narrative-evaluate
Skill2 starsChanged 3 months agoMITView on GitHub
Evaluate story concepts, outlines, beats, scenes, manuscripts, and screenplays using domain-native narrative criteria without silently rewriting them. Use for developmental editing, structural diagnosis, scene evaluation, artifact readiness, continuity-aware review, and editorial reports.
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-pack-createSkill
- narrative-reviseSkill
- narrative-writeSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 23
Check basic coherence, hard constraints, catastrophic contradiction, candidate distinctiveness and whether the artifact is worth developing.
- Distinctive: line 27
Verify requested correction, preservation, continuity and regressions.
- Distinctive: line 31
Run all applicable developmental checks.
- Distinctive: line 35
Use as applicable: premise, causality, character, conflict, stakes, structure, pacing, scene purpose, world consistency, continuity, POV, …
- Distinctive: line 43
Do not rewrite when evaluation only was requested.
≈ “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 Evaluate
Diagnose narrative quality and readiness without silently replacing the target artifact.
Operating sequence
- Identify target artifact and lifecycle state.
- Select only criteria meaningful at that resolution.
- Ground findings in actual evidence.
- Prioritise root causes over surface symptoms.
- Produce actionable findings rather than an unsolicited rewrite.
Lifecycle
Draft
Check basic coherence, hard constraints, catastrophic contradiction, candidate distinctiveness and whether the artifact is worth developing.
Refine
Verify requested correction, preservation, continuity and regressions.
Final
Run all applicable developmental checks. Prioritise structural/developmental issues before copy polish.
Quality dimensions
Use as applicable: premise, causality, character, conflict, stakes, structure, pacing, scene purpose, world consistency, continuity, POV, voice, dialogue, theme, tone, setup/payoff and genre/audience fit.
Findings
Each significant finding should identify category, severity, scope, location, evidence, diagnosis, affected material and recommendation.
Boundaries
Do not rewrite when evaluation only was requested. Do not force a universal story structure. Do not turn mechanical lint into a literary quality score. Do not require one numeric narrative-quality score.
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.