narrative-revise
Skill2 starsChanged 3 months agoMITView on GitHub
Plan and perform targeted narrative revision from editorial findings or direct feedback while preserving approved work. Use for developmental rewrites, scene repair, structural revision, applying notes, reopening approved decisions, impact analysis, and verifying that a correction succeeded without unnecessary regeneration.
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-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 20
Verify the correction and preservation constraints.
- Distinctive: line 42
Do not default to page-one rewrite or automatic dependency propagation.
≈ “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 Revise
Convert diagnosis or direct feedback into bounded narrative change.
Sequence
- Identify the actual problem.
- Identify the highest relevant root cause.
- Choose the smallest sufficient revision scope.
- State what must be preserved.
- State what may change.
- Identify downstream material actually affected.
- Revise.
- Verify the correction and preservation constraints.
Scope
Possible scopes include local passage, scene, beat, sequence/section, character arc, story outline and deliberate page-one rewrite.
Approved decisions
Approved work remains a constraint unless explicitly reopened. If a fix requires changing an approved upstream decision, identify it, explain why it must reopen, select the replacement direction and revise only affected descendants.
Root-cause targeting
- weak prose + sound scene → prose revision;
- weak scene design + sound beat → scene-card revision then affected scene;
- unmotivated beat → beat revision then affected scenes;
- weak causal section → affected outline region;
- premise failure → only then reopen high-level concept.
Verification
Confirm target issue improved, preserve constraints survived, continuity remains coherent and no major regression was introduced.
Do not default to page-one rewrite or automatic dependency propagation.
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.