narrative-write
Skill2 starsChanged 3 months agoMITView on GitHub
Write, continue, refine, or finalise prose and screenplay narrative from story artifacts while preserving approved story decisions and continuity. Use for scenes, chapters, dialogue in context, partial or complete manuscripts, screenplay pages, rough drafts, prose refinement, and discovery writing.
In this repository27 other files it gives its agents.
- acquire-codebase-knowledgeSkill
- ai-qa-reviewSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- contract-testingSkill
- documentation-and-adrsSkill
- github-actions-hardeningSkill
- github-issuesSkill
- incremental-implementationSkill
- nodeSkill
- release-readinessSkill
- risk-based-testingSkill
- security-and-hardeningSkill
- skill-creatorSkill
- skill-optimizerSkill
- systematic-debuggingSkill
- test-strategySkill
- typescript-magicianSkill
- unit-testingSkill
- verification-before-completionSkill
- writing-skillsSkill
- narrative-continuitySkill
- narrative-developSkill
- narrative-evaluateSkill
- narrative-pack-createSkill
- narrative-reviseSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Write at the requested resolution.
- Distinctive: line 42
If drafting reveals a material story discovery, identify the affected planning artifact and update or recommend updating it.
- Distinctive: line 46
If the requested execution cannot satisfy an approved upstream decision, surface the conflict instead of hiding it with prose.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Narrative Write
Turn sufficiently developed narrative intent into actual prose or screenplay execution.
Operating sequence
- Identify form and target scope: scene, chapter, sequence, episode, manuscript section, or screenplay section.
- Load only relevant story artifacts and nearby narrative.
- Determine
draft,refine, orfinal. - Preserve approved upstream decisions.
- Write at the requested resolution.
- Surface discoveries that materially change upstream story state.
Context
Typical context includes the current scene card, relevant beats, involved character profiles, applicable world constraints, current continuity, unresolved setup/payoff, nearby narrative and explicit voice requirements. Do not load the whole project automatically.
Rough writing
Prioritise scene function, behaviour, conflict, information flow, meaningful change and continuity before line polish.
Refinement
Improve only the requested dimensions: voice, dialogue, subtext, pacing, specificity, description, POV, rhythm or screenplay economy. Preserve declared outcomes, reveals and other approved decisions.
Prose
Support narration, interiority, POV, dialogue, chapters and scene transitions without forcing screenplay constraints.
Screenplay
Support scene headings, visible action and dialogue. Prefer Fountain when a portable screenplay text format is useful. Do not invent shot lists, cinematography, storyboards or visual character design unless handed to the downstream domain.
Discovery writing
If drafting reveals a material story discovery, identify the affected planning artifact and update or recommend updating it. Do not silently diverge.
Upstream conflicts
If the requested execution cannot satisfy an approved upstream decision, surface the conflict instead of hiding it with prose.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.