Skip to content

mrc4tt/CS2_VibeSignatures / .claude/skills/create-preprocessor-scripts

create-preprocessor-scripts

Verified

Create a new find-XXXX preprocessor Python script from scratch (no existing SKILL.md), add configs/<GAMEVER>.yaml skill and symbol entries. Covers xref-string-based and LLM_DECOMPILE-based discovery patterns. Use when a GitHub issue or user instruction specifies a new function to find.

FileKindSize
SKILL.mdskill md69.0 KB
agents/openai.yamlconfig43 B
references/pattern-A.mdmarkdown3.2 KB
references/pattern-B.mdmarkdown3.5 KB
references/pattern-C.mdmarkdown4.5 KB
references/pattern-D.mdmarkdown2.0 KB
references/pattern-E.mdmarkdown4.1 KB
references/pattern-F.mdmarkdown6.7 KB
references/pattern-G.mdmarkdown3.0 KB
references/pattern-H.mdmarkdown3.7 KB
references/pattern-I.mdmarkdown8.7 KB
references/pattern-J.mdmarkdown5.2 KB
references/pattern-L.mdmarkdown8.4 KB
references/pattern-M.mdmarkdown11.9 KB

references/pattern-D.md

View on GitHub
# Pattern D -- Regular function via LLM_DECOMPILE

**Use when:** function is NOT virtual, discovered by decompiling a known predecessor function.

## Template

```python
#!/usr/bin/env python3
"""Preprocess script for find-{SKILL_NAME} skill."""

from ida_analyze_util import preprocess_common_skill

TARGET_FUNCTION_NAMES = [
    "{FUNC_NAME}",
]

LLM_DECOMPILE = [
    # (symbol_name, path_to_prompt, path_to_reference)
    (
        "{FUNC_NAME}",
        "prompt/call_llm_decompile.md",
        "references/{MODULE}/{PREDECESSOR_FUNC}.{platform}.yaml",
    ),
]

GENERATE_YAML_DESIRED_FIELDS = [
    # (symbol_name, generate_yaml_fields)
    (
        "{FUNC_NAME}",
        [
            "func_name",
            "func_sig",
            "func_va",
            "func_rva",
            "func_size",
        ],
    ),
]

async def preprocess_skill(
    session, skill_name, expected_outputs, old_yaml_map,
    new_binary_dir, platform, image_base, llm_config=None, debug=False,
):
    """Reuse previous gamever func_sig to locate target function(s) and write YAML."""
    return await preprocess_common_skill(
        session=session,
        expected_outputs=expected_outputs,
        old_yaml_map=old_yaml_map,
        new_binary_dir=new_binary_dir,
        platform=platform,
        image_base=image_base,
        func_names=TARGET_FUNCTION_NAMES,
        llm_decompile_specs=LLM_DECOMPILE,
        llm_config=llm_config,
        generate_yaml_desired_fields=GENERATE_YAML_DESIRED_FIELDS,
        debug=debug,
    )
```

## Checklist

- [ ] `TARGET_FUNCTION_NAMES` lists all functions the script should find
- [ ] `LLM_DECOMPILE` reference path points to the correct predecessor function YAML
- [ ] `preprocess_skill` signature includes `llm_config=None`
- [ ] `preprocess_common_skill` call passes `func_names=`, `llm_decompile_specs=`, and `llm_config=`
- [ ] No `FUNC_VTABLE_RELATIONS` (regular function, not virtual)
- [ ] configs/<GAMEVER>.yaml `expected_input` includes the predecessor YAML
- [ ] Reference YAMLs exist or generated for both platforms
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 465kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 465kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 318kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 318kUpdated Claude CodeCodexVerifiedInstall