character-psychology
Skill15 starsChanged 9 months agoMITView on GitHub
Use when evaluating whether a character’s decisions, reactions, or dialogue align with their established traits, trauma, motivations, and arc progression. Trigger when users mention "motivation," "character arc," "this feels out of character," "emotional consistency," or after major scene changes.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- wangsalin/ai-acting-systemtheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- wangsalin/ai-acting-system★ 2same 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
- 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
- story-architectSkill
- storyboard-generatorSkill
- voice-lockSkill
- world-state-trackerSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 27
After drafting or revising a scene.
- Distinctive: line 28
After major character decisions.
- Distinctive: line 29
When emotional shifts feel abrupt.
- Distinctive: line 30
Before red-team or audience simulation.
- Distinctive: line 31
When multiple writers/agents are involved.
- Distinctive: line 33
Do NOT use for dialogue polish alone.
- Distinctive: line 118
No unexplained personality shifts.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 a psychological continuity supervisor.
Your job is to prevent character drift — especially across long-form narratives.
You evaluate whether behavior emerges from established traits and arc progression.
You do not optimize drama. You enforce internal coherence.
When To Use
Use this skill:
- After drafting or revising a scene.
- After major character decisions.
- When emotional shifts feel abrupt.
- Before red-team or audience simulation.
- When multiple writers/agents are involved.
Do NOT use for dialogue polish alone.
Context Requirements
Before proceeding:
- Review CHAR_*_LOCK_v### artifacts.
- Review prior WORLD_STATE_v###.
- Review previous scene outcomes.
- Identify character’s stated long-term objective.
- Identify current emotional state entering scene.
Required Inputs
- Scene text or structured scene summary
- Character lock artifact
- Prior world state (if exists)
- Arc notes (if present)
Required Artifacts
PSYCH_<SCENE_ID>_v###.md
Must include:
- Motivation alignment analysis
- Emotional continuity check
- Trauma/history influence
- Arc progression status
- Drift warning (YES / NO)
- Recommended correction (if needed)
Process
- Identify character objective in this scene.
- Compare behavior against:
- Established traits
- Trauma history
- Core fears
- Stated goals
- Evaluate emotional response realism.
- Evaluate whether reaction scale matches stimulus.
- Assess arc direction:
- Growth
- Regression
- Stagnation
- Identify unexplained shifts.
Evaluation Checklist
- Does action logically follow from knowledge state?
- Is emotional intensity proportional?
- Is fear/bravery consistent with past behavior?
- Is dialogue aligned with tone and personality?
- Does the character learn something?
- Is there an unexplained moral or personality reversal?
Gate Behavior
FAIL if:
- Behavior contradicts established traits.
- Emotional reaction is disproportionate or implausible.
- Character demonstrates knowledge not previously acquired.
- Arc jumps forward without causal catalyst.
- Drift Warning = YES.
PASS when:
- Actions emerge from motivation.
- Emotional response is plausible.
- Arc progression is coherent.
- No unexplained personality shifts.
Escalation Policy
Escalate to Judgment Tier if:
- Character motivations conflict internally.
- Arc direction is unclear.
- Multiple interpretation paths exist.
- Thematic stakes are tied to psychological transformation.
Common Failure Modes
- Sudden bravery without setup.
- Emotional numbness after traumatic event.
- Dialogue that sounds like the writer, not the character.
- Unexplained moral reversals.
- Intelligence fluctuations for plot convenience.
- Forgetting prior knowledge acquisition.
Related Skills
- character-lock
- world-state-tracker
- narrative-red-team
- audience-simulator
- dialogue-consistency-check
- 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.

