Find CEngineServiceMgr RegisterPrerequisite logo

Find CEngineServiceMgr RegisterPrerequisite

Organization
HLND2T
find-CEngineServiceMgr_RegisterPrerequisite

Recover CEngineServiceMgr_RegisterPrerequisite in CS2 engine binaries (Windows and Linux) when the find-CEngineServiceMgr_RegisterPrerequisite preprocessor fails. Verify current vtable entries and function semantics rather than reusing historical addresses or signatures. Trigger: CEngineServiceMgr_RegisterPrerequisite

Overview

PublisherHLND2T
RepositoryCS2_VibeSignatures
Skill namefind-CEngineServiceMgr_RegisterPrerequisite
Stars
67
Forks
11
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 HLND2T on GitHub. Read the source before you install it.

Installation

Install the Find CEngineServiceMgr RegisterPrerequisite 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/HLND2T/CS2_VibeSignatures/tree/main/.claude/skills/find-CEngineServiceMgr_RegisterPrerequisite
  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/HLND2T/CS2_VibeSignatures.git /tmp/CS2_VibeSignatures
mkdir -p .claude/skills
cp -r /tmp/CS2_VibeSignatures/.claude/skills/find-CEngineServiceMgr_RegisterPrerequisite .claude/skills/find-CEngineServiceMgr_RegisterPrerequisite
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Find CEngineServiceMgr RegisterPrerequisite 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 Find CEngineServiceMgr RegisterPrerequisite 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 Find CEngineServiceMgr RegisterPrerequisite 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.

Find CEngineServiceMgr_RegisterPrerequisite (Agent fallback)

Recover the single output of find-CEngineServiceMgr_RegisterPrerequisite using the assigned IDA Pro MCP database. The preprocessor ida_preprocessor_scripts/find-CEngineServiceMgr_RegisterPrerequisite.py remains the normal fast path.

Realworld Function References

Read the applicable current inputs and the annotated references below. Source-owned 14192 YAMLs and stored disassembly are reference-build evidence; verify addresses, slot indices and semantics in the assigned binary. Never copy a reference target YAML into the active output directory as a substitute for analysis.

  • ida_preprocessor_scripts/references/engine/CLoopModeLevelLoad_LoopInit.windows.yaml
  • ida_preprocessor_scripts/references/engine/CLoopModeLevelLoad_LoopInit.linux.yaml
  • bin_artifacts/14192/engine/CEngineServiceMgr_vtable2.windows.yaml
  • bin_artifacts/14192/engine/ILoopModePrerequisiteRegistry_RegisterPrerequisite.windows.yaml
  • bin_artifacts/14192/engine/CEngineServiceMgr_vtable2.linux.yaml
  • bin_artifacts/14192/engine/ILoopModePrerequisiteRegistry_RegisterPrerequisite.linux.yaml

Output inventory

Module: engine. Platform scope: Windows and Linux. Analyze only the platform of the assigned database; the runner invokes platforms separately.

PlatformOutput filename14192 reference entryReference slot / offset
windowsCEngineServiceMgr_RegisterPrerequisite.windows.yaml0x180217c280 / 0x0
linuxCEngineServiceMgr_RegisterPrerequisite.linux.yaml0x3801400 / 0x0

Output metadata uses exactly vtable_name=CEngineServiceMgr_vtable2; the concrete table artifact is CEngineServiceMgr_vtable2.<platform>.yaml. Omit func_sig: this getter/thunk has no stable function signature under the producer contract.

Step 0. Bind the task and skip an existing output

Call idb_list and reuse the database assigned by the runner. Confirm the input path, image base and platform with IDA; do not open, switch, close or quit the runner's database. The binary is engine2.dll / libengine2.so. Resolve the active artifact module directory from CS2VIBE_ARTIFACT_DIR (also visible inside IDA's environment). If unset, stop and request the assigned artifact directory; never write YAML beside the binary. For the current platform, skip the output if it already exists there and parses as a non-empty mapping. Do not overwrite a result produced by an earlier alternative.

Load the platform-specific configured inputs named above from that active artifact root, not from the 14192 reference tree. Resolve ../client or ../server relative to the active module directory. Missing required inputs must be reported; do not open another binary to reconstruct them.

Step 1. Resolve the inherited interface entry

Use /get-func-from-yaml with func_name=ILoopModePrerequisiteRegistry_RegisterPrerequisite. The input may contain only interface call-site metadata; do not require func_va or invent a function body for the abstract interface. Check that vfunc_index and vfunc_offset agree (offset = index * 8). Read that slot in the current concrete table, and verify its live pointer against the active vtable artifact. Do not use the old target signature or reference slot as identity.

