KS
Killer-Skills

anviloop-nightly — Categories.community

v1.0.0
GitHub

About this Skill

Ideal for Automation Agents requiring nightly disk space management and queue cleanup protocols For nightly runs

MoniVibe MoniVibe
[0]
[0]
Updated: 3/4/2026

Quality Score

Top 5%
21
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add MoniVibe/HeadlessRebuildTool/anviloop-nightly

Agent Capability Analysis

The anviloop-nightly MCP Server by MoniVibe is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Ideal for Automation Agents requiring nightly disk space management and queue cleanup protocols

Core Value

Empowers agents to enforce disk gates, stopping builds when free space falls below 40 GB, and automates queue cleanup using PowerShell scripts like cleanup_queue.ps1, ensuring efficient resource allocation and data retention

Capabilities Granted for anviloop-nightly MCP Server

Automating disk space checks for nightly builds
Scheduling queue cleanup with retention policies
Ensuring WSL runner and Intel ingest daemon stability

! Prerequisites & Limits

  • Requires PowerShell compatibility
  • Dependent on specific directory structures like C:/polish/queue
  • Limited to 7-day retention and 3 last builds per scenario
Project
SKILL.md
1.4 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Anviloop Nightly Protocol

Gates and cleanup (do first)

  • Disk gate: pwsh -NoProfile -Command "'C_free_GB=' + [math]::Round((Get-PSDrive C).Free/1GB,1)"
    • Stop builds if < 40 GB.
  • Queue cleanup: pwsh -NoProfile -File Polish/cleanup_queue.ps1 -QueueRoot "C:/polish/queue" -RetentionDays 7 -KeepLastPerScenario 3 -Apply

Required daemons

  • WSL runner: ./Polish/WSL/wsl_runner.sh --queue /mnt/c/polish/queue --daemon --print-summary --status-interval 60
  • Intel ingest: Polish/Intel/anviloop_intel.py
  • Scoreboard/headline: Polish/Goals/scoreboard.py

Nightly structure

  • Cycle 0 sentinel once (FTL); proof in out/player.log contains [Anviloop][FTL] FTL_JUMP with tick >= 30.
  • Exactly one concept goal per night.
  • Do not change scenario and code in the same cycle (code-only first).

Validity + chain-of-custody

  • INVALID if telemetry missing/truncated, invariants missing, or oracle keys missing.
  • Keep commits only with headless proof.
  • Commit in artifact manifest must match result meta.json.

Stop/switch rules

  • If the same failure signature repeats twice, consult the ledger first.
  • If disk drops below gate, stop builds and switch to analysis/doc.

References

  • C:/Dev/unity_clean/headlessrebuildtool/Polish/Docs/NIGHTLY_PROTOCOL.md
  • C:/Dev/unity_clean/headlessrebuildtool/Polish/Docs/MORNING_VIEW.md
  • C:/Dev/unity_clean/headlessrebuildtool/Polish/Docs/ANVILOOP_RECURRING_ERRORS.md

Related Skills

Looking for an alternative to anviloop-nightly or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication