Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Run Vcall Finder

ASecurity

Run this repository's ad hoc vcall_finder workflow for explicitly selected CS2 modules and one or more symbol names. Use when asked to temporarily find virtual calls for named symbols without registering them in a versioned analysis config.

3 stars
0 votes
0 copies
0 views
Added 9/27/2026
toolsshellapi

Works with

api

Security Analysis

A100/100

Scanned 9/27/2026

Install to Claude Code

$npx -y skills add mrc4tt/CS2_VibeSignatures --skill run-vcall-finder --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Run Vcall Finder?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Run Vcall Finder
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mrc4tt-run-vcall-finder/badge)](https://www.skillsdirectory.com/skills/mrc4tt-run-vcall-finder)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: run-vcall-finder
description: Run this repository's ad hoc vcall_finder workflow for explicitly selected CS2 modules and one or more symbol names. Use when asked to temporarily find virtual calls for named symbols without registering them in a versioned analysis config.
---

# Run VCall Finder

Run `ida_analyze_bin.py` with an explicit module list and symbol list. Never add `vcall_finder` entries to an analysis
config, use `*`, or infer additional modules or symbols.

## Resolve Inputs

1. Require one or more exact module names and one or more exact symbol names from the user. Ask for missing or ambiguous
   values before running the workflow.
2. Use the exact `GAMEVER` from the request. If omitted, read `CS2VIBE_GAMEVER` from `.env`; ask if it is absent or
   empty. Do not substitute another version.
3. Use the requested platform list. If omitted, allow the analyzer default of `windows,linux`.
4. Require `configs/<GAMEVER>.yaml` and the selected binaries under `bin/<GAMEVER>`. Do not modify the config or
   download missing binaries as part of this skill.

## Run The Analysis

Run from the repository root. Join multiple modules and symbols with commas:

```powershell
uv run ida_analyze_bin.py -gamever <GAMEVER> -configyaml configs/<GAMEVER>.yaml -modules <MODULES> -vcall_finder <SYMBOLS> -debug
```

Add `-platform <PLATFORMS>` only when the user specifies platforms. Forward user-requested `-llm_model`,
`-llm_baseurl`, `-llm_temperature`, `-llm_effort`, or `-llm_fake_as` values. Prefer `CS2VIBE_LLM_*` environment
variables for credentials and never print or persist API keys.

Do not add `-skip_error` unless the user explicitly requests best-effort processing. Do not silently retry with other
modules, symbols, platforms, game versions, or cached detail files.

The analyzer applies every requested symbol to every requested module. Split the work into separate invocations when
different symbols require different module scopes.

## Report Results

Treat exit code `0` with `Failed: 0` in the final summary as success. Report:

- the exact game version, modules, symbols, and platforms;
- the per-function detail root at `vcall_finder/<GAMEVER>/<SYMBOL>/`;
- the aggregated output at `vcall_finder/<GAMEVER>/<SYMBOL>.txt` when produced.

If the command fails, report its exit code and relevant final error or summary lines inside:

```text
<skill_error>ERROR REASON</skill_error>
```

Stop without editing configuration, deleting prior output, changing credentials, or attempting another scope.

Attribution

mrc4ttmrc4tt
View sourceMore from mrc4tt →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

ucoz-landing-skill

Playbook for creating and editing uCoz landing pages via MCP tools (`templates_tool`, `ftp_tool`, `modules_tool`). Use for tasks such as: "build a landing page", "update the homepage as a landing page", "create a promo page on the homepage", "add a lead form / menu / SEO to the homepage". Homepage: `page_list`, `page_get`; first publish — `page_update` with full `page_tmpl`; HTML edits after generation — `patch_template` (module_id=2, template_id=1), not `update_template`. Activate the mail f...

107 votes

Paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

813271 votes

Instantly Rdsthomas Mission Control

Instantly.ai cold email outreach API - manage campaigns, leads, accounts, and analytics. Use for cold email automation, lead management, campaign creation/monitoring, and email account warmup.

761 votes

Daw Music

Digital Audio Workstation usage, music composition, interactive music systems, and game audio implementation for immersive soundscapes.

761 votes

Caveman Compress

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

1074700 votes
View all in tools →