narrative-continuity
Skill2 starsChanged 3 months agoMITView on GitHub
Maintain narrative continuity and assemble task-relevant story context across long-form or evolving narrative work. Use to track canon versus plans, character beliefs and knowledge, important world rules, chronology, unresolved story state, continuity conflicts, and the context needed for a new scene or revision.
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-developSkill
- narrative-evaluateSkill
- narrative-pack-createSkill
- narrative-reviseSkill
- narrative-writeSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 35
After approved narrative changes, update only the state actually changed.
- Distinctive: line 39
Use portable files and explicit records.
≈ “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 Continuity
Maintain enough explicit story state to prevent drift without turning the project into a knowledge-engineering platform.
Use when
- continuing long-form or multi-scene work;
- checking contradictions;
- updating canon;
- tracking character knowledge or beliefs;
- tracking consequential chronology or world rules;
- preparing context for a scene or revision;
- assessing impact of an upstream change.
Narrative state
At minimum distinguish planned, canonical, character-belief, secret, uncertain, and superseded.
An outline event is not canon merely because it is planned. Promote it only when approved narrative establishes it.
Character belief, reader knowledge, narrator knowledge and objective story truth are not interchangeable.
Context assembly
Identify the target, involved characters, relevant beats/outline region, applicable world constraints, relevant continuity and nearby narrative. Omit unrelated artifacts and rejected branches.
Updating continuity
After approved narrative changes, update only the state actually changed. Identify potentially affected future material but do not rewrite it unless asked.
Boundaries
Use portable files and explicit records. Do not require automatic fact extraction, knowledge graphs, vector search, entity-resolution services, temporal engines or hidden model memory.
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.

