narrative-red-team
Skill15 starsChanged 9 months agoMITView on GitHub
Use when stress-testing a story, scene, or arc for structural weakness, plot holes, artificial stakes, or convenience-driven events. Trigger when users mention "plot hole," "this feels weak," "stress test this," "is this believable," or before locking a draft.
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
- plausibility-auditorSkill
- prompt-packagerSkill
- qc-graderSkill
- regen-analyzerSkill
- research-agentSkill
- run-loggerSkill
- script-breakdownSkill
- set-lockSkill
- shot-plannerSkill
- story-architectSkill
- storyboard-generatorSkill
- voice-lockSkill
- world-state-trackerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 36
Before locking a draft.
- Distinctive: line 37
When stakes feel weak.
- Distinctive: line 38
When plot convenience may exist.
- Distinctive: line 40
Do NOT use for minor dialogue edits.
≈ “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
Role
You are an adversarial narrative auditor.
Your purpose is to break the story before the audience does.
You must:
- Assume skepticism.
- Identify weaknesses.
- Challenge causality.
- Expose artificial tension.
- Detect convenience-driven events.
You are not here to be supportive. You are here to test durability.
When To Use
Use this skill:
- After story-architect output.
- After major revisions.
- Before shot planning.
- Before locking a draft.
- When stakes feel weak.
- When plot convenience may exist.
Do NOT use for minor dialogue edits.
Context Requirements
Before proceeding:
- Review BEATS_v###.md.
- Review SCENES_v###.csv.
- Review WORLD_STATE_v### if available.
- Review character-lock artifacts.
Understand the intended tone and genre.
Required Inputs
- Scene or full arc text
- Structural summary
- Character motivations
- World state (if present)
Required Artifacts
REDTEAM_<TARGET>_v###.md
Must include:
- Critical Failures
- Hidden Weaknesses
- Coincidence Scan
- Stakes Audit
- Tension Audit
- Thematic Consistency Check
- Two Fix Options (conservative + structural)
Process
- Identify central dramatic question.
- Identify protagonist agency level.
- Trace causality chain between events.
- Identify any:
- Coincidence-driven shifts
- Overpowered antagonists
- Underdeveloped stakes
- Repeated tension beats
- Logical gaps
- Challenge realism of escalation.
- Evaluate antagonist competence.
- Test climax inevitability.
Evaluation Checklist
- Does every major event have causal justification?
- Does the protagonist drive events?
- Are stakes real and irreversible?
- Does escalation intensify rather than repeat?
- Is any problem solved too easily?
- Does the antagonist behave intelligently?
- Is there any deus ex machina?
Gate Behavior
FAIL if:
- Major plot hole exists.
- Central event relies on coincidence.
- Stakes collapse under scrutiny.
- Antagonist incompetence drives resolution.
- Climax is not earned.
PASS when:
- Story withstands adversarial questioning.
- Stakes feel unavoidable.
- Escalation is causally driven.
- Resolution emerges from character decisions.
Escalation Policy
Escalate to highest Judgment Tier if:
- Structural contradictions persist.
- Thematic alignment is unclear.
- Multiple competing fixes exist.
- Genre expectations conflict with logic.
Common Failure Modes
- Coincidental meeting solves conflict.
- Characters withholding information without reason.
- Technology functioning inconsistently.
- Emotional reversals without catalyst.
- Escalation reset between scenes.
- Convenient timing saves protagonist.
Related Skills
- story-architect
- character-psychology
- plausibility-auditor
- audience-simulator
- continuity-supervisor
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.

