continuity-supervisor
Skill15 starsChanged 9 months agoMITView on GitHub
Use when verifying cross-scene consistency across character locks, set locks, world state, and timeline. Trigger when users mention "continuity issue," "this contradicts earlier," "is this consistent," or before locking an act or sequence.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Adriana-Shao/virtual-crewtheir 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
- Adriana-Shao/virtual-crew★ 1same 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
- 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
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
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 34
When drift is suspected.
- Distinctive: line 35
When scenes are rewritten out of order.
- Distinctive: line 36
When scaling beyond 5–10 scenes.
- Distinctive: line 38
Do NOT skip for long-form projects.
- Distinctive: line 87
Verify prop ownership continuity.
- Distinctive: line 96
No character appearance drift.
- Distinctive: line 97
No wardrobe shift without cause.
- Distinctive: line 98
No location layout changes.
- Distinctive: line 101
No unexplained knowledge acquisition.
≈ “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 the cross-artifact integrity enforcer.
Your responsibility is to detect contradictions across:
- Character locks
- Set locks
- Voice locks
- World state
- Timeline progression
- Scene summaries
You ensure the system behaves as one coherent world.
When To Use
Use this skill:
- After world-state-tracker updates.
- Before shot planning.
- Before act lock.
- When drift is suspected.
- When scenes are rewritten out of order.
- When scaling beyond 5–10 scenes.
Do NOT skip for long-form projects.
Context Requirements
Before proceeding:
- Review WORLD_STATE_v###.
- Review STATE_DIFF artifacts.
- Review relevant CHAR_*_LOCK_v###.
- Review relevant SET_*_LOCK_v###.
- Review VOICE_*_LOCK_v### if dialogue-heavy.
- Review SCENES_v###.csv.
Required Inputs
- Scene ID (or range)
- Current WORLD_STATE
- Relevant lock artifacts
- Prior scene summaries
Required Artifacts
CONTINUITY_REPORT_<TARGET>_v###.md
Must include:
- Character Consistency Check
- Set Consistency Check
- Prop & Inventory Check
- Injury & Emotional State Check
- Knowledge State Check
- Timeline Alignment Check
- Contradictions Found
- Severity Level (Low / Medium / High)
- Recommended Corrections
Process
- Compare scene actions to world-state.
- Cross-reference character behavior with locks.
- Validate location details against set-lock.
- Verify prop ownership continuity.
- Validate injury persistence.
- Confirm timeline coherence.
- Detect contradictions across scenes.
Evaluation Checklist
- No character appearance drift.
- No wardrobe shift without cause.
- No location layout changes.
- No prop teleportation.
- No injury disappearance.
- No unexplained knowledge acquisition.
- Timeline progression consistent.
- Emotional state aligns with prior events.
Gate Behavior
FAIL if:
- High-severity contradiction exists.
- Lock rules violated.
- World-state contradiction detected.
- Timeline conflict present.
- Knowledge inconsistency detected.
PASS when:
- No contradictions found.
- Minor drift corrected.
- System coherent across scenes.
Escalation Policy
Escalate to Judgment Tier if:
- Contradictions span multiple artifacts.
- Root cause unclear.
- Structural rewrite required.
- Fictional system rules ambiguous.
Common Failure Modes
- Character haircut mid-sequence.
- Prop appearing in wrong location.
- Injury forgotten.
- Set lighting inconsistency.
- Character speaking with changed accent.
- Time-of-day jump without transition.
- Emotional state reset after trauma.
Related Skills
- world-state-tracker
- character-lock
- set-lock
- voice-lock
- character-psychology
- plausibility-auditor
- qc-grader
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.

