Bulk Maintenance logo

Bulk Maintenance

Community
kevinpbuckley
bulk-maintenance

Plan, dry-run, apply, verify, roll back, and resume explicit bounded batches for Blueprint interface migration, metadata hygiene, asset naming/organization, and unused-asset cleanup preparation.

Overview

Publisherkevinpbuckley
RepositoryVibeUE
Skill namebulk-maintenance
Stars
735
Forks
161
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by kevinpbuckley on GitHub. Read the source before you install it.

Installation

Install the Bulk Maintenance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/bulk-maintenance
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git /tmp/VibeUE
mkdir -p .claude/skills
cp -r /tmp/VibeUE/Content/Skills/bulk-maintenance .claude/skills/bulk-maintenance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bulk Maintenance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bulk Maintenance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bulk Maintenance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Safe Bulk Maintenance

Use unreal.WorkflowService.run_bulk_maintenance(plan_json, apply, batch_size, stop_on_error) for an explicit target list. It is dry-run-first, path-scoped, bounded to 100 targets per GC batch, returns one result per target, rolls back a failed apply operation, and writes a resumable report under Saved/VibeUE/Bulk.

Rules:

  1. Discover candidates, but pass the final explicit targets array yourself. Never turn a search result directly into deletion.
  2. Call once with apply=False, inspect every would-change/refusal, then repeat the exact plan with apply=True and the same resume_id.
  3. Set path_scope so a malformed target cannot escape the intended content folder.
  4. Use a small batch_size (10–25) for Blueprint work. Each apply target gets a named transaction; compile/save failure is reported as failure and rolled back.
  5. Wrap an unattended task in start_run / finish_run; attach the bulk report and verification.

1. Blueprint interface migration

Discover implementers/referencers with GameIQ when available, compile the candidates before the change, and migrate in two reviewed phases:

python
import json, unreal
plan = {
  "resume_id": "combat-interface-v2",
  "operation": "interface_add",
  "path_scope": "/Game/Combat",
  "interface": "/Game/Combat/Interfaces/BPI_CombatV2",
  "targets": ["/Game/Combat/BP_Rifle", "/Game/Combat/BP_Sword"]
}
print(unreal.WorkflowService.run_bulk_maintenance(json.dumps(plan), False, 10, True))
# Review, then use True. Remove the old interface only after compile/readback proves v2 is present.

interface_add and interface_remove compile each Blueprint and save only verified successes.

2. Blueprint metadata hygiene

Descriptions are caller-provided intent; the service never invents text. Existing authored metadata is preserved unless that specific target says "overwrite": true.

json
{"resume_id":"combat-metadata-1","operation":"variable_metadata","path_scope":"/Game/Combat","targets":[
  {"asset":"/Game/Combat/BP_Rifle","variable":"Ammo","category":"Weapon|Ammo","description":"Rounds remaining in the current magazine."},
  {"asset":"/Game/Combat/BP_Sword","variable":"Damage","category":"Weapon|Damage","description":"Base damage before modifiers."}
]}

3. Asset naming and organization

Audit naming separately, resolve collisions, then supply explicit source/destination pairs. Moves outside path_scope and existing destinations are refused.

json
{"resume_id":"weapon-moves-1","operation":"asset_move","path_scope":"/Game/Weapons","targets":[
  {"source":"/Game/Weapons/Rifle","destination":"/Game/Weapons/Blueprints/BP_Rifle"}
]}

After apply, fix redirectors with the normal Unreal workflow and re-run GameIQ references/impact.

4. Dead/unused cleanup preparation

Use cleanup_review with GameIQ ProjectStats("unused") plus Impact evidence. This operation is deliberately report-only even in apply mode. Deletion is a separate, human-approved action using the reviewed exact list; an unused heuristic alone is never approval.

Partial failure and resume

Reports contain a stable targetKey, aggregate counts, rollback status, and reportPath. Repeat with the same resume_id; previously successful targets are resumed-skip, so a crash or stop-on-error does not duplicate completed work. Fix failed inputs, keep the same explicit scope, and rerun.

Frequently asked questions

What does the Bulk Maintenance AI skill do?

Plan, dry-run, apply, verify, roll back, and resume explicit bounded batches for Blueprint interface migration, metadata hygiene, asset naming/organization, and unused-asset cleanup preparation.

Why use Bulk Maintenance on TypingMind?

Because you install it once and use it with any model. Bulk Maintenance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bulk Maintenance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/bulk-maintenance. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bulk Maintenance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bulk Maintenance?

As many as you like. As long as a model supports skills, you can use Bulk Maintenance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bulk Maintenance AI skill free?

Yes. It is published on GitHub by kevinpbuckley under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