaps, brainstorm quantity minimums), clarified output contracts and success signals for each stage, preserved original author voice and reference file structure.
fiction-workshop guides long-form fiction projects through a structured three-stage editorial workflow: story bible building to establish shared story foundation, chapter development with rotating editorial personas for focused feedback, and reader testing with a fresh sub-agent to verify the manuscript works without author context. use this skill for multi-chapter manuscripts requiring character and plot consistency, complex worldbuilding, or multiple POV characters. avoid it for flash fiction under 2000 words, poetry, screenplays, technical writing, or business copy.
manuscript assets
external context
sub-agent availability
reference files (load as needed during chapter development)
stage 1: story bible building
establish story foundation. ask user for: genre and target reader, core premise/logline, protagonist identity and central want, central conflict, intended reader emotional journey, how much is written vs. planned. input: conversation with author. output: answers to seed story bible.
review or create story bible. if story bible exists, review it for completeness. if not, offer to create one using assets/story-bible-template.md. input: author responses or existing document. output: documented story bible covering plot (premise, three-act structure, major turns, ending), characters (protagonist want/need/wound/arc, antagonist motivation/threat, supporting cast function/relationships, POV voice notes), world (setting time/place/rules, tech/magic systems, social structures, sensory palette), and theme (central question, moral argument, recurring motifs).
verify story bible depth. confirm author can discuss character motivations without re-reading notes, predict antagonist reactions to new scenarios, articulate thematic question in one sentence, and summarize three-act structure in 2-3 sentences. input: story bible document and author confirmation. output: exit condition met when author demonstrates confident grasp of story fundamentals.
stage 2: chapter development
assess chapter status. determine if user is drafting new or editing existing chapter. input: chapter status and draft (if available). output: route to creation workflow or editing workflow.
creation workflow for new chapters.
editing workflow for existing chapters.
self-check after edits. verify: (a) explicit persona invocation in request, (b) feedback focused on that persona domain only, (c) no mixed feedback from multiple personas in single pass, (d) use of str_replace for surgical changes only (never reprinted sections), (e) articulation of what changed and why, (f) changes align with story bible (character voice, plot logic, world rules). input: completed editorial pass. output: pass/fail on each checkpoint; if any fail, loop back to step 6.
stage 3: reader testing
deploy fresh sub-agent. brief a new Claude sub-agent on manuscript WITHOUT story bible context to avoid author bias. input: chapter or manuscript section only (no story bible, character notes, or worldbuilding handouts). output: fresh sub-agent deployment.
test comprehension. ask fresh sub-agent to summarize plot, explain character motivations, and identify stakes. input: manuscript section. output: summary and motivation explanations from reader perspective.
test engagement. ask fresh sub-agent where reading lost momentum, what felt confusing, what raised questions. input: manuscript section. output: engagement gaps and confusion points identified.
test emotional landing. ask fresh sub-agent if key emotional moments landed, if ending felt satisfying, if theme came through without explicit author statement. input: manuscript section. output: emotional impact assessment.
diagnose and iterate. if fresh reader struggles with comprehension, engagement, or emotional beats, identify the gap (unclear motivation, pacing lag, unearned moment, confusion from missing info). input: reader testing results. output: gap diagnosis. return to stage 2 (chapter development) with specific fixes, re-test until reader understands and engages without author explanation. exit condition met when fresh reader fully grasps plot, character motivations, and stakes without clarification from author.
if story bible exists: review it for completeness and alignment with current manuscript state. if gaps identified, fill using template structure before proceeding to stage 2.
if story bible does not exist: offer to create one using assets/story-bible-template.md. do not skip to chapter development without shared context (see common mistakes below).
if user is drafting new chapter: use creation workflow (step 5). if user is editing existing chapter, use editing workflow (step 6).
if user forgets persona invocation: explicitly remind them to say "As [persona name]..." and request they re-submit prompt with persona specified. do not deliver generic feedback.
if user mixes multiple personas in single request: acknowledge the request, then process one persona at a time in sequence (e.g., "I'll give developmental feedback first, then we can do a line pass separately").
if editing pass produces reprinted sections: stop and revert to str_replace only. link to revised file location. explain that reprinting burns context tokens and obscures changes.
if chapter fails self-check on story bible alignment: halt iteration and flag misalignment (e.g., character action contradicts established arc, world rule broken, plot logic inconsistent). route back to story bible review before further edits.
if user claims "done" without stage 3 reader testing: require fresh sub-agent read before sign-off. author context blindness is real; unearned moments and plot holes often invisible to writer.
if fresh reader testing reveals major gaps: do not blame reader. identify structural or clarity issues, return to stage 2, make edits, re-test. repeat until fresh reader succeeds.
if brainstorming produces fewer than 5 options: expand the list before curation. first idea is rarely best idea; quantity enables quality.
if user wants to skip developmental editing and jump to line edits: refuse. line edits waste effort if plot, pacing, or character issues exist. always run developmental pass first (example provided in original skill).
stage 1 deliverable: completed story bible document (markdown or structured text) covering plot, characters, world, and theme sections. document must be reviewable by independent reader (fresh sub-agent) without author explanation.
stage 2 deliverables:
stage 3 deliverable: fresh sub-agent reader report documenting comprehension (plot summary, motivations, stakes identified), engagement gaps (pacing issues, confusion points, lost interest markers), and emotional impact (key moments landed yes/no, ending satisfaction, theme clarity). if failures identified, gap diagnosis and re-test plan linked.
file locations: all assets stored in assets/ subdirectory (templates, worksheets); all reference files in references/ subdirectory (persona guidance, craft guidance); all manuscript chapters and story bible in user-designated project directory with clear naming convention.
stage 1 success: author articulates story fundamentals without re-reading notes and confirms readiness for chapter development. story bible document complete and reviewable.
stage 2 success: chapter achieves intended purpose (plot function delivered, character voice consistent with story bible, emotional arc lands, pacing feels right for placement). self-check passes on all criteria. no remaining editorial feedback in that persona domain; if multiple personas involved, prior persona passes still hold.
stage 3 success: fresh sub-agent (no story bible) reads chapter and accurately summarizes plot, character motivations, and stakes. reader identifies no comprehension gaps, no confusing moments, no unearned emotional beats. reader confirms thematic thread comes through without explicit author statement. if any failure, gap is addressed and re-test passes.
user-visible signals: