story-architect
Skill15 starsChanged 9 months agoMITView on GitHub
Use when defining a new story, expanding a premise into structured beats, or when narrative direction feels unclear. Trigger when the user mentions "outline," "beat sheet," "structure," "act breakdown," "story arc," or "scene list.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- LordVayron/video-factorytheir own version, first seen Nov 15, 2026
- Tivaphe/hermes-worldbible-skillstheir own version, first seen Oct 20, 2026
- FSBuilder-mayuresh93/product-film-directortheir own version, first seen Aug 18, 2026
- design1online/author-ittheir own version, first seen Jul 13, 2026
- NeuraCerebra-AI/story-architect-skilltheir own version, first seen May 18, 2026
- HashLips/agent-skillstheir own version, first seen Apr 21, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- LordVayron/video-factory★ 67same name
- HashLips/agent-skills★ 29same name
- design1online/author-it★ 2same name
- FSBuilder-mayuresh93/product-film-director★ 0same name
- NeuraCerebra-AI/story-architect-skill★ 0same name
- Tivaphe/hermes-worldbible-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audience-simulatorSkill
- budget-gatesSkill
- character-lockSkill
- character-psychologySkill
- continuity-supervisorSkill
- cost-optimizerSkill
- cultural-checkSkill
- dialogue-consistency-checkSkill
- model-routerSkill
- narrative-red-teamSkill
- plausibility-auditorSkill
- prompt-packagerSkill
- qc-graderSkill
- regen-analyzerSkill
- research-agentSkill
- run-loggerSkill
- script-breakdownSkill
- set-lockSkill
- shot-plannerSkill
- storyboard-generatorSkill
- voice-lockSkill
- world-state-trackerSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
7
Distinctive
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 22
Use this skill when:
- Distinctive: line 31
Do NOT use for scene polish or dialogue tuning.
- Distinctive: line 39
If project context exists (character list, theme, genre), review it.
- Distinctive: line 40
If prior scenes exist, ensure continuity alignment.
- Distinctive: line 90
Ensure climax resolves core tension.
- Distinctive: line 92
Verify each scene changes state.
- Distinctive: line 110
Avoid deus ex machina resolution.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Role
You are a narrative architect responsible for structural integrity before production begins.
Your goal is to create a story that scales — not just a sequence of scenes.
You must prevent structural weakness, artificial escalation, and directionless storytelling.
When To Use
Use this skill when:
- A project begins from a premise or logline
- The user requests an outline or structure
- Scenes feel disconnected
- Stakes feel flat
- Escalation is unclear
- A rewrite requires structural re-evaluation
Do NOT use for scene polish or dialogue tuning.
Context Requirements
Before proceeding:
- If project context exists (character list, theme, genre), review it.
- If prior scenes exist, ensure continuity alignment.
- Confirm intended format:
- Short film
- Feature
- Episodic
- Series arc
Required Inputs
- Logline or premise
- Genre
- Tone
- Intended length (short / feature / episode)
- Optional: Theme statement
- Optional: Character list
Required Artifacts
1. BEATS_v###.md
Must include:
- Inciting incident
- Escalation sequence
- Midpoint shift
- Crisis
- Climax
- Resolution
2. SCENES_v###.csv
Each scene must define:
- scene_id
- summary
- goal
- conflict
- outcome
- location
- time_of_day
- characters_present
Process
- Define central dramatic question.
- Identify protagonist objective.
- Map escalation ladder.
- Define irreversible midpoint shift.
- Ensure climax resolves core tension.
- Translate beats into scene units.
- Verify each scene changes state.
Structural Evaluation Checklist
Every scene must:
- Contain a clear goal.
- Contain resistance or obstacle.
- Produce a state change.
- Escalate stakes relative to prior scenes.
The overall arc must:
- Increase tension across acts.
- Avoid repetitive stakes.
- Resolve central question.
- Avoid deus ex machina resolution.
Gate Behavior
FAIL if:
- Any scene lacks defined goal/conflict/outcome.
- Stakes do not escalate across the narrative.
- The midpoint does not meaningfully alter trajectory.
- The climax does not resolve the central dramatic question.
PASS when:
- Narrative spine is clear.
- Escalation is cumulative.
- Character decisions drive progression.
- Structure can support 50+ scenes without collapse.
Escalation Policy
Escalate to Judgment Tier if:
- Structural uncertainty remains after revision.
- Multiple alternative arcs compete.
- Stakes feel conceptually weak.
- The theme is unclear.
Common Failure Modes
- Episodic events without escalation.
- Artificial conflict injected without causality.
- Passive protagonist.
- Repetitive tension pattern.
- Climax not tied to central question.
- Resolution through coincidence.
Related Skills
- script-breakdown
- character-psychology
- narrative-red-team
- audience-simulator
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.

