swfoc-runtime-address-hunting
Use when hunting SWFOC-specific runtime addresses, function anchors, structures, or memory regions in the SWFOC editor or swfoc_memory workspaces, especially when correlating dump evidence, debugger traces, and static analysis.
- License 许可
- MIT
- 最近更新
- 2026-11-02
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- swfoc-runtime-address-hunting
- description
- Use when hunting SWFOC-specific runtime addresses, function anchors, structures, or memory regions in the SWFOC editor or swfoc_memory workspaces, especially when correlating dump evidence, debugger traces, and static analysis.
02 资源文件 2
- 参考文档agents/openai.yaml257 B
- 参考文档references/hunting-notes.md736 B
03 SKILL.md 正文
SWFOC Runtime Address Hunting
Overview
Use this skill for SWFOC-specific native address work. The point is not just to find an address once; it is to identify a reproducible anchor that can be checked against dumps, debugger traces, and static analysis.
Workflow
- Start from the strongest existing evidence source you already have: the dump bundle, a debugger breakpoint, or a Cheat Engine value discovery.
- Confirm the target module and capture module-relative offsets immediately.
- Cross-check the same region in IDA Pro, Binary Ninja, or Ghidra before treating it as stable.
- When the finding matters across builds, route it through
$dump-to-signature-workflow. - Keep all SWFOC-specific notes tied to the real workspace artifacts, not to memory-only assumptions.
Common Mistakes
- Hunting addresses from scratch without first reading the existing SWFOC dump bundle.
- Keeping absolute addresses without module-base context.
- Mixing trainer/editor source assumptions with runtime-native evidence without proving the bridge.
Reference Map
Read references/hunting-notes.md for the exact local workspaces and the prebuilt artifact bundle to consult first.
04 同仓库更多 Skills
clarify-requirements
Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.
openmm-md
Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein / protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.
visual-review
Take screenshots of web pages and UI using Playwright for visual review and iteration
status
Diagnostic status report — shows metaswarm installation state, project setup, and potential issues
start
Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work
setup
Interactive project setup — detects your project, configures metaswarm, writes project-local files