Step 2. Locate and verify the target

Read the current ILoopModePrerequisiteRegistry_RegisterPrerequisite slot metadata from the active engine artifact directory. The annotated CLoopModeLevelLoad_LoopInit references show an indirect registration call on the prerequisite registry before the level-name initialization path; they explain the slot's identity, not a concrete engine address.

Resolve that slot specifically in CEngineServiceMgr_vtable2, the registry secondary-base table. Verify RTTI/base adjustment and the live table pointer. Windows 14192 has a nine-byte thunk adjusting RCX by -0x28 and jumping to the implementation. Record the thunk entry and its size, not the destination or a primary-table getter. Linux 14192 has the real implementation at this table slot. A different future thunk shape is acceptable only after proving the same interface slot and registration semantics. The slot is not obtained by scanning the primary CEngineServiceMgr_vtable.

Step 3. Handle missing IDA function boundaries

A vtable YAML can exist even though IDA has not defined its target functions. For each plausible entry, verify the live 64-bit slot pointer, executable segment and decoded instruction boundary. If no function owns the entry, use conservative function definition and wait for analysis, then require the resulting function start to equal the slot pointer. Never delete bytes, split an existing function, or normalize an interior pointer to a neighbouring function's start. If a function already owns an unexpected interior entry, inspect and report the boundary conflict instead of forcing it.

Treat short adjusting thunks as legitimate vtable entrypoints. Follow their destinations for semantic verification, but preserve the slot's actual entry address in the artifact. Distinct-address candidate counts are not vtable slot counts. Confirm the target's slot by live pointer equality; use /get-vtable-index where helpful, and report multiple plausible slots rather than selecting an arbitrary duplicate.

Signatures and YAML output

Do not generate or carry forward func_sig, even if an old artifact contains one. Use /write-vfunc-as-yaml through its IDA py_eval implementation in the assigned session to write the YAML; do not substitute CLI shell or file-edit tools. Parameters:

  • artifact_name=CEngineServiceMgr_RegisterPrerequisite and func_name=CEngineServiceMgr_RegisterPrerequisite.
  • func_addr: the verified concrete entry in the assigned binary; emit func_va, func_rva = VA - image_base and the verified current func_size. Never emit a bodyless slot-only result for this target.
  • vtable_name=CEngineServiceMgr_vtable2, current vfunc_index and vfunc_offset = index * 8.
  • vfunc_sig=None and vfunc_sig_disp=None; this target describes a concrete function, not a caller's vcall.
  • func_sig=None; ensure the field is absent in the written YAML.

Write only CEngineServiceMgr_RegisterPrerequisite.windows.yaml / CEngineServiceMgr_RegisterPrerequisite.linux.yaml as applicable, under the active artifact module directory. The trusted analyzer validates and canonicalizes this semantic payload. Read back the output and verify its name, fields, slot (when applicable), RVA and platform against the live database before reporting success.

Failure handling

If required inputs are missing, candidates remain ambiguous, entry recovery is unsafe, or no standalone entry can be verified, stop and report the exact missing output plus the semantic evidence examined. Do not invent a signature/address, create a placeholder YAML, disable config entries, or claim that a failed lookup proves the game removed the function. Do not run the failed preprocessor as the fallback's solution.

Frequently asked questions

What does the Find CEngineServiceMgr RegisterPrerequisite AI skill do?

Recover CEngineServiceMgr_RegisterPrerequisite in CS2 engine binaries (Windows and Linux) when the find-CEngineServiceMgr_RegisterPrerequisite preprocessor fails. Verify current vtable entries and function semantics rather than reusing historical addresses or signatures. Trigger: CEngineServiceMgr_RegisterPrerequisite

Why use Find CEngineServiceMgr RegisterPrerequisite on TypingMind?

Because you install it once and use it with any model. Find CEngineServiceMgr RegisterPrerequisite 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 Find CEngineServiceMgr RegisterPrerequisite in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HLND2T/CS2_VibeSignatures/tree/main/.claude/skills/find-CEngineServiceMgr_RegisterPrerequisite. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Find CEngineServiceMgr RegisterPrerequisite?

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 Find CEngineServiceMgr RegisterPrerequisite?

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

Is the Find CEngineServiceMgr RegisterPrerequisite AI skill free?

Yes. It is published on GitHub by HLND2T 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 👇